Smart home Internet of Things control system based on WIFI

Abstract

The invention relates to the technical field of Internet of Things control of smart home, and particularly discloses a smart home Internet of Things control system based on WIFI, which monitors sound wave frequency change and air pressure fluctuation in an environment in real time through a sound wave sensor and an air pressure sensor built in a smart door lock, and obtains accurate sound wave sensing data and air pressure sensing data. The data evaluation module uses Haar wavelet transform and fast Fourier transform to calculate abnormal sound wave characteristic values and air pressure abnormal characteristic values respectively, whether potential security threats exist in the smart home environment is evaluated, the smart home security prediction module constructs the characteristic values into comprehensive characteristic vectors, the comprehensive characteristic vectors are input into a support vector machine model to be analyzed, and the safety of the smart home environment is improved. And the intelligent home control module automatically switches to a safety protection mode once a potential risk is detected, and executes a series of preset safety measures, such as activating a security camera, locking doors and windows, starting an alarm system and informing residents.

Description

Technical Field

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

[0002] With the continuous development of smart home technology, smart door locks, as the first line of defense for home security, have gradually become a vital component of modern smart home systems. Smart door locks not only provide convenient keyless entry but also integrate a variety of sensors and communication modules, such as acoustic sensors, air pressure sensors, and Wi-Fi connectivity, to enable real-time environmental monitoring and remote control. However, in practical applications, existing smart door locks still face some significant challenges when facing complex and changing security threats.

[0003] The existing technology has the following deficiencies:

[0004] Current smart home systems, such as smart door locks, rely on simple unlocking and locking status monitoring and basic intrusion detection, but lack effective recognition of complex abnormal behaviors (such as illegal intrusions through airflow changes or subtle sound patterns). Their environmental perception capabilities are limited, failing to fully capture all potential threats in the surrounding environment. For example, they overlook rapid airflow changes caused by the sudden opening of doors and windows, and unusual sound patterns caused by illegal intrusions. The lack of effective integration and analysis of multi-source data leads to high false alarm rates, with minor environmental changes potentially being mistaken for illegal intrusions, impacting the user experience. Furthermore, existing systems have limited data analysis and processing capabilities, resulting in untimely responses that may miss the optimal opportunity for response. These limitations reduce the overall security and reliability of smart home systems.

[0005] To address these issues, the present invention proposes a Wi-Fi-based smart home IoT control system. This system integrates data from acoustic and air pressure sensors, uses advanced signal processing techniques (such as Haar wavelet transform and fast Fourier transform) to calculate anomaly eigenvalues, and combines this with a support vector machine model to construct a smart home security prediction model. This system enables accurate assessment and immediate response to potential risks in smart home environments. This not only improves the system's detection accuracy and reduces false alarm rates, but also enhances its ability to learn from unknown threat patterns, ensuring effective protection against potential safety hazards even in unattended environments. This provides users with a more intelligent and secure living environment. Summary of the Invention

[0006] The purpose of the present invention is to provide a WIFI-based smart home IoT control system to solve the above-mentioned problems.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] WIFI-based smart home IoT control system, including:

[0009] A data acquisition module, wherein during the smart home monitoring cycle, the smart door lock uses a built-in sound wave sensor and air pressure sensor to monitor the sound wave frequency changes and air pressure fluctuations in the environment in real time, and obtains sound wave sensing data and air pressure sensing data;

[0010] A data evaluation module, which determines abnormal sound wave characteristic values ​​based on the degree of sound wave frequency change to evaluate whether the smart home has abnormal sound wave changes; and simultaneously determines abnormal air pressure characteristic values ​​based on the air pressure wave amplitude to evaluate whether the smart home has abnormal airflow changes;

[0011] A smart home safety prediction module, which comprehensively analyzes abnormal sound wave characteristic values ​​and abnormal air pressure characteristic values, and constructs a smart home safety prediction model to predict whether there are potential risks in the smart home environment;

[0012] The smart home control module switches the smart home environment from a normal mode to a safety protection mode based on the prediction result if there is a potential risk in the smart home environment.

