Intelligent door and window control system and method based on Internet of Things

Through the Internet of Things system based on artificial intelligence, the light intensity, humidity and air pressure analysis is used to determine the tendency of rain and automatically control windows, solving the problems of low manual operation efficiency and lack of intelligence in the existing door and window control system, and realizing intelligent door and window control automation and security improvement.

CN118933501AInactive Publication Date: 2024-11-12JIANGSU SHENGSHITUO TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411052080.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing door and window control systems rely on manual operation, are inefficient and lack an intelligent automatic response mechanism, and are unable to respond to sudden weather changes in a timely manner, resulting in safety hazards and environmental losses.

Method used

The Internet of Things system based on artificial intelligence is adopted to analyze outdoor light intensity, humidity and air pressure values ​​in real time, judge the rain tendency, automatically control the window status, and use stepper motors to perform switching operations.

Benefits of technology

It realizes the automation and intelligence of window control, improves the comfort and safety of the indoor environment, responds to weather changes in a timely manner, and reduces losses caused by weather changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118933501A_ABST
    Figure CN118933501A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent door and window control system and method based on the Internet of Things, and relates to the field of intelligent home furnishing.The data analysis technology based on artificial intelligence is adopted, outdoor illumination intensity values, humidity values and air pressure values at multiple time points are analyzed in real time, and therefore the tendency of raining weather is judged; and then whether the stepping motor needs to be driven to close the window or not is determined. Thus, automation and intelligentization of window control are achieved, and comfort and safety of the indoor environment can be kept by more accurately controlling the state of the window.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of smart home, and more specifically, to an intelligent door and window control system and method based on the Internet of Things. Background Art

[0002] With the rapid development of science and technology, smart home is gradually integrated into our daily life, providing us with a more convenient and comfortable living environment. However, although smart home technology has made significant progress in many aspects, the existing door and window control system still has some limitations.

[0003] First, many door and window control systems still rely on manual operation, which means that users need to manually open or close windows and doors to cope with different weather conditions. This operation mode is not only inefficient, but also cannot respond in time when the user is not at home or forgets to operate. Secondly, existing systems often lack intelligent automatic response mechanisms. For example, when encountering sudden heavy rain, if the windows are not closed in time, rainwater may invade the room, causing damage to furniture, floors, etc., and may even cause safety hazards such as circuit short circuits.

[0004] Therefore, an optimized IoT-based smart door and window control solution is needed. Summary of the invention

[0005] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides an intelligent door and window control system and method based on the Internet of Things, which adopts data analysis technology based on artificial intelligence, and judges the tendency of rainy weather by real-time analysis of outdoor light intensity values, humidity values ​​and air pressure values ​​at multiple time points, and then determines whether it is necessary to drive the stepper motor to close the window. In this way, the automation and intelligence of window control are realized, and by more accurately controlling the window state, it is conducive to maintaining the comfort and safety of the indoor environment.

[0006] According to one aspect of the present application, there is provided an intelligent door and window control system based on the Internet of Things, which includes:

[0007] The weather monitoring parameter data acquisition module is used to obtain the outdoor light intensity value, humidity value and air pressure value at multiple predetermined time points within a predetermined time period;

[0008] A weather monitoring parameter data structuring module, for structuring the outdoor light intensity values, humidity values ​​and air pressure values ​​at the plurality of predetermined time points to obtain an outdoor weather parameter monitoring time series input matrix;

[0009] A weather monitoring parameter data encoding module, used for performing feature encoding on the outdoor weather parameter monitoring time series input matrix to obtain an outdoor weather parameter monitoring feature graph;

[0010] The stepper motor driving result generation module is used to determine whether the stepper motor needs to be driven at the current time point based on the outdoor weather parameter monitoring characteristic diagram.

[0011] According to another aspect of the present application, a smart door and window control method based on the Internet of Things is provided, which includes:

[0012] Obtain outdoor light intensity values, humidity values, and air pressure values ​​at multiple predetermined time points within a predetermined time period;

[0013] Structuring the outdoor light intensity values, humidity values ​​and air pressure values ​​at the plurality of predetermined time points to obtain an outdoor weather parameter monitoring time series input matrix;

[0014] Performing feature encoding on the outdoor weather parameter monitoring time series input matrix to obtain an outdoor weather parameter monitoring feature graph;

[0015] Based on the outdoor weather parameter monitoring characteristic graph, it is determined whether the stepper motor needs to be driven at the current time point.

