Method and system for controlling aluminum alloy doors and windows of smart home

Through deep learning algorithms combining position and meteorological data, intelligently calculate door and window wind loads and dynamically adjust thresholds, solving the problems of existing systems' response lag and inflexible thresholds, real-time monitoring and prediction of meteorological conditions are realized, and door and window control is improved intelligence and security.

CN118933502AInactive Publication Date: 2024-11-12QINGDAO YINGLIDA IND & TRADE CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411335574.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-24
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing smart home door and window control system relies on real-time data to make decisions and cannot predict meteorological changes, resulting in lagging responses, and the static safety threshold cannot accurately reflect risks under dynamic meteorological conditions, affecting safety protection and comfort.

Method used

The position information of doors and windows is collected through the position sensing module, and real-time meteorological data is obtained in combination with the meteorological data acquisition module. Deep learning algorithms are used to perform data embedding encoding and timing feature analysis, calculate wind loads and dynamically adjust thresholds to achieve intelligent meteorological conditions and risk levels Resolve decisions and responses.

Benefits of technology

Real-time monitoring and trend prediction of meteorological conditions are achieved, accurate decisions are made in advance, thresholds are dynamically adjusted to adapt to different meteorological conditions and risk levels, and the intelligence and safety of door and window control are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118933502A_ABST
    Figure CN118933502A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of smart home, and particularly discloses a smart home aluminum alloy door and window control method and system, and the method comprises the steps: collecting the position sensing information of an aluminum alloy door and window through a position sensing module, and collecting a real-time meteorological data set through a meteorological data collection module; a data analysis and processing algorithm based on deep learning is adopted to carry out embedded coding on position sensing information and carry out time sequence correlation analysis on meteorological data; modulation decoding is carried out based on time sequence characteristics of wind speed, wind direction and position sensing information so as to obtain wind load and air temperature of the aluminum alloy door and window; whether the aluminum alloy door and window is closed or not is automatically judged by comparing a risk factor between rainfall estimation decoding values obtained by decoding and estimating the time sequence characteristics of the air pressure and the rainfall with a preset threshold value. Therefore, meteorological conditions can be monitored in real time, the trend and the association mode of meteorological data can be learned, and future changes can be predicted, so that a more accurate decision can be made in advance.
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 technology, and more specifically, to a smart home aluminum alloy door and window control method and system. Background Art

[0002] With climate change, extreme weather events such as typhoons and hurricanes are becoming more and more frequent, and the safety of building structures has become a critical issue. Doors and windows are the outer protective components of buildings, and their wind resistance directly affects the safety of buildings. Existing door and window wind load sensing systems rely heavily on sensors, such as strain sensors installed in glass pads. However, this method not only increases costs, but also brings problems such as difficult maintenance, easy damage, and unsightly appearance.

[0003] In response to the above technical problems, the invention with patent publication number CN118532102A proposes a real-time sensing and risk avoidance control system and method for intelligent doors and windows wind loads. It obtains the position sensing information and real-time meteorological data of the target space, calculates the wind load on the doors and windows, and controls the doors and windows to perform risk avoidance actions based on the calculation results, thereby avoiding the need for additional sensors in the existing system and achieving more accurate, economical and easy-to-maintain wind load monitoring and risk avoidance control.

[0004] However, the above patent solution focuses on immediate evaluation and response based on data at the current moment, which ensures that the system can quickly respond to current environmental conditions. However, if it only relies on data at the current moment, the ability to predict future trends will be ignored, which means that the system can only make decisions based on immediate data and cannot predict future meteorological changes in advance. In practical applications, especially when meteorological conditions change rapidly, this method may lead to delayed response. For example, before a sudden strong wind or rainstorm, the system may fail to identify risks and take measures in time, thereby affecting the safety protection effect of doors and windows. In addition, the patent determines whether to close doors and windows by comparing with the safety threshold. Although a benchmark is provided, the safety threshold is usually determined based on a preset fixed value, which may not be flexible enough in some cases. When meteorological conditions change rapidly, the static safety threshold may not accurately reflect the current risk level, resulting in doors and windows failing to close in time when they need to be closed, or closing doors and windows when they do not need to be closed, affecting ventilation and comfort.

[0005] Therefore, an optimized aluminum alloy door and window control solution for smart home is desired. Summary of the invention

[0006] The present application provides a smart home aluminum alloy door and window control method and system, which can monitor meteorological conditions in real time, learn the trends and correlation patterns of meteorological data, predict future changes, and make more accurate decisions in advance. At the same time, the threshold can be dynamically adjusted according to current and historical data, so that the system can make more intelligent decisions and responses according to different meteorological conditions and risk levels.

[0007] In a first aspect, a method for controlling aluminum alloy doors and windows of a smart home is provided, comprising:

[0008] Using a position sensing module to collect position sensing information of aluminum alloy doors and windows, the position sensing information includes door and window orientation data and floor data;

[0009] The meteorological data collection module is used to collect a real-time meteorological data set, wherein each meteorological data in the real-time meteorological data set includes a temperature value, an air pressure value, a wind speed value, a wind direction value and a rainfall amount;

[0010] Calculating the wind load of the aluminum alloy doors and windows based on the real-time meteorological data set and the position sensing information;

[0011] Wherein, based on the real-time meteorological data set and the position sensing information, the wind load of the aluminum alloy doors and windows is calculated, including: performing position embedding coding on the position sensing information to obtain a position sensing embedded coding vector; performing data arrangement and time series feature extraction on the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector; performing wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature; performing modulation and decoding processing on the position sensing embedded coding vector and the wind speed-wind force interactive response feature to obtain the wind load of the aluminum alloy doors and windows;

[0012] Based on the real-time meteorological data set and the wind load of the aluminum alloy doors and windows, it is determined whether to close the aluminum alloy doors and windows.

[0013] In a possible implementation, performing position embedding coding on the position sensing information to obtain a position sensing embedded coding vector includes: performing position embedding coding on the position sensing information using a position sensing embedded coding matrix to obtain the position sensing embedded coding vector.

