A joint control method of smart home system based on Internet of Things

Abstract

The present invention relates to the field of smart home technology, and in particular to a smart home system joint control method based on the Internet of Things, comprising the following steps: S1: collecting relevant environmental parameter data through a sensor network installed in the home environment; S2: real-time monitoring of the operating status and energy consumption of each smart device in the home environment, and generating device status data; S3: generating an optimal joint control strategy using a predefined adaptive algorithm; S4: matching the generated joint control strategy with a user-preset life scene mode; S5: sending the control scheme to each smart device through an Internet of Things gateway; S6: optimizing and adjusting the joint control strategy according to feedback data. The present invention significantly improves the adaptability, energy efficiency and user satisfaction of the smart home system by automatically matching the control strategy with the life scene and integrating the user feedback optimization system.

Description

Technical Field

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

[0002] The development of smart home systems is increasingly integrated into modern life. By integrating sensors, controllers and user interfaces, these systems can provide automated home management, thereby improving the convenience and comfort of living. However, with the increase in the types and functions of devices, existing smart home systems are faced with the challenge of how to efficiently coordinate various devices. Traditional control strategies often rely on fixed rules or simple trigger events, which limits the adaptability and intelligence level of the system in complex environments. For example, different life scenarios (such as returning home, leaving home or sleeping mode) require different device settings, but existing systems often cannot be flexibly adjusted to meet personalized user needs.

[0003] The present invention aims to solve the deficiencies of existing smart home systems in terms of device linkage and control strategy adaptability. In the prior art, coordination between devices is usually insufficient to handle complex user scenarios and environmental changes, resulting in energy waste and poor user experience. In addition, the existing system lacks an effective mechanism to integrate user feedback for optimizing control strategies and improving system intelligence.

[0004] Therefore, developing a smart home system that can dynamically adapt to various life scenarios, automatically optimize the operating status of equipment, and adjust the control strategy according to user feedback has become the key to improving system performance and user satisfaction. Summary of the invention

[0005] Based on the above purpose, the present invention provides a smart home system joint control method based on the Internet of Things.

[0006] A smart home system joint control method based on the Internet of Things comprises the following steps:

[0007] S1: Collect relevant environmental parameter data, including temperature, humidity, light, air quality and user activity information, through a sensor network installed in the home environment;

[0008] S2: Real-time monitoring of the operating status and energy consumption of each smart device in the home environment, generating device status data;

[0009] S3: Based on the data collected in S1 and S2, the optimal joint control strategy is generated using a predefined adaptive algorithm;

[0010] S4: Match the generated joint control strategy with the life scenario mode preset by the user to determine the specific control scheme;

[0011] S5: Send the control solution to each smart device through the IoT gateway to achieve intelligent linkage and collaborative work between devices;

[0012] S6: Collect user feedback on the operation of the smart home system, and optimize and adjust the joint control strategy based on the feedback data.

[0013] Optionally, the S1 specifically includes:

[0014] S11: Configure a wireless sensor network in the home environment, including temperature sensors, humidity sensors, light sensors, air quality sensors, and motion sensors. All sensors are connected to the central control system through wireless communication protocols.

[0015] S12: Collecting environmental parameter data, the temperature sensor uses thermocouple or thermistor technology to measure environmental temperature data according to the resistance change caused by temperature change; the humidity sensor uses capacitive technology to detect the water vapor content in the air by measuring the change in dielectric constant to obtain humidity data; the light sensor uses a photodiode to convert the received light intensity into an electrical signal output to measure the light data; the air quality sensor uses an electrochemical sensor or light scattering technology to detect harmful gases and particulate matter in the air to obtain air quality data; the motion sensor uses an infrared sensor or a microwave sensor to collect user activity information data by detecting moving objects in the space;

[0016] S13: The sensor network will periodically send the collected data to the central control unit, and integrate, filter and denoise the data.