[0013] As a further solution of the present invention, the step of evaluating whether there are abnormal sound wave changes in the smart home specifically includes:

[0014] During the smart home monitoring cycle, the smart door lock collects the sound wave frequency in the smart home environment in real time through the built-in sound wave sensor, calculates the abnormal sound wave characteristic value based on the change amplitude of the sound wave frequency in the environment, and determines whether the abnormal sound wave characteristic value is greater than or equal to the preset threshold. If so, there is abnormal sound wave change in the smart home; if not, there is no abnormal sound wave change in the smart home.

[0015] As a further solution of the present invention: the process of obtaining the abnormal sound wave characteristic value is:

[0016] During the smart home monitoring cycle, the smart door lock collects real-time sound wave frequency data in the smart home environment through the built-in sound wave sensor;

[0017] Calculate the amplitude of the sound wave frequency change at adjacent moments in the smart home environment to obtain the sound wave frequency change value at adjacent moments;

[0018] The calculated sound wave frequency change values ​​at adjacent moments are integrated according to the time series. The time series of the integrated sound wave frequency change values ​​at adjacent moments is applied with the Haar wavelet transform to extract the energy information of different scales and calculate the Haar wavelet coefficients. For each scale j, the squares of the Haar wavelet coefficients of the corresponding scale are summed to obtain the energy of the corresponding scale. The energy of all scale levels is accumulated to obtain the abnormal sound wave characteristic value.

[0019] As a further solution of the present invention, the step of evaluating whether abnormal airflow changes occur in a smart home specifically includes:

[0020] During the smart home monitoring cycle, the smart door lock monitors the air pressure sensing data in the smart home environment in real time through the built-in air pressure sensor, calculates the air pressure abnormality characteristic value based on the air pressure fluctuation amplitude in the smart home environment, and determines whether the air pressure abnormality characteristic value is greater than or equal to the preset threshold. If so, abnormal airflow changes have occurred in the smart home; if not, abnormal airflow changes have not occurred in the smart home.

[0021] As a further solution of the present invention: the process of obtaining the abnormal air pressure characteristic value is as follows:

[0022] During the smart home monitoring cycle, the smart door lock collects the air pressure sensing data in the smart home environment at fixed time intervals through the built-in air pressure sensor during the monitoring cycle to obtain an air pressure data sequence;

[0023] Calculate the absolute value of the pressure difference between adjacent time points, integrate the absolute value of the pressure difference into a pressure fluctuation amplitude sequence, and apply fast Fourier transform to the pressure fluctuation amplitude sequence to convert it into the frequency domain to obtain the frequency domain coefficient;

[0024] Calculate the square of the modulus of the frequency domain coefficient of each frequency component to obtain the energy spectrum density of each frequency component;

[0025] Calculate the mean of the energy spectral density of all frequency components, compare the energy spectral density of all frequency components with the mean of the energy spectral density, record the frequency component whose energy spectral density is greater than the mean of the energy spectral density as the high-frequency part, and calculate the ratio of the sum of the energy spectral density of all high-frequency parts to the energy spectral density of all frequency components to obtain the characteristic value of the air pressure anomaly.

[0026] As a further solution of the present invention: the comprehensive analysis of the abnormal sound wave characteristic value and the abnormal air pressure characteristic value specifically includes:

[0027] During the smart home monitoring cycle, the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​are obtained, and the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​are constructed into a comprehensive characteristic vector as the input of the smart home security prediction model to minimize the error between the predicted smart home security score and the actual smart home security score. As the training target of the model, the smart home security score is output according to the trained model.

[0028] As a further solution of the present invention: the construction process of the smart home security prediction model is:

[0029] The smart home safety prediction model is constructed using a support vector machine model. Specifically, the model uses historical abnormal sound wave eigenvalues, abnormal air pressure eigenvalues, and safety scores as labels to construct a supervised learning dataset. The support vector machine model is used to train the dataset with the goal of minimizing the error between the predicted safety score and the actual safety score. By selecting a radial basis function (RBF), adjusting the penalty coefficient and kernel function parameters, and optimizing model performance, a smart home safety prediction model that can accurately predict the smart home safety score is obtained after multiple iterations.