[0014] In a possible implementation, data arrangement and time series feature extraction are performed on the wind speed values ​​and wind direction values ​​in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector, including:

[0015] Arrange the wind speed values ​​and wind direction values ​​in the real-time meteorological data set according to the time dimension to obtain a wind speed time series input vector and a wind direction time series input vector;

[0016] The wind speed time series input vector and the wind direction time series input vector are input into a time series association encoder based on a backward LSTM model to obtain the wind speed time series association feature vector and the wind direction time series association feature vector.

[0017] In a possible implementation, performing a wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature includes:

[0018] Performing feature decoupling on the wind direction time series associated feature vector to obtain a sequence of wind direction local time series associated feature vectors;

[0019] Performing a nonlinear transformation on the wind speed time series associated characteristic vector to obtain a nonlinearly transformed wind speed time series associated characteristic vector;

[0020] Calculating the correlation matrix between the wind speed time series correlation feature vector after the nonlinear transformation and each wind direction local time series correlation feature vector in the sequence of the wind direction local time series correlation feature vector to obtain a sequence of wind speed-wind direction local time series correlation matrices;

[0021] A local-global interaction analysis is performed on the sequence of the wind speed-wind direction local time series association matrix to obtain the wind speed-wind force interaction response characteristics.

[0022] In a second aspect, a smart home aluminum alloy door and window control system is provided, comprising:

[0023] A position sensing information acquisition module, used to acquire position sensing information of aluminum alloy doors and windows using the position sensing module, wherein the position sensing information includes door and window orientation data and floor data;

[0024] A real-time meteorological data set acquisition module is used to acquire a real-time meteorological data set using the meteorological data acquisition module, wherein each meteorological data in the real-time meteorological data set includes a temperature value, an air pressure value, a wind speed value, a wind direction value and a rainfall amount;

[0025] A wind load calculation module, used to calculate the wind load of the aluminum alloy door and window based on the real-time meteorological data set and the position sensing information;

[0026] Wherein, the wind load calculation module includes: a position embedding coding unit, which is used to perform position embedding coding on the position sensing information to obtain a position sensing embedded coding vector; a time series feature extraction unit, which is used to perform data arrangement and time series feature extraction on the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector; a wind speed-wind direction interactive response analysis unit, which is used to perform a wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature; a modulation and decoding processing unit, which is used to perform modulation and decoding processing on the position sensing embedded coding vector and the wind speed-wind force interactive response feature to obtain the wind load of the aluminum alloy doors and windows;

[0027] The aluminum alloy door and window control unit is used to determine whether to close the aluminum alloy door and window based on the real-time meteorological data set and the wind load of the aluminum alloy door and window.

[0028] Compared with the prior art, the present application has the following beneficial effects: the position sensing information (door and window orientation data and floor data) of aluminum alloy doors and windows is collected through the position sensing module, and the real-time meteorological data set (temperature value, air pressure value, wind speed value, wind direction value and rainfall) is collected by using the meteorological data collection module, and the position sensing information is embedded and encoded by using the data analysis and processing algorithm based on deep learning, and the meteorological data is analyzed for temporal correlation, so as to automatically judge whether to close the aluminum alloy doors and windows by comparing the risk factor between the wind load of the aluminum alloy doors and windows obtained by modulation and decoding based on the temporal characteristics of wind speed, wind direction and position sensing information and the rainfall estimated decoded value obtained by decoding and estimating the temporal characteristics of temperature, air pressure and rainfall with the preset threshold value. In this way, the meteorological conditions can be monitored in real time, and the trend and correlation pattern of meteorological data can be learned to predict future changes, so as to make more accurate decisions in advance. At the same time, the threshold can be dynamically adjusted according to the current and historical data, so that the system can make more intelligent decisions and responses according to different meteorological conditions and risk levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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.

[0030] Figure 1 This is a schematic flowchart of the aluminum alloy door and window control method for a smart home according to an embodiment of the present application.

[0031] Figure 2 This is a data flow diagram of the aluminum alloy door and window control method for a smart home according to an embodiment of the present application.

[0032] Figure 3 This is a schematic flow chart of calculating the wind load of the aluminum alloy doors and windows based on the real-time meteorological data set and the position sensing information in the aluminum alloy door and window control method for a smart home in an embodiment of the present application.

[0033] Figure 4 In the aluminum alloy door and window control method for a smart home in an embodiment of the present application, a wind speed-wind direction interactive response analysis based on feature decoupling is performed on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a schematic flowchart of the wind speed-wind force interactive response feature.

[0034] Figure 5 This is a schematic flowchart of determining whether to close the aluminum alloy doors and windows based on the real-time meteorological data set and the wind load of the aluminum alloy doors and windows in the aluminum alloy door and window control method of the smart home in an embodiment of the present application.

[0035] Figure 6 This is a schematic block diagram of an aluminum alloy door and window control system for a smart home according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0037] In the prior art, the instant response of doors and windows to environmental conditions is achieved through real-time data collection, thereby ensuring that the system can quickly adapt to changes in the current environment, but it lacks the function of predicting future environmental trends. This means that the system can only make decisions based on existing environmental information, and cannot predict possible environmental changes in the future in advance. In actual operation, especially when weather conditions change dramatically, this approach may cause delays in system response. For example, in the face of sudden strong winds or heavy rains, the system may not be able to detect potential threats in time and take protective measures immediately, which will weaken the effect of doors and windows as a protective barrier for the home. At the same time, the method of using fixed safety thresholds to determine the opening and closing of doors and windows mentioned in the above patents, although providing certain standards, is not flexible enough when facing dynamically changing climate conditions. Fixed threshold settings may not accurately reflect the rapidly changing risk levels, resulting in doors and windows not being closed when they should be closed, or remaining closed when they do not need to be closed, which not only affects the safety of the house, but also may reduce the comfort of living.