[0017] Optionally, the S2 specifically includes:

[0018] S21: Install a monitoring module on each smart device, where the monitoring module includes a current sensor, a voltage sensor, and a communication module;

[0019] S22: The monitoring module collects the working current and voltage data of the smart device in real time through the current sensor and the voltage sensor, and transmits the data to the central control unit through the communication module;

[0020] S23: The central control unit calculates the energy consumption of each smart device according to the current and voltage data collected in S22 using the formula P=U×I, where P represents power, U represents voltage, and I represents current;

[0021] S24: The central control unit generates device status data by analyzing the operation time, working mode and energy consumption of the smart device, including the on / off status of the device, the current working mode and real-time energy consumption data;

[0022] S25: The generated device status data is stored in a database of the central control unit and updated regularly.

[0023] Optionally, the S3 specifically includes:

[0024] S31: pre-processing the environmental parameter data and equipment status data collected in S1 and S2, including data cleaning, denoising and standardization;

[0025] S32: extracting characteristic parameters from the preprocessed data using a feature extraction algorithm, including ambient temperature, humidity, light intensity, air quality index, equipment operating status, and real-time energy consumption;

[0026] S33: Based on the extracted characteristic parameters, an adaptive control model is trained using historical data and a supervised learning algorithm to predict the optimal control strategy based on the input environment and equipment status data;

[0027] S34: Input the environmental parameter data and device status data collected in real time into the trained adaptive control model. The adaptive control model calculates and generates the optimal joint control strategy based on the real-time input data. The joint control strategy includes the operating status and adjustment parameters of each intelligent device.

[0028] Optionally, the S32 specifically includes:

[0029] S321: Temperature feature extraction: for the preprocessed temperature data, the sliding average algorithm is used to calculate the average temperature value within a period of time. The formula is: ,in, represents the average temperature, Indicates Temperature data at a time point, Indicates the size of the sliding window;

[0030] S322: Humidity feature extraction: For the pre-processed humidity data, the maximum and minimum values ​​algorithms are used to calculate the maximum and minimum values ​​within a period of time. The formula is:

[0031] ; ,in, and Represents the maximum humidity and minimum humidity respectively. Indicates Humidity data at a time point, Indicates the total number of data points in the time period;

[0032] S323: Light feature extraction: for the pre-processed light data, the standard deviation algorithm is used to calculate the fluctuation of light intensity. The formula is: ,in, represents the standard deviation of light intensity, Indicates Light data at each time point, Represents the average value of illumination data;

[0033] S324: Extract air quality features. For the pre-processed air quality data, use a weighted average algorithm to calculate the air quality index over a period of time. The formula is: ,in, represents the weighted average air quality index, Indicates Air quality data at a given time point, Indicates The weight value at each time point, Indicates the total number of data points in the time period;

[0034] S325: User activity feature extraction: For the pre-processed user activity data, a frequency analysis algorithm is used to calculate the frequency features of the user activity. The formula is: ,in, Represents the user activity frequency characteristics, Indicates User activity data at a point in time, Indicates the total time period, Represents the total number of data points in the time period.

[0035] Optionally, the S33 specifically includes:

[0036] S331: extracting preprocessed feature parameters from the historical data set to form a training data set and a validation data set, the feature parameters including temperature, humidity, light intensity, air quality index, and user activity frequency;

[0037] S332: Feature vector construction, combining the feature parameter values ​​at each time point into a feature vector : ;

[0038] S333: Target variable definition, define the target variable according to the actual control strategy and equipment status in the historical data , the target variable represents the optimal control strategy corresponding to each eigenvector;

[0039] S334: Select the multi-layer perceptron algorithm in the supervised learning algorithm for model training. The model structure of the multi-layer perceptron is: ,in, represents the multi-layer perceptron model, represents the model parameters;

[0040] S335: Define loss function To evaluate the error between the control strategy predicted by the model and the target variable, the loss function uses the mean square error, and the formula is: ,in, represents the control strategy predicted by the model, represents the target control strategy, represents the number of samples;

[0041] S336: Use back propagation algorithm and gradient descent algorithm to minimize the loss function and update model parameters , the formula is: ,in, represents the learning rate, Represents the gradient of the loss function with respect to the model parameters;

[0042] S337: Use the validation data set to evaluate the performance of the trained model and optimize the model by adjusting the hyperparameters until the validation error of the model is minimized.