[0016] Compared with the prior art, the intelligent door and window control system and method based on the Internet of Things provided by the present application adopts data analysis technology based on artificial intelligence, and judges the tendency of rainy weather by real-time analysis of outdoor light intensity values, humidity values ​​and air pressure values ​​at multiple time points, and then determines whether it is necessary to drive the stepper motor to close the window. In this way, the automation and intelligence of window control are realized, and by more accurately controlling the window state, it is conducive to maintaining the comfort and safety of the indoor environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 The present invention is a flowchart of an intelligent door and window control method based on the Internet of Things according to an embodiment of the present application.

[0019] Figure 2 This is an architecture diagram of an intelligent door and window control method based on the Internet of Things according to an embodiment of the present application.

[0020] Figure 3 The present invention is a flowchart of performing feature encoding on the outdoor weather parameter monitoring timing input matrix to obtain an outdoor weather parameter monitoring feature diagram in the smart door and window control method based on the Internet of Things according to an embodiment of the present application.

[0021] Figure 4 This is a flow chart of determining whether a stepper motor needs to be driven at the current time point based on the outdoor weather parameter monitoring characteristic diagram in the smart door and window control method based on the Internet of Things according to an embodiment of the present application.

[0022] Figure 5 This is a system block diagram of an intelligent door and window control system based on the Internet of Things according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] As mentioned in the above background technology, with the rapid development of science and technology, smart homes are gradually being integrated into our daily lives, providing us with a more convenient and comfortable living environment. This change is not only reflected in the basic automation of home operations, but also in its ability to improve our quality of life through intelligent analysis and prediction. However, although smart home technology has made significant progress in many aspects, the existing door and window control system still has some limitations, which are particularly obvious in real applications. The first is the problem of manual dependence. Many door and window control systems still rely on manual operation, which is particularly cumbersome in daily life. Users need to pay attention to changes in the indoor and outdoor environments at all times and manually adjust the status of windows and doors. This mode of operation is not only inefficient, but also causes untimely control of the indoor environment when the user is not at home. The second is the lack of intelligent automatic response mechanism. Existing systems often lack intelligent automatic response mechanism. In the event of sudden heavy rain, if the windows are not closed in time, rainwater may invade the room, which will not only damage furniture, floors and other properties, but also cause safety hazards such as circuit short circuits. In other words, the current door and window control system is also relatively limited in its ability to predict and respond to emergencies, and cannot effectively prevent and reduce losses caused by weather changes. Therefore, an optimized smart door and window control solution based on the Internet of Things is expected.

[0025] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also shown a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for intelligent door and window control based on the Internet of Things.

[0026] Figure 1 The present invention is a flowchart of an intelligent door and window control method based on the Internet of Things according to an embodiment of the present application.

[0027] Figure 2 FIG. 1 is an architecture diagram of an intelligent door and window control method based on the Internet of Things according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the embodiment of the present application, the smart door and window control method based on the Internet of Things includes: S110, obtaining the outdoor light intensity value, humidity value and air pressure value at multiple predetermined time points within a predetermined time period; S120, structuring the outdoor light intensity value, humidity value and air pressure value at the multiple predetermined time points to obtain an outdoor weather parameter monitoring timing input matrix; S130, feature encoding the outdoor weather parameter monitoring timing input matrix to obtain an outdoor weather parameter monitoring characteristic graph; S140, based on the outdoor weather parameter monitoring characteristic graph, judging whether the stepper motor needs to be driven at the current time point.

[0028] Specifically, in the technical solution of the present application, firstly, the outdoor light intensity value, humidity value and air pressure value at multiple predetermined time points within a predetermined time period are obtained. It should be understood that although the light intensity itself does not directly indicate rainfall, it can be used as an auxiliary indicator of weather changes. Before the arrival of rainfall, the cloud layer may thicken, resulting in a sharp drop in light intensity. Humidity is one of the important indicators for judging the possibility of rainfall. The increase in air humidity is often accompanied by the accumulation of water vapor, which is a prerequisite for rainfall. Therefore, monitoring the outdoor humidity value can directly reflect the content of water vapor in the air, and then predict the possibility of rainfall. Changes in air pressure are usually closely related to weather changes. A drop in air pressure often indicates the arrival of a storm or rainfall, because a drop in air pressure is usually associated with a low pressure system, and a low pressure system often brings precipitation. That is, obtaining the outdoor light intensity value, humidity value and air pressure value is to comprehensively evaluate the current and future weather conditions, so as to drive the stepper motor to open and close the window when necessary. These parameters reflect different aspects of the weather in different ways, and together constitute the basis for judging the possibility of rainfall and taking corresponding measures.