[0038] In view of the above technical problems, the technical concept of the present application is to collect the position sensing information (door and window orientation data and floor data) of aluminum alloy doors and windows through the position sensing module, and use the meteorological data acquisition module to collect real-time meteorological data sets (temperature value, air pressure value, wind speed value, wind direction value and rainfall), and use the data analysis and processing algorithm based on deep learning to embed the position sensing information, and perform time series correlation analysis on the meteorological data, so as to automatically judge whether to close the aluminum alloy doors and windows by comparing the risk factor between the wind load of the aluminum alloy doors and windows obtained by modulation and decoding based on the time series characteristics of wind speed, wind direction and position sensing information and the rainfall estimated decoded value obtained by decoding and estimating the time series characteristics of temperature, air pressure and rainfall with the preset threshold value. In this way, it is possible to monitor meteorological conditions in real time, learn the trends and correlation patterns of meteorological data, predict future changes, and make more accurate decisions in advance. At the same time, the threshold can be dynamically adjusted according to current and historical data, so that the system can make more intelligent decisions and responses according to different meteorological conditions and risk levels.

[0039] Figure 1 This is a schematic flowchart of the aluminum alloy door and window control method for a smart home according to an embodiment of the present application. Figure 2 This is a data flow diagram of the aluminum alloy door and window control method of the smart home in the embodiment of the present application. Figure 1 and Figure 2As shown, the aluminum alloy door and window control method of the smart home includes: S1, using a position sensing module to collect position sensing information of the aluminum alloy doors and windows, and the position sensing information includes door and window orientation data and floor data; S2, using a meteorological data acquisition module to collect a real-time meteorological data set, wherein each meteorological data in the real-time meteorological data set includes a temperature value, an air pressure value, a wind speed value, a wind direction value and a rainfall amount; S3, based on the real-time meteorological data set and the position sensing information, calculating the wind load of the aluminum alloy doors and windows; S4, based on the real-time meteorological data set and the wind load of the aluminum alloy doors and windows, determining whether to close the aluminum alloy doors and windows.

[0040] In the above-mentioned aluminum alloy door and window control method of smart home, S1 uses the position sensing module to collect the position sensing information of the aluminum alloy doors and windows, and the position sensing information includes the door and window orientation data and floor data. It should be understood that the specific position information of the doors and windows has a direct impact on the external natural forces it bears, such as the size and direction of the wind. The orientation of the doors and windows determines the direction it faces, and the floor height affects whether the doors and windows are in a more open area. These factors will affect the actual wind load borne by the doors and windows. For example, a high-rise window facing the northeast may be under greater pressure under weather conditions with strong northeast winds, while low-rise windows may be less affected by the wind due to the obstruction of surrounding buildings. Therefore, understanding the orientation and floor of the doors and windows helps to more accurately evaluate the stress conditions of the doors and windows under specific meteorological conditions, and then formulate a more reasonable switching strategy.

[0041] Optionally, in one embodiment of the present application, the position sensing information of doors and windows is collected by installing corresponding sensors. For example, a magnetic sensor, a proximity sensor or other types of position detection devices can be installed to determine whether the doors and windows are in an open state and the degree of opening. As for the orientation data and floor data of the doors and windows, this information can be preset when the doors and windows are installed and input into the smart home system, or the precise position of the doors and windows can be obtained through GPS positioning technology, and its approximate orientation can be inferred accordingly. If the location information of the doors and windows has been entered into the system in advance, this information can be called through the data management within the system without the need for additional sensor equipment. Such information collection and processing helps the smart home system to more intelligently adjust the state of the doors and windows according to changes in the external environment to achieve better safety, comfort and energy saving effects.

[0042] In the above-mentioned smart home aluminum alloy door and window control method, S2 uses a meteorological data acquisition module to collect real-time meteorological data sets, wherein each meteorological data in the real-time meteorological data set includes temperature value, air pressure value, wind speed value, wind direction value and rainfall. It should be understood that considering that the collection of real-time meteorological data sets is crucial for evaluating the wind load on doors and windows, it also provides a necessary basis for predicting future weather changes and deciding whether doors and windows need to be closed. Specifically, the temperature value and air pressure value can reflect the overall condition of the atmospheric environment, while the wind speed value and wind direction value are directly related to the size and direction of the wind force faced by the doors and windows, which is very critical for calculating the wind load on the doors and windows. The information on rainfall is helpful in assessing the risks faced by doors and windows, especially under severe weather conditions, high rainfall may cause water to flow into the room, so this factor also needs to be considered when designing the door and window control logic.

[0043] Optionally, in one embodiment of the present application, the collection of real-time meteorological data sets can be achieved by installing a special meteorological data collection module. This module usually includes a series of sensors, such as temperature sensors, barometers, anemometers, wind vanes and rain gauges, etc., which can measure air temperature, air pressure, wind speed, wind direction and rainfall respectively. The collection module integrates the data collected by these sensors to form a real-time meteorological data set for subsequent analysis and processing. Optionally, in one embodiment of the present application, it is also possible to connect to the Internet through a smart home system to obtain more accurate local weather forecast data from online meteorological services to supplement the information collected by local sensors and ensure that the door and window control system can make the most appropriate decision.

[0044] In the above-mentioned aluminum alloy door and window control method of smart home, the S3 calculates the wind load of the aluminum alloy door and window based on the real-time meteorological data set and the position sensing information. It should be understood that the wind load refers to the force of wind acting on the doors and windows, and the position sensing information of the doors and windows includes the direction of the doors and windows and the floor data, which will affect the size of the wind force received by the doors and windows. The current weather conditions can be known through the information such as the temperature value, air pressure value, wind speed value, wind direction value and rainfall in the real-time meteorological data set. Combining these data with the position information of the doors and windows, the wind load received by the doors and windows can be more accurately estimated. This step is the key to ensure that the doors and windows can be automatically closed under extreme weather conditions to protect the safety of indoor property.