[0043] Optionally, the S4 specifically includes:

[0044] S41: defining a plurality of preset life scene modes, specifically including a home mode, a leaving mode, a sleeping mode, an entertainment mode, and a reading mode;

[0045] S42: Setting trigger conditions for each life scenario mode, including time setting, user location or scheduled activity recognition;

[0046] S43: matching the optimal control strategy generated in S3 with the corresponding life scenario mode;

[0047] S44: The smart home system automatically executes corresponding control strategies according to the matching results.

[0048] Optionally, the S43 specifically includes:

[0049] S431: Analyze the optimal control strategy generated by S3, extract the specific control parameters and status information of each smart device, and form a control vector : ,in Indicates Control parameters of each device;

[0050] S432: Defining a target parameter vector for each life scenario mode : ,in, Indicated in In scene mode Target control parameters of each device;

[0051] S433: Calculate the similarity between the optimal control strategy and each life scenario model, and use the Euclidean distance formula to calculate the control vector With the target parameter vector The distance between them is: ,in, Represents the control vector With The target parameter vector of the scene mode The Euclidean distance between Indicates the number of smart devices;

[0052] S434: Select the scene mode with the highest similarity, i.e., distance Minimum target parameter vector , as the matching scenario for the current optimal control strategy.

[0053] Optionally, the S5 specifically includes:

[0054] S51: Configure a central IoT gateway in the home network to manage and coordinate all connected smart devices. The IoT gateway supports multiple communication protocols, including WiFi, Zigbee, and Bluetooth.

[0055] S52: Generate a specific control command according to the life scenario mode and the optimal control strategy matched in S4, the control command including the target state and operation instruction of each smart device;

[0056] S53: The IoT gateway sends the control command to each smart device through a predefined communication protocol;

[0057] S54: The IoT gateway monitors the response status of each smart device in real time to ensure that the device correctly executes the control command and feeds back the execution result;

[0058] S55: Based on the operating status and real-time feedback of smart devices, the IoT gateway makes dynamic adjustments to ensure linkage and collaborative work between devices.

[0059] Optionally, the S6 specifically includes:

[0060] S61: Collect user feedback on the operation of the smart home system through the user interface of the smart home system, including satisfaction ratings, suggestions and specific questions;

[0061] S62: Classify the collected feedback data into positive feedback and negative feedback, and store them in different databases respectively;

[0062] S63: Analyze negative feedback data, identify problems or deficiencies in system operation, extract relevant feature parameters, and form a problem vector : ,in Indicates Problem characteristic parameters;

[0063] S64: Based on the problem vector , use the weighted summation method to determine the control strategy part that needs to be optimized, the formula is: ,in, Indicates the part of the strategy that needs to be optimized, Indicates The weight of the characteristic parameters of each problem;

[0064] S65: According to the determined optimization requirements, the joint control strategy is adjusted using an adaptive algorithm to generate a new control strategy, the formula is: ,in, represents the existing control strategy, Indicates the adjustment amount.

[0065] Beneficial effects of the present invention:

[0066] The present invention, by accurately matching the preset life scene mode with the optimal control strategy, the system can automatically adjust the device status to adapt to the specific needs of different scenarios such as returning home, leaving home, sleeping, etc. This intelligent adjustment not only ensures the comfort and convenience of the living environment, but also reduces energy consumption by optimizing the equipment operation efficiency, thereby achieving both economic and ecological benefits.

[0067] The present invention adopts a control strategy optimization mechanism driven by user feedback, so that the smart home system can continuously learn and improve its performance. By analyzing user satisfaction feedback and system execution data, the system can dynamically adjust the control strategy to better meet the user's actual usage habits and preferences. This adaptive adjustment not only improves user satisfaction, but also enhances the intelligence level of the system, making the smart home system more humane and meeting the high standards of modern life. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0069] Figure 1 A schematic diagram of a smart home system joint control method according to an embodiment of the present invention;

[0070] Figure 2 The present invention provides a schematic diagram of the process of matching the living scene mode with the control strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0072] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0073] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0074] like Figure 1-Figure 2 As shown, a smart home system joint control method based on the Internet of Things includes the following steps:

[0075] S1: Collect relevant environmental parameter data, including temperature, humidity, light, air quality and user activity information, through a sensor network installed in the home environment;

[0076] S2: Real-time monitoring of the operating status and energy consumption of each smart device in the home environment, generating device status data;

[0077] S3: Based on the data collected in S1 and S2, the optimal joint control strategy is generated using a predefined adaptive algorithm;

[0078] S4: matching the generated joint control strategy with the user's preset life scenario mode (such as home mode, leaving mode, and sleeping mode) to determine a specific control plan;

[0079] S5: Send the control solution to each smart device through the IoT gateway to achieve intelligent linkage and collaborative work between devices;

[0080] S6: Collect user feedback on the operation of the smart home system, and optimize and adjust the joint control strategy based on the feedback data to improve the intelligence level of the system.