[0029] The Internet of Things (IoT) refers to a network system that connects various physical devices, sensors, software, and other technologies through the Internet, enabling them to communicate with each other and exchange data. Simply put, the Internet of Things is a technology that connects and controls various physical devices through the Internet, allowing these devices to operate and interact automatically and intelligently. The core idea of ​​the Internet of Things is to enable objects in daily life to connect and communicate through the Internet, and to achieve intelligent and automated control and management. Through embedded sensors, software, and network connections, these objects can collect, exchange, and analyze data, thereby achieving more efficient and intelligent functions and services.

[0030] In an embodiment of the present application, a possible implementation method for obtaining outdoor light intensity values, humidity values, and air pressure values ​​at multiple predetermined time points within a predetermined time period may be: outdoor light intensity data at multiple time points may be obtained through a light intensity sensor; humidity data at multiple time points may be obtained through a humidity sensor; and air pressure data at multiple times may be obtained through a barometer. Internet of Things technology uses the Internet as a communication medium to transmit light intensity value data, humidity value data, and air pressure value data collected by multiple sensors to a cloud server, and processes and analyzes these data on the cloud server to achieve intelligent control of windows.

[0031] Considering that the data collected are data at multiple time points, the data at multiple time points can better capture the trend and law of weather changes. When the continuous decline in air pressure may indicate the approach of a low pressure system, and the gradual increase in humidity may indicate the approach of rainfall, this trend analysis is more accurate and reliable than considering the data at a certain moment alone. An important feature of the collected time series data is the time sequence relationship between the data points. In order to ensure that the time sequence of the data is retained and help the model identify the trend of weather changes, in the technical solution of the present application, the outdoor light intensity values, humidity values ​​and air pressure values ​​at the multiple predetermined time points are arranged according to the time dimension as an outdoor weather parameter monitoring time series input matrix. It should be understood that the outdoor light intensity, humidity, and air pressure are arranged in the same matrix according to the same time dimension, and all data related to weather forecasting are concentrated in one place, avoiding the problem of data dispersion processing. At the same time, arranging data in the same matrix can ensure that the sampling frequency, timestamp and other attributes of all data remain consistent, which is conducive to the model's weather forecast analysis. Each row in the outdoor weather parameter monitoring time series input matrix formed by the arrangement is a weather parameter monitoring sample at a time point, and each column is a specific weather monitoring parameter indicator.

[0032] Figure 3 The present invention is a flowchart of a method for controlling smart doors and windows based on the Internet of Things according to an embodiment of the present application, in which the outdoor weather parameter monitoring time series input matrix is ​​feature encoded to obtain an outdoor weather parameter monitoring feature graph. Figure 3 As shown, the outdoor weather parameter monitoring timing input matrix is ​​feature encoded to obtain an outdoor weather parameter monitoring feature map, including: S121, local feature extraction of the outdoor weather parameter monitoring timing input matrix to obtain an outdoor weather parameter monitoring local feature map; S122, global feature extraction of the outdoor weather parameter monitoring local feature map to obtain an outdoor weather parameter monitoring global feature map; S123, fusing the outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map to obtain the outdoor weather parameter monitoring feature map.

[0033] The complex relationship between weather parameters is often hidden in the original data, that is, the outdoor weather parameter monitoring time series input matrix formed by arrangement. By extracting features from the matrix, key information such as the trend of weather changes can be captured. Therefore, the outdoor weather parameter monitoring time series input matrix is ​​passed through the weather parameter time series feature encoder to obtain the outdoor weather parameter monitoring local feature map. The essence of the weather parameter time series feature encoder in this application is a convolutional neural network model using a spatial attention mechanism. Compared with using ordinary convolutional neural network models to extract features from matrices, convolutional neural network models using spatial attention mechanisms have the following advantages: a. Improving the pertinence of feature extraction: The spatial attention mechanism enables the model to pay more attention to important areas during the feature extraction process, which helps the model better capture the key features of weather changes and extract more useful information; b. Enhancing the robustness of the model: By introducing the attention mechanism, the model can better handle noise and abnormal data, improving the robustness and stability of the model, which is especially important for monitoring weather parameters because weather data often contains a lot of noise and uncertainty; c. Improving prediction accuracy: Since the key features of weather parameters can be extracted more accurately, convolutional neural network models using spatial attention mechanisms often have higher accuracy in predicting weather conditions, which helps the control system make more reasonable decisions and improve the overall performance of the system.