[0045] Figure 3 This is a schematic flow chart of calculating the wind load of the aluminum alloy doors and windows based on the real-time meteorological data set and the position sensing information in the aluminum alloy door and window control method for smart home of the embodiment of the present application. Figure 3As shown, based on the real-time meteorological data set and the position sensing information, the wind load of the aluminum alloy doors and windows is calculated, including: S31, position embedding coding of the position sensing information to obtain a position sensing embedded coding vector; S32, data arrangement and time series feature extraction of the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector; S33, wind speed-wind direction interactive response analysis based on feature decoupling of the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature; S34, modulation and decoding processing of the position sensing embedded coding vector and the wind speed-wind force interactive response feature to obtain the wind load of the aluminum alloy doors and windows.

[0046] In the above-mentioned aluminum alloy door and window control method for smart home, the S31 performs position embedding coding on the position sensing information to obtain a position sensing embedded coding vector. It should be understood that, considering that the position sensing information contains door and window orientation data and floor data, specifically, the orientation of the door and window may be expressed in words (such as east, south, west, north), and the floor may be categorical data (such as the first floor and the second floor), and this information itself is discrete and non-numerical data. In addition, there is an implicit relationship between different types of position information. Based on this, in order to convert it into a continuous numerical vector and capture the implicit association between each data, in the technical solution of the present application, the position sensing information is position embedded using a position sensing embedded coding matrix to obtain a position sensing embedded coding vector. That is, embedded coding can capture the implicit relationship between different types of position information. For example, the similarity between different orientations can be represented by their distance in the embedding space.

[0047] Optionally, in one embodiment of the present application, position embedding encoding is performed on the position sensing information to obtain a position sensing embedded coding vector, including: performing position embedding encoding on the position sensing information using a position sensing embedded coding matrix to obtain the position sensing embedded coding vector.

[0048] In the above-mentioned smart home aluminum alloy door and window control method, the S32 performs data arrangement and time series feature extraction on the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector. It should be understood that considering that the wind speed value and wind direction value in the real-time meteorological data set have time series characteristics in the time dimension, based on this, in the technical solution of the present application, the wind speed value and wind direction value in the real-time meteorological data set are data arranged according to the time dimension to obtain a wind speed time series input vector and a wind direction time series input vector.

[0049] Furthermore, in order to further capture and mine the time series feature information implicit in the wind speed time series input vector and the wind direction time series input vector, so as to better understand and analyze the time series dynamic changes of wind speed and wind direction, in the technical solution of the present application, the wind speed time series input vector and the wind direction time series input vector are input into a time series association encoder based on a backward LSTM model to obtain a wind speed time series association feature vector and a wind direction time series association feature vector.

[0050] Optionally, in one embodiment of the present application, data arrangement and time series feature extraction are performed on the wind speed values ​​and wind direction values ​​in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector, including: arranging the wind speed values ​​and wind direction values ​​in the real-time meteorological data set according to the time dimension to obtain a wind speed time series input vector and a wind direction time series input vector; inputting the wind speed time series input vector and the wind direction time series input vector into a time series associated encoder based on a backward LSTM model to obtain the wind speed time series associated feature vector and the wind direction time series associated feature vector.

[0051] In the above-mentioned smart home aluminum alloy door and window control method, the S33 performs a wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature. It should be understood that although wind speed and wind direction are two independent variables, they usually influence each other in a real environment. For example, wind in a specific direction may cause higher wind speeds or produce different wind force effects. Moreover, in different local time segments, the interrelated influences and dynamic relationships of wind speed and wind direction are different. Therefore, in the technical solution of the present application, a wind speed-wind direction interactive response analysis based on feature decoupling is performed on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind direction interactive response module as a wind speed-wind force interactive response feature.

[0052] Figure 4 In the aluminum alloy door and window control method for smart home of the embodiment of the present application, the wind speed time series associated feature vector and the wind direction time series associated feature vector are subjected to wind speed-wind direction interactive response analysis based on feature decoupling to obtain a schematic flow chart of wind speed-wind force interactive response characteristics. Figure 4As shown, optionally, in one embodiment of the present application, a wind speed-wind direction interactive response analysis based on feature decoupling is performed on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature, including: S331, feature decoupling is performed on the wind direction time series associated feature vector to obtain a sequence of wind direction local time series associated feature vectors; S332, nonlinear transformation is performed on the wind speed time series associated feature vector to obtain a wind speed time series associated feature vector after nonlinear transformation; S333, correlation matrix is ​​calculated between the wind speed time series associated feature vector after nonlinear transformation and each wind direction local time series associated feature vector in the sequence of wind direction local time series associated feature vectors to obtain a sequence of wind speed-wind direction local time series correlation matrices; S334, local-global interactive influence analysis is performed on the sequence of wind speed-wind direction local time series correlation matrices to obtain the wind speed-wind force interactive response feature.

[0053] Optionally, in one embodiment of the present application, the wind speed time series associated characteristic vector is nonlinearly transformed to obtain a wind speed time series associated characteristic vector after nonlinear transformation, including: multiplying the wind speed time series associated characteristic vector with the wind speed transformation matrix, and then adding the obtained wind speed time series transformation vector and wind speed bias vector by position to obtain the wind speed time series associated characteristic vector after nonlinear transformation.

[0054] Optionally, in one embodiment of the present application, the correlation matrix between the wind speed time series correlation feature vector after the nonlinear transformation and each wind direction local time series correlation feature vector in the sequence of the wind direction local time series correlation feature vector is calculated to obtain a sequence of wind speed-wind direction local time series correlation matrices, including: vector multiplying the transposed vector of the wind speed time series correlation feature vector after the nonlinear transformation and each wind direction local time series correlation feature vector in the sequence of the wind direction local time series correlation feature vector to obtain the sequence of wind speed-wind direction local time series correlation matrices.