[0081] S1 specifically includes:

[0082] S11: Configure a wireless sensor network in the home environment, including temperature sensors, humidity sensors, light sensors, air quality sensors, and motion sensors. All sensors are connected to the central control system through wireless communication protocols such as Zigbee, WiFi, or Bluetooth.

[0083] S12: Collect environmental parameter data. The temperature sensor uses thermocouple or thermistor technology to measure environmental temperature data based on the resistance change caused by temperature change. The humidity sensor uses capacitive technology to detect the water vapor content in the air by measuring the change in dielectric constant to obtain humidity data. The light sensor uses a photodiode to convert the received light intensity into an electrical signal output to measure the light data. The air quality sensor uses an electrochemical sensor or light scattering technology to detect harmful gases and particulate matter in the air, such as CO2 and PM2.5, to obtain air quality data. The motion sensor uses an infrared sensor or a microwave sensor to collect user activity information data by detecting moving objects in the space.

[0084] S13: The sensor network will periodically send the collected data to the central control unit, and integrate, filter and denoise the data to ensure the accuracy and availability of the data;

[0085] By combining the above steps, key parameter data in the home environment, such as temperature, humidity, light, air quality and user activity information, can be accurately collected. This precise data collection provides high-quality input for subsequent joint control strategies, enabling the smart home system to respond more effectively to environmental changes and user needs, thereby improving the intelligence level of the entire system and the user's living experience.

[0086] S2 specifically includes:

[0087] S21: Install a monitoring module on each smart device, where the monitoring module includes a current sensor, a voltage sensor, and a communication module;

[0088] S22: The monitoring module collects the working current and voltage data of the smart device in real time through the current sensor and the voltage sensor, and transmits the data to the central control unit through the communication module;

[0089] S23: The central control unit calculates the energy consumption of each smart device according to the current and voltage data collected in S22 using the formula P=U×I, where P represents power, U represents voltage, and I represents current;

[0090] S24: The central control unit generates device status data by analyzing the operation time, working mode and energy consumption of the smart device, including the on / off status of the device, the current working mode and real-time energy consumption data;

[0091] S25: The generated device status data is stored in a database of the central control unit and updated regularly to ensure the real-time and accuracy of the device status data.

[0092] S3 specifically includes:

[0093] S31: Preprocess the environmental parameter data and equipment status data collected in S1 and S2, including data cleaning, denoising and standardization, to ensure the accuracy and consistency of the data;

[0094] S32: extracting characteristic parameters from the preprocessed data using a feature extraction algorithm, including ambient temperature, humidity, light intensity, air quality index, equipment operating status, and real-time energy consumption;

[0095] S33: Based on the extracted characteristic parameters, an adaptive control model is trained using historical data and a supervised learning algorithm to predict the optimal control strategy based on the input environment and equipment status data;

[0096] S34: The environmental parameter data and device status data collected in real time are input into the trained adaptive control model. The adaptive control model calculates and generates the optimal joint control strategy based on the real-time input data. The joint control strategy includes the operating status and adjustment parameters of each smart device to achieve the best energy efficiency and user comfort. Through the above steps, it is ensured that the system can achieve the best energy efficiency and user comfort under different environmental conditions. Through this optimized joint control strategy, the smart home system can not only improve energy utilization efficiency, but also significantly improve the user's living experience, and has significant technical advantages and application prospects.