[0034] In an embodiment of the present application, a possible implementation method of passing the outdoor weather parameter monitoring time series input matrix through a weather parameter time series feature encoder to obtain an outdoor weather parameter monitoring local feature map can be: using each layer of the weather parameter time series feature encoder to perform the following on the input data in the forward pass of the layer: convolution processing on the input data based on the convolution kernel to obtain a convolution feature map; passing the convolution feature map through a spatial attention module to obtain a spatial attention score matrix; multiplying the spatial attention score matrix and each feature matrix of the convolution feature map along the channel dimension by the spatial attention feature map at each position point; performing pooling processing on the spatial attention feature map based on the local feature matrix to obtain a pooling feature map; performing nonlinear activation on the pooling feature map to obtain an activation feature map; wherein the input of the first layer of the weather parameter time series feature encoder is the outdoor weather parameter monitoring time series input matrix, and the output of the last layer of the weather parameter time series feature encoder is the outdoor weather parameter monitoring local feature map.

[0035] Although the local feature map of outdoor weather parameter monitoring obtained by processing the weather parameter time series feature encoder can capture the characteristics of weather parameters in local time or space, it often ignores the dependencies in the global scope. In order to integrate the information between different local features and form a more comprehensive understanding of weather conditions, in the technical solution of the present application, the local feature map of outdoor weather parameter monitoring is passed through a non-local neural network to obtain a global feature map of outdoor weather parameter monitoring. Non-local Neural Networks is a neural network structure that can capture long-distance dependencies in input data. It draws on the idea of ​​non-local means and calculates the response at a position as the weighted sum of features at all positions, thereby breaking through the limitation that traditional convolutional neural networks (CNNs) can only capture local features. The global feature map extracted by the non-local neural network contains more global information and dependencies about weather changes, and can better represent weather conditions. It is worth mentioning that by capturing global features, the model can better adapt to weather forecasting tasks under different environments and conditions and improve generalization capabilities.

[0036] The local feature map for outdoor weather parameter monitoring mainly focuses on the characteristics of weather parameters at a local time, ignoring important information and dependencies in the global scope, which may lead to inaccurate weather forecast results when the weather changes are complex or sudden; although the global feature map for outdoor weather parameter monitoring can capture the global dependencies of weather parameters, local detail information may be lost in the processing process. These details are equally important for accurately judging the current weather conditions and their changing trends. In order to make full use of the advantages of the global feature map and the local feature map, in the technical solution of the present application, the local feature map for outdoor weather parameter monitoring and the global feature map for outdoor weather parameter monitoring are fused to obtain the outdoor weather parameter monitoring feature map. The feature map obtained by fusion retains the local detail information and captures the global dependencies, thereby improving the accuracy of weather forecasts and better judging whether the stepper motor needs to be driven.

[0037] In an embodiment of the present application, a possible implementation method of fusing the outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map to obtain the outdoor weather parameter monitoring feature map may be: fusing the outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map using the following fusion formula to obtain the outdoor weather parameter monitoring feature map; wherein the fusion formula is:

[0038] F c =αF a ⊕βF b

[0039] Among them, Fc is the outdoor weather parameter monitoring characteristic diagram, F a is the local characteristic map of outdoor weather parameter monitoring, F b A global characteristic map for monitoring outdoor weather parameters, It represents the addition of the elements at corresponding positions of the outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map, and α and β are weighted parameters for controlling the balance between the outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map in the outdoor weather parameter monitoring feature map.