[0055] Optionally, in one embodiment of the present application, a local-global interaction influence analysis is performed on the sequence of the wind speed-wind direction local time series association matrices to obtain the wind speed-wind force interaction response characteristics, including: calculating the characteristic interaction energy factors of each wind speed-wind direction local time series association matrix in the sequence of the wind speed-wind direction local time series association matrix to obtain a sequence of wind speed-wind direction local time series association characteristic interaction energy factors; inputting the sequence of wind speed-wind direction local time series association characteristic interaction energy factors into a Sigmoid function to obtain a sequence of normalized wind speed-wind direction local time series association characteristic interaction energy factors; using the sequence of normalized wind speed-wind direction local time series association characteristic interaction energy factors as a sequence of weights, calculating the position-weighted sum of the sequence of wind speed-wind direction local time series association matrices to obtain a wind speed-wind force interaction response characteristic matrix as the wind speed-wind force interaction response characteristics.

[0056] Optionally, in one embodiment of the present application, the characteristic interaction energy factors of each wind speed-wind direction local time series association matrix in the sequence of the wind speed-wind direction local time series association matrices are calculated to obtain a sequence of wind speed-wind direction local time series association characteristic interaction energy factors, including: respectively calculating the mean and variance of the wind speed-wind direction local time series association matrix to obtain the wind speed-wind direction local time series association mean and the wind speed-wind direction local time series association variance; calculating the positional difference between the wind speed-wind direction local time series association matrix and the wind speed-wind direction local time series association mean to obtain a wind speed-wind direction local time series association difference matrix; calculating the fourth power of each eigenvalue in the wind speed-wind direction local time series association difference matrix to obtain a wind speed-wind direction local time series association modulation difference matrix; calculating the expected value of the wind speed-wind direction local time series association modulation difference matrix to obtain the wind speed-wind direction local time series association expected value; and adding the wind speed-wind direction local time series association expected value to the wind speed-wind direction local time series association. The value is divided by the square of the variance of the local time series association of wind speed and wind direction to obtain the kurtosis value of the local time series association of wind speed and wind direction; the sum of the variance of the local time series association of wind speed and wind direction and the hyperparameter is calculated to obtain the first energy factor of the local time series association of wind speed and wind direction; the square of the difference between the kurtosis value of the local time series association of wind speed and wind direction and the mean value of the local time series association of wind speed and wind direction is calculated to obtain the difference value of the local time series association of wind speed and wind direction; the value obtained by multiplying the variance of the local time series association of wind speed and wind direction by a constant two and the value obtained by multiplying the hyperparameter by a constant two are added to the difference value of the local time series association of wind speed and wind direction to obtain the second energy factor of the local time series association of wind speed and wind direction; the first energy factor of the local time series association of wind speed and wind direction is divided by the second energy factor of the local time series association of wind speed and wind direction to obtain the wind speed and wind direction local time series association characteristic interaction energy factor corresponding to the local time series association matrix of wind speed and wind direction.

[0057] In summary, in the embodiment of the present application, the wind speed time series associated characteristic vector and the wind direction time series associated characteristic vector are subjected to wind speed-wind direction interactive response analysis based on characteristic decoupling, which can be expressed by the formula:

[0058] Decouple(f2)={f 21 ,f 22 ,...,f 2i ,...,f 2n}

[0059] f 1t =Wf1+b

[0060]

[0061] E norm,12i =sigmoid(E 12i )

[0062]

[0063] Wherein, f2 is the wind direction time series associated feature vector, Decouple(·) is the feature decoupling operation, and f 21 ,f 22 ,...,f 2i ,...,f 2n are the 1st, 2nd, ..., ith, ..., nth wind direction local time series associated feature vectors in the sequence of the wind direction local time series associated feature vectors, n is the number of feature vectors in the sequence of the wind direction local time series associated feature vectors, f1 is the wind speed time series associated feature vector, W and b are the wind speed transformation matrix and the wind speed offset vector, respectively, f 1t is the wind speed time series correlation feature vector after the nonlinear transformation, f 1t T Yes 1t The transposed vector of Represents vector multiplication, M 12i is the wind speed-wind direction local time series correlation matrix between the i-th wind direction local time series correlation feature vector and the wind speed time series correlation feature vector after the nonlinear transformation, M 12i (t) is M 12i The eigenvalues ​​at each position in 12i It is M 12i The mean of the matrix, E(·) is the expected value of the matrix, σ 12i 2 It is M 12i The variance of k 12i M 12i The kurtosis value, λ is a hyperparameter, E 12i It is M 12iThe corresponding wind speed-wind direction local time series correlation feature interaction energy factor, sigmoid(·) is the sigmoid function, E norm,12i It is M 12i The corresponding normalized wind speed-wind direction local time series correlation feature interaction energy factor, ⊙ is the point multiplication by position, and M is the wind speed-wind force interaction response feature matrix.

[0064] In detail, first, the wind direction time series correlation feature vector is feature decoupled to obtain a sequence of wind direction local time series correlation feature vectors, that is, by feature decoupling the wind direction time series correlation feature, the complex wind direction time series correlation feature vector can be split into a sequence of multiple finer-grained local features, each local time series feature represents the dynamic change characteristics of the wind direction in a specific time period, so that the system can better understand and process the local changes of the wind direction and improve the model's perception of the details of the wind direction. Next, the wind speed time series correlation feature vector is processed by nonlinear changes to capture and enhance the expression ability of the model to obtain the wind speed time series correlation feature vector after nonlinear transformation. Then, the correlation matrix between each wind direction local time series correlation feature and the wind speed time series feature after nonlinear change is calculated to quantify the relationship strength between the wind direction local time series correlation feature and the wind speed time series feature after nonlinear change, and help analyze the interaction between wind direction and wind speed. Subsequently, the characteristic interaction energy factor of each correlation matrix is ​​calculated to obtain a sequence of wind speed-wind direction local time series correlation feature interaction energy factors. It should be understood that the feature interaction energy factor can help quantify the interaction intensity between features. By calculating this factor, it is clear which feature combinations have a greater impact on the system output, which is very important for understanding how wind speed and wind direction work together to affect the opening and closing state of doors and windows. Then, each feature interaction energy factor is normalized based on the Sigmoid function to convert the energy factor into a weight within (0,1) to ensure the balance of the weight, so that the model can more reasonably allocate the attention to the interaction of different features. Finally, the normalized factor is used as a weight to weight each association matrix and sum it to obtain the wind speed-wind force interaction response feature matrix. In this way, the local interactions between different features can be combined to obtain a result that fully reflects the interactive influence between wind speed and wind direction, which provides help for the subsequent control of doors and windows.