[0097] The characteristic parameters extracted in S32 specifically include:

[0098] S321: Temperature feature extraction: for the preprocessed temperature data, the sliding average algorithm is used to calculate the average temperature value within a period of time. The formula is: ,in, represents the average temperature, Indicates Temperature data at a time point, Indicates the size of the sliding window;

[0099] S322: Humidity feature extraction: For the pre-processed humidity data, the maximum and minimum values ​​algorithms are used to calculate the maximum and minimum values ​​within a period of time. The formula is:

[0100] ; ,in, and Represents the maximum humidity and minimum humidity respectively. Indicates Humidity data at a time point, Indicates the total number of data points in the time period;

[0101] S323: Light feature extraction: for the pre-processed light data, the standard deviation algorithm is used to calculate the fluctuation of light intensity. The formula is: ,in, represents the standard deviation of light intensity, Indicates Light data at each time point, Represents the average value of illumination data;

[0102] S324: Extract air quality features. For the pre-processed air quality data, use a weighted average algorithm to calculate the air quality index over a period of time. The formula is: ,in, represents the weighted average air quality index, Indicates Air quality data at a given time point, Indicates The weight value at each time point, Indicates the total number of data points in the time period;

[0103] S325: User activity feature extraction: For the pre-processed user activity data, a frequency analysis algorithm is used to calculate the frequency features of the user activity. The formula is: ,in, Represents the user activity frequency characteristics, Indicates User activity data at a point in time, Indicates the total time period, Represents the total number of data points in a time period; the above steps are refined by the feature extraction algorithm of temperature, humidity, light, air quality and user activity data. This dependent claim clarifies the method of extracting key feature parameters using a predefined algorithm. The precise extraction of these feature parameters provides high-quality input data for the subsequent joint control strategy, ensuring the accuracy and effectiveness of the control strategy, thereby improving the intelligence level of the smart home system and user experience.

[0104] The training of the adaptive control model in S33 specifically includes:

[0105] S331: extracting preprocessed feature parameters from the historical data set to form a training data set and a validation data set, the feature parameters including temperature, humidity, light intensity, air quality index, and user activity frequency;

[0106] S332: Feature vector construction, combining the feature parameter values ​​at each time point into a feature vector : ;

[0107] S333: Target variable definition, define the target variable according to the actual control strategy and equipment status in the historical data , the target variable represents the optimal control strategy corresponding to each eigenvector;

[0108] S334: Select the multi-layer perceptron (MLP) algorithm in the supervised learning algorithm for model training. The model structure of the multi-layer perceptron is: ,in, represents the multi-layer perceptron model, represents the model parameters;

[0109] S335: Define loss function To evaluate the error between the control strategy predicted by the model and the target variable, the loss function uses the mean square error (MSE), and the formula is: ,in, represents the control strategy predicted by the model, represents the target control strategy, represents the number of samples;

[0110] S336: Use back propagation algorithm and gradient descent algorithm to minimize the loss function and update model parameters , the formula is: ,in, represents the learning rate, Represents the gradient of the loss function with respect to the model parameters;

[0111] S337: Use the validation data set to evaluate the performance of the trained model, and optimize the model by adjusting hyperparameters (such as learning rate, number of hidden layers, etc.) until the validation error of the model is minimized; the adaptive control model trained through the above steps can predict the optimal control strategy based on the input environment and device status data, thereby achieving precise control and optimization of the smart home system, improving the energy efficiency of the system and the comfort of users, and has significant technical advantages and application prospects.

[0112] S4 specifically includes:

[0113] S41: defining multiple preset life scene modes, including home mode, leaving mode, sleeping mode, entertainment mode and reading mode; wherein the home mode is used to automatically adjust the home environment when the user arrives home, such as turning on lights, adjusting the air conditioner to a comfortable temperature, playing relaxing music, etc.;

[0114] Away mode is used to automatically shut down non-essential devices when the user leaves home, such as turning off lights and TV, setting up security systems, etc.