[0030] As a further solution of the present invention: the predicting whether there is a potential risk in the smart home environment specifically includes:

[0031] According to the security score output by the smart home security prediction model, it is determined whether the security score of the smart home is greater than or equal to a preset threshold. If so, there is a potential risk in the smart home environment; if not, there is no potential risk in the smart home environment.

[0032] As a further solution of the present invention: switching the smart home environment from the normal mode to the safety protection mode specifically includes:

[0033] Based on the risk prediction results of the smart home environment, if it is determined that there is a potential risk in the smart home environment, the smart home environment will be switched from normal mode to safety protection mode, and the switching program will be immediately started to adjust the working status of various smart home devices, including activating security cameras, locking all doors and windows, turning on the alarm system, and notifying residents to ensure that the smart home environment quickly enters safety protection mode.

[0034] Beneficial effects of the present invention:

[0035] (1) The present invention integrates the data of the acoustic wave sensor and the air pressure sensor and uses advanced signal processing technologies such as Haar wavelet transform and fast Fourier transform to calculate the abnormal acoustic wave characteristic value and the abnormal air pressure characteristic value respectively, thereby achieving an accurate assessment of potential security threats in the smart home environment. Once the system detects an abnormal situation, it will immediately switch from normal mode to security protection mode and automatically activate a series of preset security measures, including but not limited to starting the security camera for real-time monitoring, automatically locking all doors and windows to prevent external intrusion, triggering the alarm system to send a warning signal, and immediately notifying residents or other designated contacts, so as to respond to potential threats in the shortest time. This integrated real-time monitoring and intelligent response mechanism can effectively prevent safety hazards even in unattended situations, greatly improving home security and emergency response efficiency, and providing users with a more secure and intelligent living environment. In addition, by optimizing the support vector machine model and its parameter settings, the present invention further enhances the accuracy and reliability of the prediction model, ensuring that each security assessment can be based on the most accurate data analysis results, bringing the protection capability of the smart home system to a new level.

[0036] (2) The present invention uses a support vector machine model to comprehensively analyze the abnormal sound wave characteristic values ​​and abnormal air pressure characteristic values ​​obtained from the sound wave sensor and the air pressure sensor, and constructs an efficient smart home security prediction model, which aims to accurately predict the potential security risks in the smart home environment. By carefully selecting the radial basis function as the kernel function and fine-tuning the penalty coefficient and the kernel function parameter γ, the model can avoid overfitting while ensuring high accuracy, ensuring that the output security score has high reliability and accuracy. Once the system detects a potential risk, it will not only automatically execute a series of protective measures, such as activating security cameras, locking doors and windows, and starting alarms, but will also immediately notify residents and related contacts through mobile phone applications or other preset communication channels, ensuring that users can understand the situation at home in a timely manner and take corresponding actions quickly. This immediate response mechanism greatly enhances users' trust and daily dependence on the smart home system, and reflects the outstanding ability of modern smart home technology in improving residential safety and comfort. In addition, through learning from historical data and continuously optimizing the model, the present invention continuously adapts to new threat patterns, providing users with a dynamically updated and always reliable intelligent security system, creating a more secure and convenient living environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention will be further described below with reference to the accompanying drawings.

[0038] Figure 1 It is a flow chart of the WIFI-based smart home IoT control system of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0040] See also Figure 1 As shown, the present invention is a WIFI-based smart home IoT control system, comprising:

[0041] A data acquisition module, wherein during the smart home monitoring cycle, the smart door lock uses a built-in sound wave sensor and air pressure sensor to monitor the sound wave frequency changes and air pressure fluctuations in the environment in real time, and obtains sound wave sensing data and air pressure sensing data;

[0042] A data evaluation module, which determines abnormal sound wave characteristic values ​​based on the degree of sound wave frequency change to evaluate whether the smart home has abnormal sound wave changes; and simultaneously determines abnormal air pressure characteristic values ​​based on the air pressure wave amplitude to evaluate whether the smart home has abnormal airflow changes;

[0043] A smart home safety prediction module, which comprehensively analyzes abnormal sound wave characteristic values ​​and abnormal air pressure characteristic values, and constructs a smart home safety prediction model to predict whether there are potential risks in the smart home environment;

[0044] The smart home control module switches the smart home environment from a normal mode to a safety protection mode based on the prediction result if there is a potential risk in the smart home environment.