[0065] Optionally, in one embodiment of the present application, the S34, performs modulation and decoding processing on the position sensing embedded coding vector and the wind speed-wind force interaction response characteristics to obtain the wind load of the aluminum alloy doors and windows, including: using the position sensing embedded coding vector as an auxiliary modal vector, inputting the auxiliary modal vector and the wind speed-wind force interaction response feature matrix into a projection layer-based modulation module to obtain a wind effect modulation feature vector; inputting the wind effect modulation feature vector into a decoder-based wind load estimation module to obtain the wind load of the aluminum alloy doors and windows.

[0066] In the above-mentioned aluminum alloy door and window control method of smart home, the position sensing embedded coding vector is used as an auxiliary modal vector, and the auxiliary modal vector and the wind speed-wind force interactive response feature matrix are input into the modulation module based on the projection layer to obtain the wind effect modulation feature vector. It should be understood that considering that the position sensing embedded coding vector contains the specific position information of the doors and windows, the specific position of the doors and windows will affect the size of the wind force they are subjected to. For example, doors and windows located on higher floors may be more susceptible to strong winds than doors and windows on lower floors. Based on this, in the technical solution of the present application, the position sensing embedded coding vector is used as an auxiliary modal vector, and the auxiliary modal vector and the wind speed-wind force interactive response feature matrix are input into the modulation module based on the projection layer to obtain the wind effect modulation feature vector. In particular, here, the wind force parameters are modulated by calculating the product between the wind speed-wind force interactive response feature matrix and the position sensing embedded coding vector, so that the position information can be combined with the interactive response characteristics of wind speed and wind direction, so as to perform personalized wind force modulation for each specific door and window position.

[0067] Optionally, in one embodiment of the present application, the position sensing embedded coding vector is used as an auxiliary modal vector, and the auxiliary modal vector and the wind speed-wind force interaction response feature matrix are input into a projection layer-based modulation module to obtain a wind effect modulation feature vector, including: matrix-vector multiplication of the wind speed-wind force interaction response feature matrix and the auxiliary modal vector to obtain the wind effect modulation feature vector.

[0068] In the above-mentioned smart home aluminum alloy door and window control method, the wind effect modulation feature vector is input into the decoder-based wind load estimation module to obtain the wind load of the aluminum alloy door and window. That is, the wind effect modulation feature vector contains the processed position information and interactive response characteristics of wind speed and wind direction, and the decoder can be responsible for reconstructing these characteristics into actual wind load values, that is, the actual pressure that the doors and windows bear under the current meteorological conditions, so as to improve the accuracy of subsequent processing.

[0069] Optionally, in one embodiment of the present application, the decoder-based wind load estimation module is used to decode and regress the wind effect modulation feature vector using the following decoding formula to obtain the wind load of the aluminum alloy door and window, wherein the decoding formula is: Wherein, V is the wind effect modulation feature vector, Y is the wind load of the aluminum alloy door and window, W is the first decoding weight matrix, Represents matrix multiplication

[0070] In particular, considering that the wind speed-wind force interaction response feature matrix represents the full time domain expression of the interaction response between the wind speed time series correlation features and the wind direction time series correlation features, the position sensing embedded coding vector represents the semantic embedded coding features of the position sensing information of the aluminum alloy doors and windows. In this way, when the position sensing embedded coding vector is used as an auxiliary modal vector and the auxiliary modal vector and the wind speed-wind force interaction response feature matrix are input into a modulation module based on a projection layer, the differences in the feature distribution time series order and time series structure between the auxiliary modal vector and the wind speed-wind force interaction response feature matrix will make the wind effect modulation feature vector have the aggregation difference of the time series feature interaction difference. Therefore, it is expected to improve the detail time series semantic aggregation expression effect of the wind effect modulation feature vector based on the fusion of local time series interaction differences.

[0071] Preferably, inputting the wind effect modulation feature vector into a decoder-based wind load estimation module to obtain the wind load of the aluminum alloy door and window comprises:

[0072] Calculating the sum of the absolute values ​​of each eigenvalue of the wind effect modulation feature vector to obtain a first wind effect modulation feature and a modulation value, and calculating the square root of the sum of the squares of each eigenvalue of the wind effect modulation feature vector to obtain a second wind effect modulation feature and a modulation value;

[0073] After performing dot-wise subtraction on the wind effect modulation feature vector and the second wind effect modulation feature and modulation value, perform dot-wise multiplication on the number of eigenvalues ​​of the wind effect modulation feature vector and the reciprocal of the first wind effect modulation feature and modulation value, and take the reciprocal of each eigenvalue to obtain a first wind effect modulation feature phase conversion vector;

[0074] After performing dot-wise subtraction on the wind effect modulation feature vector and the first wind effect modulation feature and modulation value, perform dot-wise multiplication on the wind effect modulation feature vector and the square root of the number of eigenvalues ​​of the wind effect modulation feature vector and the reciprocal of the second wind effect modulation feature and modulation value, and take the reciprocal of each eigenvalue to obtain a second wind effect modulation feature phase conversion vector;

[0075] Subtract the dot product vector of the second wind effect modulation characteristic phase conversion vector and the weighted hyperparameter from the first wind effect modulation characteristic phase conversion vector to obtain an optimized wind effect modulation characteristic vector;

[0076] The optimized wind effect modulation feature vector is input into the decoder-based wind load estimation module to obtain the wind load of the aluminum alloy door and window.