[0040] Figure 4 The present invention is a flowchart of determining whether the stepper motor needs to be driven at the current time point based on the outdoor weather parameter monitoring characteristic diagram in the smart door and window control method based on the Internet of Things according to the embodiment of the present application. Figure 4 As shown, judging whether the stepper motor needs to be driven at the current time point based on the outdoor weather parameter monitoring feature map includes: S141, pooling the feature matrices of the outdoor weather parameter monitoring feature map along the channel dimension to obtain an outdoor weather parameter monitoring feature vector; S142, subjecting the outdoor weather parameter monitoring feature vector to acceptable group distribution constraints based on mapping matching to obtain an optimized outdoor weather parameter monitoring feature vector; S143, passing the optimized outdoor weather parameter monitoring feature vector through a stepper motor driving classifier to obtain a classification result, and the classification result is used to indicate whether the stepper motor needs to be driven at the current time point.

[0041] Considering that the outdoor weather parameter monitoring feature graph has a high dimension, which will increase the computational complexity of subsequent steps, in order to reduce the computational complexity and improve the operational efficiency of the entire model, in the technical solution of this application, the outdoor weather parameter monitoring feature graph is pooled along the channel dimension of each feature matrix to obtain an outdoor weather parameter monitoring feature vector. Through the pooling operation, the three-dimensional feature graph can be converted into a one-dimensional feature vector, which reduces the dimension while retaining the key features in the feature graph and removing some redundant information.

[0042] In particular, outdoor environmental parameters (light intensity, humidity, air pressure) are affected by many factors, such as time, geographical location, etc. These factors can cause instantaneous fluctuations or outliers in the data collection process, and the sensors used in the process of collecting outdoor environmental parameters have accuracy limitations and measurement errors. These errors accumulate in the data collection process, which will cause disturbances to be introduced into the outdoor weather parameter monitoring feature vector. Accordingly, in the technical solution of the present application, considering that the neural network model performs feature mining on the input outdoor weather data based on the network parameter matrix, if the inherent implicit association between the network output features and the network parameter matrix can be further considered, the prior information of the neural network model can be further used to modulate the characteristic manifold of the outdoor weather parameter monitoring feature vector to reduce the possibility of special instance disturbances of its characteristic values. Therefore, the outdoor weather parameter monitoring feature vector is subjected to acceptable constraints based on the mapping matching degree of the group distribution to obtain the optimized outdoor weather parameter monitoring feature vector.

[0043] Specifically, in an embodiment of the present application, the outdoor weather parameter monitoring feature vector is subjected to acceptable constraints on the group distribution based on the mapping matching degree to obtain an optimized outdoor weather parameter monitoring feature vector, including: calculating the mean and variance of the outdoor weather parameter monitoring feature vector; calculating the difference between the eigenvalue of the predetermined position of the outdoor weather parameter monitoring feature vector and the mean of the outdoor weather parameter monitoring feature vector to obtain a first intermediate calculated value; multiplying the network parameter matrix by the outdoor weather parameter monitoring feature vector and then subtracting the matrix from the outdoor weather parameter monitoring feature vector by position to obtain a first intermediate vector, and calculating the Frobenius norm of the first intermediate vector to obtain a first norm value; adding the first norm value to the outdoor weather parameter monitoring feature vector; The variance of the outdoor weather parameter monitoring feature vector is then squared to obtain a second intermediate calculated value; the first intermediate calculated value is divided by the second intermediate calculated value to obtain a third intermediate calculated value; the squares of each position of the outdoor weather parameter monitoring feature vector are calculated and then accumulated to obtain a first total value; the square root of the first total value is divided by the scale of the network parameter matrix and then the natural exponential function value is calculated to obtain a fourth intermediate calculated value, wherein the scale of the network parameter matrix is ​​equal to the product of the width value of the network parameter matrix and the height value thereof; the fourth intermediate calculated value is multiplied by a weighted hyperparameter and then added to the third intermediate calculated value to obtain the eigenvalue of the predetermined position of the optimized outdoor weather parameter monitoring feature vector.

[0044] In an embodiment of the present application, another expression of subjecting the outdoor weather parameter monitoring feature vector to the acceptable group distribution constraint based on the mapping matching degree to obtain the optimized outdoor weather parameter monitoring feature vector may be: processing the outdoor weather parameter monitoring feature vector with the following formula to obtain the optimized outdoor weather parameter monitoring feature vector, including:

[0045]

[0046] Where V is the outdoor weather parameter monitoring feature vector, M is the network parameter matrix, β represents the weighted hyperparameter, and v i is the eigenvalue of the ith position of the outdoor weather parameter monitoring feature vector, N is the scale of the network parameter matrix, the scale of the network parameter matrix is ​​equal to the product of the width value and the height value of the network parameter matrix, L is the length of the outdoor weather parameter monitoring feature vector, ||·|| F represents the F norm of the feature vector, μ represents the mean of the outdoor weather parameter monitoring feature vector, σ 2 represents the variance of the outdoor weather parameter monitoring feature vector, exp(·) represents the exponential function with the natural constant e as the base, v' i represents the eigenvalue of the i-th position of the optimized outdoor weather parameter monitoring eigenvector, Represents matrix multiplication.