[0045] In the data acquisition module, during the smart home monitoring cycle, the smart door lock uses built-in acoustic wave sensors and air pressure sensors to monitor the changes in acoustic wave frequency and air pressure fluctuations in the environment in real time, and obtains acoustic wave sensing data and air pressure sensing data, including:

[0046] During the smart home monitoring cycle, the smart door lock uses a built-in acoustic sensor to monitor the changes in the sound wave frequency in the smart home environment in real time to obtain accurate acoustic sensing data. Specifically, the acoustic sensor samples the surrounding environment at fixed time intervals and collects a series of sound wave frequency values.

[0047] Smart door locks use built-in pressure sensors to monitor air pressure fluctuations in the smart home environment in real time, thereby obtaining accurate air pressure sensing data. The pressure sensor also samples the air pressure sensing data at fixed time intervals to generate an air pressure data sequence.

[0048] In the data evaluation module, the abnormal sound wave characteristic value is determined based on the degree of change in the sound wave frequency to evaluate whether the smart home has abnormal sound wave changes. At the same time, the abnormal air pressure characteristic value is determined based on the air pressure wave amplitude to evaluate whether the smart home has abnormal airflow changes. Specifically, the following are included:

[0049] During the smart home monitoring cycle, the smart door lock collects the sound wave frequency in the smart home environment in real time through the built-in sound wave sensor, calculates the abnormal sound wave characteristic value based on the change amplitude of the sound wave frequency in the environment, and determines whether the abnormal sound wave characteristic value is greater than or equal to the preset threshold. If so, there is abnormal sound wave change in the smart home; if not, there is no abnormal sound wave change in the smart home.

[0050] The process of obtaining the abnormal sound wave characteristic value is as follows:

[0051] During the smart home monitoring cycle, the smart door lock collects real-time sound wave frequency data in the smart home environment through the built-in sound wave sensor;

[0052] Calculate the amplitude of the change in the sound wave frequency at adjacent moments in the smart home environment. The calculation expression is: Δf(t) = |f(t+1)-f(t)|, where t represents the acquisition time point, f(t) represents the sound wave frequency value at time t, f(t+1) represents the sound wave frequency value at f(t+1), and Δf(t) represents the change in the sound wave frequency at adjacent moments.

[0053] The calculated sound wave frequency change values ​​at adjacent moments are integrated according to the time series. The time series of the integrated sound wave frequency change values ​​at adjacent moments is transformed using the Haar wavelet transform to extract energy information at different scales and calculate the Haar wavelet coefficients. The calculation expression is: Where j represents the number of scales, k represents the specific position at each scale, h(n) represents the Haar wavelet filter coefficient, and W j (k) represents the Haar wavelet coefficient at scale j and position k, n represents the number of selected data points, Δf(2 j (k+n)) represents the time point 2 j The frequency change value of the sound wave at (k+n) is calculated. For each scale j, the energy of the corresponding level is calculated. The calculation expression is: Among them, E j represents the energy of the jth scale, J represents the total number of scales, and the energy of all scale levels is integrated to calculate the abnormal sound wave characteristic value. The calculation expression is: Among them, A represents the abnormal sound wave characteristic value, w j represents the weight of the j-th scale.

[0054] During the smart home monitoring cycle, the smart door lock monitors the air pressure sensing data in the smart home environment in real time through the built-in air pressure sensor, calculates the air pressure abnormality characteristic value based on the air pressure fluctuation amplitude in the smart home environment, and determines whether the air pressure abnormality characteristic value is greater than or equal to the preset threshold. If so, abnormal airflow changes have occurred in the smart home; if not, abnormal airflow changes have not occurred in the smart home.