[0077] Here, the wind effect modulation feature vector, denoted as V, is optimally expressed as:

[0078]

[0079] v i ∈V∈R n

[0080] Where V is the wind effect modulation feature vector, R represents a real number set, and v i represents the eigenvalue of the i-th position of the wind effect modulation feature vector, n represents the number of eigenvalues ​​of the wind effect modulation feature vector, α represents the first wind effect modulation feature and modulation value, β represents the second wind effect modulation feature and modulation value, ⊙ represents the point multiplication by position, Indicates positional subtraction, (·) ⊙-1 represents the inverse of each eigenvalue of the calculated eigenvector, V1 represents the first wind effect modulation feature phase transition vector, V2 represents the second wind effect modulation feature phase transition vector, ω represents the weighted hyperparameter, and V′ represents the optimized wind effect modulation feature vector.

[0081] In this preferred embodiment, the difference of the characteristic value of the wind effect modulation feature vector relative to the feature set of the whole vector of the wind effect modulation feature vector and the difference of the modulation representation are used as the semantic change intensity information, and the phase-like conversion corresponding to the position-based intensity modulation is performed through different modulation representation forms, so that the aggregation enhancement of the semantic change phase perception can improve the axial aggregation receptive field along the feature aggregation direction by performing a spatial translation operation based on alternating stacking under the scale balance of the vector set of the wind effect modulation feature vector, thereby improving the perception effect of the aggregated semantics of the wind effect modulation feature vector for the change of the semantic sequence of details, so as to improve the expression effect of the wind effect modulation feature vector, and improve the accuracy of the wind load of the aluminum alloy doors and windows obtained by the wind load estimation module based on the decoder. In this way, it is possible to monitor meteorological conditions in real time, learn the trends and patterns of meteorological data, predict future changes, and make more accurate decisions in advance. At the same time, the threshold can be dynamically adjusted according to current and historical data, so that the system can make more intelligent decisions and responses according to different meteorological conditions and risk levels.

[0082] In the above-mentioned aluminum alloy door and window control method of smart home, the S4 determines whether to close the aluminum alloy door and window based on the real-time meteorological data set and the wind load of the aluminum alloy door and window. It should be understood that the real-time meteorological data set provides important information about the current weather conditions, including temperature, air pressure, wind speed, wind direction and rainfall, etc., which are factors that affect whether the doors and windows need to be closed. Wind load refers to the force generated by the wind on the doors and windows, and the location of the doors and windows (such as orientation and floor) will affect the size of the wind force they withstand. By comprehensively analyzing this information, the system can more accurately determine whether the doors and windows need to be closed under the current meteorological conditions to prevent damage caused by severe weather such as strong winds and heavy rains.

[0083] Figure 5 This is a schematic flow chart of determining whether to close the aluminum alloy door and window based on the real-time meteorological data set and the wind load of the aluminum alloy door and window in the aluminum alloy door and window control method of the smart home of the embodiment of the present application. Figure 5 As shown, optionally, in one embodiment of the present application, based on the real-time meteorological data set and the wind load of the aluminum alloy doors and windows, determining whether to close the aluminum alloy doors and windows includes: S41, performing data regularization on the temperature value, air pressure value and rainfall in the real-time meteorological data set according to the parameter sample dimension and the time dimension to obtain a rainfall-related data time series joint representation matrix; S42, performing time series correlation analysis and rainfall decoding estimation on the rainfall-related data time series joint representation matrix to obtain a rainfall estimation decoding value; S43, determining whether to close the aluminum alloy doors and windows based on the rainfall estimation decoding value and the wind load of the aluminum alloy doors and windows.

[0084] In the above-mentioned smart home aluminum alloy door and window control method, the S41, the temperature value, air pressure value and rainfall in the real-time meteorological data set are data regularized according to the parameter sample dimension and the time dimension to obtain a rainfall-related data time series joint representation matrix. It should be understood that considering that the temperature value, air pressure value and rainfall in the real-time meteorological data set are also constantly changing with the passage of time, that is, these data have time series characteristics on the time scale, and there is a mutual correlation between the various data on the time scale. Based on this, in the technical solution of the present application, the temperature value, air pressure value and rainfall in the real-time meteorological data set are data regularized according to the parameter sample dimension and the time dimension to obtain a rainfall-related data time series joint representation matrix.

[0085] In the above-mentioned aluminum alloy door and window control method of smart home, the S42 performs time series correlation analysis and rainfall decoding estimation on the rainfall related data time series joint representation matrix to obtain rainfall estimation decoding value. It should be understood that in order to capture the complex time series relationship and association information contained in the rainfall related data, so as to better capture the interaction between different meteorological parameters, in the technical solution of the present application, the rainfall related data time series joint representation matrix is ​​input into the rainfall related data time series association encoder based on the converter structure to obtain the rainfall related data time series association feature vector. Furthermore, in order to convert the processed rainfall related data time series association feature vector into a specific rainfall estimation value, so as to provide accurate meteorological information for the smart home system, in the technical solution of the present application, the rainfall related data time series association feature vector is input into the rainfall estimation module based on the decoder to obtain the rainfall estimation decoding value. That is, the decoder can improve the accuracy of rainfall estimation by learning the mapping relationship between the feature vector and the actual rainfall, so as to help the system make more reasonable door and window control decisions.

[0086] Optionally, in one embodiment of the present application, the rainfall-related data timing joint representation matrix is ​​subjected to timing correlation analysis and rainfall decoding estimation to obtain a rainfall estimation decoding value, including: inputting the rainfall-related data timing joint representation matrix into a rainfall-related data timing correlation encoder based on a converter structure to obtain a rainfall-related data timing correlation feature vector; inputting the rainfall-related data timing correlation feature vector into a rainfall estimation module based on a decoder to obtain the rainfall estimation decoding value.

[0087] In the above-mentioned aluminum alloy door and window control method of smart home, the S43 determines whether to close the aluminum alloy door and window based on the rainfall estimation decoding value and the wind load of the aluminum alloy door and window. Optionally, in one embodiment of the present application, determining whether to close the aluminum alloy door and window based on the rainfall estimation decoding value and the wind load of the aluminum alloy door and window includes: multiplying the rainfall estimation decoding value with the wind load of the aluminum alloy door and window to obtain a risk factor; and determining whether to close the aluminum alloy door and window based on the comparison between the risk factor and a preset threshold. It should be understood that the wind load reflects the pressure that the doors and windows are subjected to due to the action of wind, while the rainfall estimation decoding value provides information about the possibility and intensity of rainfall. The combination of the two can give a comprehensive indicator-risk factor, which is used to measure the safety status of doors and windows under current meteorological conditions. If the risk factor exceeds the preset safety threshold, it indicates that the doors and windows are facing a greater risk and should be closed to protect the room from wind and rain.