[0047] It should be understood that in the technical solution of the present application, considering that the neural network model performs feature mining on the input data based on the network parameter matrix, if the inherent implicit association between the network output feature and the network parameter matrix can be further considered, the prior information of the neural network model can be further used to modulate the characteristic manifold of the outdoor weather parameter monitoring feature vector to reduce the possibility of special instance disturbances of its characteristic values. Based on this, in a preferred embodiment, the outdoor weather parameter monitoring feature vector is subjected to a group distribution acceptability constraint based on the mapping matching degree, which first maps the outdoor weather parameter monitoring feature vector to the high-dimensional feature space where the network parameter matrix is ​​located, and uses the compatibility perception factor between the mapping result and the original input as the inherent implicit association descriptor between the network output feature and the network parameter matrix. Then, the statistical characteristics of the feature group of the outdoor weather parameter monitoring feature vector are used as the inherent modal information of the outdoor weather parameter monitoring feature vector, and the inherent implicit association descriptor is used as the instance disturbance differential adjustment variable, and the attribute values ​​of each position of the outdoor weather parameter monitoring feature vector are dynamically normalized. At the same time, the class-normalized modulus data of the outdoor weather parameter monitoring feature vector is used as a bias item to constrain the acceptable range of the group distribution of the outdoor weather parameter monitoring feature vector. In this way, the attribute influence of the interference distribution of abnormal samples can be suppressed as much as possible, thereby improving the expression accuracy of the outdoor weather parameter monitoring feature vector.

[0048] Finally, the optimized outdoor weather parameter monitoring feature vector is passed through a stepper motor driving classifier to obtain a classification result, and the classification result is used to indicate whether the stepper motor needs to be driven at the current time point. It should be understood that the optimized outdoor weather parameter monitoring feature vector contains weather parameter information after feature extraction and fusion processing, which is an important basis for judging the operation of the control stepper motor. As a machine learning model, the stepper motor driving classifier can analyze and judge according to the input data and map it to different categories. The stepper motor driving classifier can output a classification result indicating whether the window state needs to be adjusted to cope with the current weather, and the stepper motor, as an actuator, is responsible for driving the opening and closing of the window according to the classification result. This can respond to weather changes in a timely manner, adjust the window state, and maintain the comfort and safety of the indoor environment.

[0049] In an embodiment of the present application, the optimized outdoor weather parameter monitoring feature vector is passed through a stepper motor drive classifier to obtain a classification result, and the classification result is used to indicate whether the stepper motor needs to be driven at the current time point. One possible implementation method may be: use the fully connected layer of the stepper motor drive classifier to fully connect encode the optimized outdoor weather parameter monitoring feature vector to obtain a fully connected encoded feature vector; input the fully connected encoded feature vector into the Softmax classification function of the stepper motor drive classifier to obtain the probability values ​​belonging to each classification label in the optimized outdoor weather parameter monitoring feature vector, and the classification labels include those used to indicate that the stepper motor needs to be driven at the current time point and those used to indicate that the stepper motor does not need to be driven at the current time point; and determine the classification label corresponding to the largest of the probability values ​​as the classification result.

[0050] In summary, the method for controlling smart doors and windows based on the Internet of Things according to the embodiment of the present application is explained, which uses data analysis technology based on artificial intelligence to judge the tendency of rainy weather by real-time analysis of outdoor light intensity values, humidity values ​​and air pressure values ​​at multiple time points, and then determines whether it is necessary to drive the stepper motor to close the window. In this way, the automation and intelligence of window control are realized, and by more accurately controlling the window state, it is conducive to maintaining the comfort and safety of the indoor environment.