[0115] The sleep mode is used to adjust the indoor lighting and temperature according to the external environment when the user is sleeping to ensure a comfortable sleeping environment;

[0116] Entertainment mode is used to adjust the lighting and sound system to create a suitable entertainment atmosphere during family gatherings or watching movies;

[0117] Reading mode is used to provide appropriate lighting and indoor temperature, reduce distractions, and create a good reading environment;

[0118] S42: Setting trigger conditions for each life scenario mode, including time setting, user location or scheduled activity recognition;

[0119] S43: According to the optimal control strategy generated by S3, it is matched with the corresponding life scene mode to ensure that the device settings in each scene are most suitable for the environmental requirements;

[0120] S44: The smart home system automatically executes the corresponding control strategy according to the matching results without the need for manual intervention by the user, thereby improving the automation and user experience of the smart home system; by defining specific life scenario modes and accurately matching these scenarios with the control strategy of the smart home system, the smart home system can respond to the user's life needs more intelligently and automatically, which not only improves the user's living comfort and convenience, but also optimizes energy efficiency by accurately controlling the operation of home appliances.

[0121] S43 specifically includes:

[0122] S431: Analyze the optimal control strategy generated by S3, extract the specific control parameters and status information of each smart device, and form a control vector : ,in Indicates Control parameters of each device;

[0123] S432: Defining a target parameter vector for each life scenario mode : ,in, Indicated in In scene mode Target control parameters of each device;

[0124] S433: Calculate the similarity between the optimal control strategy and each life scenario model, and use the Euclidean distance formula to calculate the control vector With the target parameter vector The distance between them is: ,in, Represents the control vector With The target parameter vector of the scene mode The Euclidean distance between Indicates the number of smart devices;

[0125] S434: Select the scene mode with the highest similarity, i.e., distance Minimum target parameter vector , as the matching scenario of the current optimal control strategy; through the steps of control strategy analysis, scenario parameter definition, similarity calculation and optimal matching selection, the similarity is calculated using Euclidean distance to ensure that the control strategy can accurately adapt to the user's preset life scenarios, thereby improving the response accuracy and user experience of the smart home system.

[0126] S5 specifically includes:

[0127] S51: Configure a central IoT gateway in the home network to manage and coordinate all connected smart devices. The IoT gateway supports multiple communication protocols, including WiFi, Zigbee, and Bluetooth.

[0128] S52: Generate a specific control command according to the life scenario mode and the optimal control strategy matched in S4, the control command including the target state and operation instruction of each smart device;

[0129] S53: The IoT gateway sends control commands to each smart device through a predefined communication protocol to ensure that each device can receive the corresponding command and respond;

[0130] S54: The IoT gateway monitors the response status of each smart device in real time to ensure that the device correctly executes the control command and feeds back the execution result;

[0131] S55: Based on the operating status and real-time feedback of smart devices, the IoT gateway makes dynamic adjustments to ensure linkage and collaboration between devices to avoid conflicts and waste of resources.

[0132] S6 specifically includes:

[0133] S61: Collect user feedback on the operation of the smart home system through the user interface of the smart home system (such as a mobile phone application or voice assistant), including satisfaction ratings, suggestions, and specific questions;

[0134] S62: Classify the collected feedback data into positive feedback and negative feedback, and store them in different databases respectively;

[0135] S63: Analyze negative feedback data, identify problems or deficiencies in system operation, extract relevant feature parameters, and form a problem vector : ,in Indicates Problem characteristic parameters;

[0136] S64: Based on the problem vector , use the weighted summation method to determine the control strategy part that needs to be optimized, the formula is: ,in, Indicates the part of the strategy that needs to be optimized, Indicates The weight of the characteristic parameters of each problem;

[0137] S65: According to the determined optimization requirements, the joint control strategy is adjusted using an adaptive algorithm to generate a new control strategy, the formula is: ,in, represents the existing control strategy, Represents the adjustment amount; and applies the new control strategy to the smart home system, verifies the effectiveness of the strategy and user satisfaction through small-scale experiments or simulation tests; through systematic feedback analysis and optimization processes, the smart home system can quickly respond to user needs, solve problems in operation, and continuously improve the system's intelligence level and user satisfaction.