[0055] The process of obtaining the pressure anomaly characteristic value is as follows:

[0056] During the smart home monitoring cycle, the smart door lock collects the air pressure sensing data in the smart home environment at fixed time intervals through the built-in air pressure sensor during the monitoring cycle to obtain an air pressure data sequence;

[0057] Calculate the absolute value of the pressure difference between adjacent time points, integrate the absolute value of the pressure difference into a pressure fluctuation amplitude sequence, and apply fast Fourier transform to the pressure fluctuation amplitude sequence to convert it into the frequency domain to obtain the frequency domain coefficient;

[0058] Calculate the energy spectral density of each frequency component. The calculation expression is: E(s)=|ΔP(s)| 2 , where ΔP(s) represents the frequency domain coefficient of the sth frequency component, s represents the number of frequency components, and E(s) represents the s frequency domain coefficients of the sth frequency domain component;

[0059] Calculate the mean of the energy spectral density of all frequency components, compare the energy spectral density of all frequency components with the mean of the energy spectral density, record the frequency component whose energy spectral density is greater than the mean of the energy spectral density as the high-frequency part, and calculate the ratio of the sum of the energy spectral density of all high-frequency parts to the energy spectral density of all frequency components to obtain the characteristic value of the air pressure anomaly.

[0060] It should be noted that this module combines data from acoustic and air pressure sensors, utilizing advanced signal processing techniques (such as Haar wavelet transform and Fast Fourier transform) to calculate abnormal acoustic and air pressure eigenvalues, respectively. Based on these eigenvalues, it assesses potential security threats within the smart home environment. Specifically, for acoustic data, Haar wavelet transform is used to extract energy information at different scales, accurately capturing subtle changes in the environment and effectively identifying abnormal behaviors such as unauthorized intrusions. For air pressure data, Fast Fourier transform is used to analyze frequency domain characteristics, accurately detecting abnormal airflow changes caused by the sudden opening or closing of doors and windows. This module not only improves the accuracy of smart home security assessments but also enables real-time monitoring and response to complex and changing home environments, providing users with a more intelligent and secure living space. This further enhances home security and demonstrates a high level of automation and intelligence.

[0061] In the smart home safety prediction module, a comprehensive analysis of abnormal sound wave characteristic values ​​and abnormal air pressure characteristic values ​​is performed, and a smart home safety prediction model is constructed to predict whether there are potential risks in the smart home environment. Specifically, the following are included:

[0062] During the smart home monitoring cycle, the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​are obtained, and the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​are constructed into a comprehensive characteristic vector as the input of the smart home security prediction model to minimize the error between the predicted smart home security score and the actual smart home security score. As the training target of the model, the smart home security score is output according to the trained model.

[0063] The construction process of the smart home security prediction model is as follows:

[0064] The smart home safety prediction model is constructed using a support vector machine model. Specifically, the model uses historical abnormal sound wave eigenvalues, abnormal air pressure eigenvalues, and safety scores as labels to construct a supervised learning dataset. The support vector machine model is used to train the dataset with the goal of minimizing the error between the predicted safety score and the actual safety score. By selecting a radial basis function (RBF), adjusting the penalty coefficient and kernel function parameters, and optimizing model performance, a smart home safety prediction model that can accurately predict the smart home safety score is obtained after multiple iterations.

[0065] The real-time abnormal sound wave feature values ​​and air pressure abnormality features are combined into a comprehensive feature vector, which is input into the smart home security prediction model, and the model outputs a safety score.

[0066] The prediction of whether there is a potential risk in the smart home environment specifically includes:

[0067] According to the security score output by the smart home security prediction model, it is determined whether the security score of the smart home is greater than or equal to a preset threshold. If so, there is a potential risk in the smart home environment; if not, there is no potential risk in the smart home environment.

[0068] In the smart home control module, based on the prediction results, if there is a potential risk in the smart home environment, the smart home environment will be switched from normal mode to safety protection mode, including:

[0069] Based on the risk prediction results of the smart home environment, if it is determined that there is a potential risk in the smart home environment, the smart home environment will be switched from normal mode to safety protection mode, and the switching program will be immediately started to adjust the working status of various smart home devices, including activating security cameras, locking all doors and windows, turning on the alarm system, and notifying residents to ensure that the smart home environment quickly enters safety protection mode.