[0051] Figure 5 : is a system block diagram of an intelligent door and window control system based on the Internet of Things according to an embodiment of the present application. Figure 5 As shown, according to the embodiment of the present application, the smart door and window control system 100 based on the Internet of Things includes: a weather monitoring parameter data acquisition module 110, which is used to obtain the outdoor light intensity value, humidity value and air pressure value at multiple predetermined time points within a predetermined time period; a weather monitoring parameter data structuring module 120, which is used to structure the outdoor light intensity value, humidity value and air pressure value at the multiple predetermined time points to obtain an outdoor weather parameter monitoring timing input matrix; a weather monitoring parameter data encoding module 130, which is used to feature encode the outdoor weather parameter monitoring timing input matrix to obtain an outdoor weather parameter monitoring characteristic diagram; a stepper motor drive result generation module 140, which is used to determine whether the stepper motor needs to be driven at the current time point based on the outdoor weather parameter monitoring characteristic diagram.

[0052] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above-mentioned smart door and window control system 100 based on the Internet of Things have been referred to above. Figures 1 to 4 The description of the intelligent door and window control method based on the Internet of Things has been introduced in detail, and therefore, its repeated description will be omitted.

[0053] In summary, the IoT-based smart door and window control system 100 according to the embodiment of the present application is explained, which uses artificial intelligence-based data analysis technology to perform real-time analysis of outdoor light intensity values, humidity values, and air pressure values ​​at multiple time points to determine the tendency of rainy weather, and then determine whether it is necessary to drive the stepper motor to close the window. In this way, the automation and intelligence of window control is realized, and by more accurately controlling the window state, it is conducive to maintaining the comfort and safety of the indoor environment.

[0054] As described above, the smart door and window control system 100 based on the Internet of Things according to the embodiment of the present application can be implemented in various wireless terminals, such as a server for smart door and window control based on the Internet of Things. In one example, the smart door and window control system 100 based on the Internet of Things according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the smart door and window control system 100 based on the Internet of Things can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the smart door and window control system 100 based on the Internet of Things can also be one of the many hardware modules of the wireless terminal.

[0055] Alternatively, in another example, the IoT-based smart door and window control system 100 and the wireless terminal may also be separate devices, and the IoT-based smart door and window control system 100 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0056] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details of the above application are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present application to the use of the above specific details to be implemented.

[0057] In this application, words such as "including", "comprising", "having", etc. are open words, meaning "including but not limited to", and can be used interchangeably therewith. The words "or" and "and" used herein mean the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably therewith.

[0058] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0059] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0060] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present application.

[0061] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A smart door and window control method based on the Internet of Things, characterized in that: include: Obtain outdoor light intensity values, humidity values, and air pressure values ​​at multiple predetermined time points within a predetermined time period; Structuring the outdoor light intensity values, humidity values ​​and air pressure values ​​at the plurality of predetermined time points to obtain an outdoor weather parameter monitoring time series input matrix; Performing feature encoding on the outdoor weather parameter monitoring time series input matrix to obtain an outdoor weather parameter monitoring feature graph; Based on the outdoor weather parameter monitoring characteristic graph, it is determined whether the stepper motor needs to be driven at the current time point.

2. The method for controlling smart doors and windows based on the Internet of Things according to claim 1, characterized in that: The outdoor light intensity values, humidity values ​​and air pressure values ​​at the multiple predetermined time points are structured and sorted to obtain an outdoor weather parameter monitoring timing input matrix, including: arranging the outdoor light intensity values, humidity values ​​and air pressure values ​​at the multiple predetermined time points according to the time dimension into the outdoor weather parameter monitoring timing input matrix.

3. The method for controlling smart doors and windows based on the Internet of Things according to claim 2 is characterized in that: The outdoor weather parameter monitoring time series input matrix is ​​feature encoded to obtain an outdoor weather parameter monitoring feature graph, including: Performing local feature extraction on the outdoor weather parameter monitoring time series input matrix to obtain an outdoor weather parameter monitoring local feature graph; Performing global feature extraction on the outdoor weather parameter monitoring local feature map to obtain an outdoor weather parameter monitoring global feature map; The outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map are fused to obtain the outdoor weather parameter monitoring feature map.

4. The method for controlling smart doors and windows based on the Internet of Things according to claim 3 is characterized in that: Performing local feature extraction on the outdoor weather parameter monitoring timing input matrix to obtain an outdoor weather parameter monitoring local feature map, including: passing the outdoor weather parameter monitoring timing input matrix through a weather parameter timing feature encoder to obtain the outdoor weather parameter monitoring local feature map.