[0138] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0139] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A joint control method for a smart home system based on the Internet of Things, characterized in that: The following steps are involved: S1: Collect relevant environmental parameter data, including temperature, humidity, light, air quality and user activity information, through a sensor network installed in the home environment; S2: Real-time monitoring of the operating status and energy consumption of each smart device in the home environment, generating device status data; S3: Based on the data collected in S1 and S2, the optimal joint control strategy is generated using a predefined adaptive algorithm, including: S31: pre-processing the environmental parameter data and equipment status data collected in S1 and S2, including data cleaning, denoising and standardization; S32: extracting characteristic parameters from the preprocessed data using a feature extraction algorithm, including ambient temperature, humidity, light intensity, air quality index, equipment operating status, and real-time energy consumption; S33: Based on the extracted characteristic parameters, an adaptive control model is trained using historical data and a supervised learning algorithm to predict the optimal control strategy based on the input environment and equipment status data; S34: inputting the environmental parameter data and device status data collected in real time into the trained adaptive control model, and the adaptive control model calculates and generates an optimal joint control strategy based on the real-time input data, and the joint control strategy includes the operating status and adjustment parameters of each intelligent device; The S32 specifically includes: S321: Temperature feature extraction: for the preprocessed temperature data, the sliding average algorithm is used to calculate the average temperature value within a period of time. The formula is: ,in, represents the average temperature, Indicates Temperature data at a time point, Indicates the size of the sliding window; S322: Humidity feature extraction: For the pre-processed humidity data, the maximum and minimum values ​​algorithms are used to calculate the maximum and minimum values ​​within a period of time. The formula is: ; ,in, and Represents the maximum humidity and minimum humidity respectively. Indicates Humidity data at a time point, Indicates the total number of data points in the time period; S323: Light feature extraction: for the pre-processed light data, the standard deviation algorithm is used to calculate the fluctuation of light intensity. The formula is: ,in, represents the standard deviation of light intensity, Indicates Light data at a time point, Represents the average value of illumination data; S324: Extract air quality features. For the pre-processed air quality data, use a weighted average algorithm to calculate the air quality index over a period of time. The formula is: ,in, represents the weighted average air quality index, Indicates Air quality data at a given time point, Indicates The weight value at each time point, Indicates the total number of data points in the time period; S325: User activity feature extraction: For the pre-processed user activity data, a frequency analysis algorithm is used to calculate the frequency features of the user activity. The formula is: ,in, Represents the user activity frequency characteristics, Indicates User activity data at a point in time, Indicates the total time period, Indicates the total number of data points in the time period; The S33 specifically includes: S331: extracting preprocessed feature parameters from the historical data set to form a training data set and a validation data set, the feature parameters including temperature, humidity, light intensity, air quality index, and user activity frequency; S332: Feature vector construction, combining the feature parameter values ​​at each time point into a feature vector : ; S333: Target variable definition, define the target variable according to the actual control strategy and equipment status in the historical data , the target variable represents the optimal control strategy corresponding to each eigenvector; S334: Select the multi-layer perceptron algorithm in the supervised learning algorithm for model training. The model structure of the multi-layer perceptron is: ,in, represents the multi-layer perceptron model, represents the model parameters; S335: Define loss function To evaluate the error between the control strategy predicted by the model and the target variable, the loss function uses the mean square error, and the formula is: ,in, represents the control strategy predicted by the model, represents the target control strategy, represents the number of samples; S336: Use back propagation algorithm and gradient descent algorithm to minimize the loss function and update model parameters , the formula is: ,in, represents the learning rate, Represents the gradient of the loss function with respect to the model parameters; S337: Use the validation data set to evaluate the performance of the trained model and optimize the model by adjusting the hyperparameters until the validation error of the model is minimized; S4: Match the generated joint control strategy with the life scenario mode preset by the user to determine the specific control scheme; S5: Send the control solution to each smart device through the IoT gateway to achieve intelligent linkage and collaborative work between devices; S6: Collect user feedback on the operation of the smart home system, and optimize and adjust the joint control strategy based on the feedback data.

2. The method for joint control of a smart home system based on the Internet of Things according to claim 1, characterized in that: The S1 specifically includes: S11: Configure a wireless sensor network in the home environment, including temperature sensors, humidity sensors, light sensors, air quality sensors, and motion sensors. All sensors are connected to the central control system through wireless communication protocols. S12: Collecting environmental parameter data, the temperature sensor uses thermocouple or thermistor technology to measure environmental temperature data according to the resistance change caused by temperature change; the humidity sensor uses capacitive technology to detect the water vapor content in the air by measuring the change in dielectric constant to obtain humidity data; the light sensor uses a photodiode to convert the received light intensity into an electrical signal output to measure the light data; the air quality sensor uses an electrochemical sensor or light scattering technology to detect harmful gases and particulate matter in the air to obtain air quality data; the motion sensor uses an infrared sensor or a microwave sensor to collect user activity information data by detecting moving objects in the space; S13: The sensor network will periodically send the collected data to the central control unit, and integrate, filter and denoise the data.