[0070] It's important to note that once in safety protection mode, the system activates security cameras to provide real-time monitoring footage, automatically locks all doors and windows to prevent intrusion, and activates the alarm system to sound a warning signal, deterring potential threats and alerting residents to safety. Furthermore, the intelligent system notifies residents and their contacts via a mobile app or other pre-set communication methods, ensuring they are immediately aware of any home incidents and can take appropriate action. This rapid and comprehensive response mechanism not only significantly improves home security but also strengthens users' trust and reliance on smart home systems, demonstrating the efficiency and reliability of modern smart home technology in ensuring home safety.

[0071] Working Principle of the Present Invention: The present invention provides a Wi-Fi-based smart home IoT control system, comprising a data acquisition module, a data evaluation module, a smart home security prediction module, and a smart home control module. The data acquisition module uses the built-in acoustic wave sensor and air pressure sensor in the smart door lock to monitor changes in acoustic wave frequency and air pressure fluctuations in real time, acquiring accurate acoustic and air pressure sensing data. Specifically, the acoustic wave sensor samples the ambient acoustic wave frequency at fixed intervals, while the air pressure sensor also samples the air pressure at fixed intervals, generating corresponding data sequences. Based on the collected data, the data evaluation module calculates abnormal acoustic wave eigenvalues ​​using the Haar wavelet transform and analyzes the air pressure fluctuation amplitude using the fast Fourier transform to determine the abnormal air pressure eigenvalue, thereby assessing the presence of abnormal acoustic waves or airflow changes. The smart home security prediction module constructs a comprehensive feature vector from the abnormal acoustic wave eigenvalues ​​and the abnormal air pressure eigenvalues ​​as input to a support vector machine model. The model is trained to minimize the error between the predicted and actual security scores, thereby constructing a smart home security prediction model for predicting potential risks in the smart home environment. Based on the security score output by the model, the smart home control module determines whether it is necessary to switch from normal mode to security protection mode. Once a potential risk is confirmed, the system immediately starts the switching program, activates the security camera, locks all doors and windows, turns on the alarm system and notifies the residents, ensuring that the smart home environment quickly enters a comprehensive security protection state. This highly integrated smart home control system not only significantly improves home security, but also realizes real-time monitoring and intelligent response of the home environment, providing users with a safer and more convenient living space. Through the above method, the present invention effectively solves the problem of insufficient security monitoring of smart home environments in the prior art, and provides a new solution that is suitable for various smart home application scenarios.

[0072] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The WIFI-based smart home IoT control system is characterized by: include: A data acquisition module, wherein during the smart home monitoring cycle, the smart door lock uses a built-in sound wave sensor and air pressure sensor to monitor the sound wave frequency changes and air pressure fluctuations in the environment in real time, and obtains sound wave sensing data and air pressure sensing data; A data evaluation module, which determines abnormal sound wave characteristic values ​​based on the degree of sound wave frequency change to evaluate whether the smart home has abnormal sound wave changes; and simultaneously determines abnormal air pressure characteristic values ​​based on the air pressure wave amplitude to evaluate whether the smart home has abnormal airflow changes; A smart home safety prediction module, which comprehensively analyzes abnormal sound wave characteristic values ​​and abnormal air pressure characteristic values, and constructs a smart home safety prediction model to predict whether there are potential risks in the smart home environment; The smart home control module switches the smart home environment from a normal mode to a safety protection mode based on the prediction result if there is a potential risk in the smart home environment.

2. The WIFI-based smart home IoT control system according to claim 1, characterized in that: The evaluation of whether there are abnormal sound wave changes in the smart home specifically includes: During the smart home monitoring cycle, the smart door lock collects the sound wave frequency in the smart home environment in real time through the built-in sound wave sensor, calculates the abnormal sound wave characteristic value based on the change amplitude of the sound wave frequency in the environment, and determines whether the abnormal sound wave characteristic value is greater than or equal to the preset threshold. If so, there is abnormal sound wave change in the smart home; if not, there is no abnormal sound wave change in the smart home.