5. The method for controlling smart doors and windows based on the Internet of Things according to claim 4 is characterized in that: Performing global feature extraction on the outdoor weather parameter monitoring local feature map to obtain the outdoor weather parameter monitoring global feature map includes: passing the outdoor weather parameter monitoring local feature map through a non-local neural network to obtain the outdoor weather parameter monitoring global feature map.

6. The method for controlling smart doors and windows based on the Internet of Things according to claim 5, characterized in that: The weather parameter temporal feature encoder is a convolutional neural network model using a spatial attention mechanism.

7. The method for controlling smart doors and windows based on the Internet of Things according to claim 6, characterized in that: Based on the outdoor weather parameter monitoring characteristic graph, judging whether the stepper motor needs to be driven at the current time point includes: Pooling the outdoor weather parameter monitoring feature map with each feature matrix along the channel dimension to obtain an outdoor weather parameter monitoring feature vector; Performing group distribution acceptability constraints based on mapping matching degree on the outdoor weather parameter monitoring feature vector to obtain an optimized outdoor weather parameter monitoring feature vector; The optimized outdoor weather parameter monitoring feature vector is passed through a stepper motor driving classifier to obtain a classification result, and the classification result is used to indicate whether the stepper motor needs to be driven at the current time point.

8. The method for controlling smart doors and windows based on the Internet of Things according to claim 7, characterized in that: The outdoor weather parameter monitoring feature vector is subjected to a group distribution acceptability constraint based on a mapping matching degree to obtain an optimized outdoor weather parameter monitoring feature vector, including: Calculating the mean and variance of the outdoor weather parameter monitoring feature vector; Calculating the difference between the characteristic value of the predetermined position of the outdoor weather parameter monitoring characteristic vector and the mean value of the outdoor weather parameter monitoring characteristic vector to obtain a first intermediate calculated value; Multiplying the network parameter matrix by the outdoor weather parameter monitoring feature vector and then subtracting the matrix from the outdoor weather parameter monitoring feature vector by position to obtain a first intermediate vector, and calculating the Frobenius norm of the first intermediate vector to obtain a first norm value; Adding the first norm value to the variance of the outdoor weather parameter monitoring feature vector and then performing a square root operation to obtain a second intermediate calculated value; dividing the first intermediate calculated value by the second intermediate calculated value to obtain a third intermediate calculated value; Calculating the square of each position of the outdoor weather parameter monitoring feature vector and then accumulating and summing them to obtain a first sum value; Calculate a natural exponential function value after taking the square root of the first sum value and dividing it by the scale of the network parameter matrix to obtain a fourth intermediate calculation value, wherein the scale of the network parameter matrix is ​​equal to the product of the width value of the network parameter matrix and the height value thereof; The fourth intermediate calculated value is multiplied by the weighted hyperparameter and then added to the third intermediate calculated value to obtain the characteristic value of the predetermined position of the optimized outdoor weather parameter monitoring characteristic vector.

9. An intelligent door and window control system based on the Internet of Things, characterized in that: include: The weather monitoring parameter data acquisition module is used to obtain the outdoor light intensity value, humidity value and air pressure value at multiple predetermined time points within a predetermined time period; A weather monitoring parameter data structuring module, for structuring the outdoor light intensity values, humidity values ​​and air pressure values ​​at the plurality of predetermined time points to obtain an outdoor weather parameter monitoring time series input matrix; A weather monitoring parameter data encoding module, used for performing feature encoding on the outdoor weather parameter monitoring time series input matrix to obtain an outdoor weather parameter monitoring feature graph; The stepper motor driving result generation module is used to determine whether the stepper motor needs to be driven at the current time point based on the outdoor weather parameter monitoring characteristic diagram.

10. The intelligent door and window control system based on the Internet of Things according to claim 9 is characterized in that: The weather monitoring parameter data encoding module comprises: An outdoor weather parameter monitoring local feature extraction unit is used to extract local features from the outdoor weather parameter monitoring time series input matrix to obtain an outdoor weather parameter monitoring local feature map; An outdoor weather parameter monitoring global feature extraction unit is used to extract a global feature map of outdoor weather parameter monitoring from the outdoor weather parameter monitoring local feature map; The outdoor weather parameter monitoring feature fusion unit is used to fuse the outdoor weather parameter monitoring local feature map and the outdoor weather parameter monitoring global feature map to obtain the outdoor weather parameter monitoring feature map.