3. The method for joint control of a smart home system based on the Internet of Things according to claim 1, characterized in that: The S2 specifically includes: S21: Install a monitoring module on each smart device, where the monitoring module includes a current sensor, a voltage sensor, and a communication module; S22: The monitoring module collects the working current and voltage data of the smart device in real time through the current sensor and the voltage sensor, and transmits the data to the central control unit through the communication module; S23: The central control unit calculates the energy consumption of each smart device according to the current and voltage data collected in S22 using the formula P=U×I, where P represents power, U represents voltage, and I represents current; S24: The central control unit generates device status data by analyzing the operation time, working mode and energy consumption of the smart device, including the on / off status of the device, the current working mode and real-time energy consumption data; S25: The generated device status data is stored in a database of the central control unit and updated regularly.

4. The method for joint control of a smart home system based on the Internet of Things according to claim 1, characterized in that: The S4 specifically includes: S41: defining a plurality of preset life scene modes, specifically including a home mode, a leaving mode, a sleeping mode, an entertainment mode, and a reading mode; S42: Setting trigger conditions for each life scenario mode, including time setting, user location or scheduled activity recognition; S43: matching the optimal control strategy generated in S3 with the corresponding life scenario mode; S44: The smart home system automatically executes corresponding control strategies according to the matching results.

5. The method for joint control of a smart home system based on the Internet of Things according to claim 4, characterized in that: The S43 specifically includes: S431: Analyze the optimal control strategy generated by S3, extract the specific control parameters and status information of each smart device, and form a control vector : ,in Indicates Control parameters of each device; S432: Defining a target parameter vector for each life scenario mode : ,in, Indicated in In scene mode Target control parameters of each device; S433: Calculate the similarity between the optimal control strategy and each life scenario model, and use the Euclidean distance formula to calculate the control vector With the target parameter vector The distance between them is: ,in, Represents the control vector With The target parameter vector of the scene mode The Euclidean distance between Indicates the number of smart devices; S434: Select the scene mode with the highest similarity, i.e., distance Minimum target parameter vector , as the matching scenario for the current optimal control strategy.

6. The method for joint control of a smart home system based on the Internet of Things according to claim 1, characterized in that: The S5 specifically includes: S51: Configure a central IoT gateway in the home network to manage and coordinate all connected smart devices. The IoT gateway supports multiple communication protocols, including WiFi, Zigbee, and Bluetooth. S52: Generate a specific control command according to the life scenario mode and the optimal control strategy matched in S4, the control command including the target state and operation instruction of each smart device; S53: The IoT gateway sends the control command to each smart device through a predefined communication protocol; S54: The IoT gateway monitors the response status of each smart device in real time to ensure that the device correctly executes the control command and feeds back the execution result; S55: Based on the operating status and real-time feedback of smart devices, the IoT gateway makes dynamic adjustments to ensure linkage and collaborative work between devices.

7. The method for joint control of a smart home system based on the Internet of Things according to claim 1, characterized in that: The S6 specifically includes: S61: Collect user feedback on the operation of the smart home system through the user interface of the smart home system, including satisfaction ratings, suggestions and specific questions; S62: Classify the collected feedback data into positive feedback and negative feedback, and store them in different databases respectively; S63: Analyze negative feedback data, identify problems or deficiencies in system operation, extract relevant feature parameters, and form a problem vector : ,in Indicates Problem characteristic parameters; S64: Based on the problem vector , use the weighted summation method to determine the control strategy part that needs to be optimized, the formula is: ,in, Indicates the part of the strategy that needs to be optimized, Indicates The weight of the characteristic parameters of each problem; S65: According to the determined optimization requirements, the joint control strategy is adjusted using an adaptive algorithm to generate a new control strategy, the formula is: ,in, represents the existing control strategy, Indicates the adjustment amount.

Images