3. The WIFI-based smart home IoT control system according to claim 2, characterized in that: The process of obtaining the abnormal sound wave characteristic value is as follows: During the smart home monitoring cycle, the smart door lock collects real-time sound wave frequency data in the smart home environment through the built-in sound wave sensor; Calculate the amplitude of the sound wave frequency change at adjacent moments in the smart home environment to obtain the sound wave frequency change value at adjacent moments; The calculated sound wave frequency change values ​​at adjacent moments are integrated according to the time series. The time series of the integrated sound wave frequency change values ​​at adjacent moments is applied with the Haar wavelet transform to extract the energy information of different scales and calculate the Haar wavelet coefficients. For each scale j, the squares of the Haar wavelet coefficients of the corresponding scale are summed to obtain the energy of the corresponding scale. The energy of all scale levels is accumulated to obtain the abnormal sound wave characteristic value.

4. The WIFI-based smart home IoT control system according to claim 1, characterized in that: The evaluation of whether abnormal airflow changes occur in the smart home specifically includes: During the smart home monitoring cycle, the smart door lock monitors the air pressure sensing data in the smart home environment in real time through the built-in air pressure sensor, calculates the air pressure abnormality characteristic value based on the air pressure fluctuation amplitude in the smart home environment, and determines whether the air pressure abnormality characteristic value is greater than or equal to the preset threshold. If so, abnormal airflow changes have occurred in the smart home; if not, abnormal airflow changes have not occurred in the smart home.

5. The WIFI-based smart home IoT control system according to claim 4, characterized in that: The process of obtaining the pressure anomaly characteristic value is as follows: During the smart home monitoring cycle, the smart door lock collects the air pressure sensing data in the smart home environment at fixed time intervals through the built-in air pressure sensor during the monitoring cycle to obtain an air pressure data sequence; Calculate the absolute value of the pressure difference between adjacent time points, integrate the absolute value of the pressure difference into a pressure fluctuation amplitude sequence, and apply fast Fourier transform to the pressure fluctuation amplitude sequence to convert it into the frequency domain to obtain the frequency domain coefficient; Calculate the square of the modulus of the frequency domain coefficient of each frequency component to obtain the energy spectrum density of each frequency component; Calculate the mean of the energy spectral density of all frequency components, compare the energy spectral density of all frequency components with the mean of the energy spectral density, record the frequency component whose energy spectral density is greater than the mean of the energy spectral density as the high-frequency part, and calculate the ratio of the sum of the energy spectral density of all high-frequency parts to the energy spectral density of all frequency components to obtain the characteristic value of the air pressure anomaly.

6. The WIFI-based smart home IoT control system according to claim 1, characterized in that: The comprehensive analysis of the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​specifically includes: During the smart home monitoring cycle, the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​are obtained, and the abnormal sound wave characteristic values ​​and the abnormal air pressure characteristic values ​​are constructed into a comprehensive characteristic vector as the input of the smart home security prediction model to minimize the error between the predicted smart home security score and the actual smart home security score. As the training target of the model, the smart home security score is output according to the trained model.

7. The WIFI-based smart home IoT control system according to claim 6, characterized in that: The construction process of the smart home security prediction model is as follows: The smart home safety prediction model is constructed using a support vector machine model. Specifically, the model uses historical abnormal sound wave eigenvalues, abnormal air pressure eigenvalues, and safety scores as labels to construct a supervised learning dataset. The support vector machine model is used to train the dataset with the goal of minimizing the error between the predicted safety score and the actual safety score. By selecting a radial basis function (RBF), adjusting the penalty coefficient and kernel function parameters, and optimizing model performance, a smart home safety prediction model that can accurately predict the smart home safety score is obtained after multiple iterations.

8. The WIFI-based smart home IoT control system according to claim 1, characterized in that: The prediction of whether there is a potential risk in the smart home environment specifically includes: According to the security score output by the smart home security prediction model, it is determined whether the security score of the smart home is greater than or equal to a preset threshold. If so, there is a potential risk in the smart home environment; if not, there is no potential risk in the smart home environment.

9. The WIFI-based smart home IoT control system according to claim 1, characterized in that: Switching the smart home environment from the normal mode to the security protection mode specifically includes: Based on the risk prediction results of the smart home environment, if it is determined that there is a potential risk in the smart home environment, the smart home environment will be switched from normal mode to safety protection mode, and the switching program will be immediately started to adjust the working status of various smart home devices, including activating security cameras, locking all doors and windows, turning on the alarm system, and notifying residents to ensure that the smart home environment quickly enters safety protection mode.

Images