[0088] The advantage of this method is that it does not rely solely on a single meteorological parameter (such as wind speed), but rather comprehensively considers the impact of multiple meteorological factors on the safety of doors and windows. In this way, the system can more comprehensively assess the environmental risks faced by doors and windows, and make more accurate and timely control decisions accordingly. For example, in the case of strong winds accompanied by rainfall, even if the wind speed does not reach the threshold for closing doors and windows, considering the rainfall, doors and windows may need to be closed to prevent rain from entering the room.

[0089] In addition, this approach allows the system to dynamically adjust safety thresholds based on current and historical meteorological data, which means that the system can make more intelligent decisions and responses based on different meteorological conditions and risk levels. For example, during typhoon season, the system may use lower thresholds to ensure that doors and windows are closed in time even at lower wind speeds and rainfall, providing stronger safety protection. On the contrary, in seasons with mild and stable weather, the system may use higher thresholds, allowing doors and windows to remain open for more time to increase ventilation.

[0090] Optionally, in one embodiment of the present application, the risk factor is compared with a preset safety threshold, and if the risk factor exceeds the preset safety threshold, the action of closing the doors and windows is triggered. The closing operation is performed through the automatic control mechanism of the smart home system, including: the system sends a command to close the doors and windows to the door and window controller. After receiving the command, the door and window controller drives the doors and windows to close through a motor or other driving device.

[0091] In summary, the aluminum alloy door and window control method of the smart home according to the embodiment of the present application is explained, which collects the position sensing information (door and window orientation data and floor data) of the aluminum alloy door and window through the position sensing module, and uses the meteorological data acquisition module to collect real-time meteorological data sets (temperature value, air pressure value, wind speed value, wind direction value and rainfall), and adopts the data analysis and processing algorithm based on deep learning to embed the position sensing information, and perform time series correlation analysis on the meteorological data, so as to automatically judge whether to close the aluminum alloy door and window by comparing the risk factor between the wind load of the aluminum alloy door and window obtained by modulation and decoding based on the time series characteristics of wind speed, wind direction and position sensing information and the rainfall estimated decoded value obtained by decoding and estimating the time series characteristics of temperature, air pressure and rainfall with the preset threshold value. In this way, it is possible to monitor the meteorological conditions in real time, learn the trend and correlation pattern of meteorological data, predict future changes, and make more accurate decisions in advance. At the same time, the threshold can be dynamically adjusted according to current and historical data, so that the system can make more intelligent decisions and responses according to different meteorological conditions and risk levels.

[0092] Figure 6 Schematic block diagram of the aluminum alloy door and window control system of the smart home in the embodiment of the present application. Figure 6As shown, the aluminum alloy door and window control system 100 of the smart home includes: a position sensing information acquisition module 110, which is used to collect position sensing information of aluminum alloy doors and windows using the position sensing module, and the position sensing information includes door and window orientation data and floor data; a real-time meteorological data set acquisition module 120, which is used to collect real-time meteorological data sets using the meteorological data acquisition module, wherein each meteorological data in the real-time meteorological data set includes temperature value, air pressure value, wind speed value, wind direction value and rainfall; a wind load calculation module 130, which is used to calculate the wind load of the aluminum alloy doors and windows based on the real-time meteorological data set and the position sensing information; an aluminum alloy door and window control unit 140, which is used to determine whether to close the aluminum alloy doors and windows based on the real-time meteorological data set and the wind load of the aluminum alloy doors and windows.

[0093] Optionally, in one embodiment of the present application, the wind load calculation module includes: a position embedding coding unit, used to perform position embedding coding on the position sensing information to obtain a position sensing embedded coding vector; a time series feature extraction unit, used to perform data arrangement and time series feature extraction on the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series correlation feature vector and a wind direction time series correlation feature vector; a wind speed-wind direction interactive response analysis unit, used to perform a wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series correlation feature vector and the wind direction time series correlation feature vector to obtain a wind speed-wind force interactive response feature; a modulation decoding processing unit, used to perform modulation decoding processing on the position sensing embedded coding vector and the wind speed-wind force interactive response feature to obtain the wind load of the aluminum alloy door and window.

[0094] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned smart home aluminum alloy door and window control method have been referenced above. Figures 1 to 5 The description of the aluminum alloy door and window control system of the smart home has been introduced in detail, and therefore, its repeated description will be omitted.

[0095] 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 embodiments 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.

[0096] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the module division is only a logical function division, and there may be other division methods in actual implementation. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0097] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0098] It is obvious to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any reference to a figure in a claim should not be regarded as limiting the claim to which it relates.

[0099] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units stated in the device claim can also be implemented by one unit through software or hardware.

[0100] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for controlling aluminum alloy doors and windows of a smart home, characterized in that: include: Using a position sensing module to collect position sensing information of aluminum alloy doors and windows, the position sensing information includes door and window orientation data and floor data; The meteorological data collection module is used to collect a real-time meteorological data set, wherein each meteorological data in the real-time meteorological data set includes a temperature value, an air pressure value, a wind speed value, a wind direction value and a rainfall amount; Calculating the wind load of the aluminum alloy doors and windows based on the real-time meteorological data set and the position sensing information; Wherein, based on the real-time meteorological data set and the position sensing information, the wind load of the aluminum alloy doors and windows is calculated, including: performing position embedding coding on the position sensing information to obtain a position sensing embedded coding vector; performing data arrangement and time series feature extraction on the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector; performing wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature; performing modulation and decoding processing on the position sensing embedded coding vector and the wind speed-wind force interactive response feature to obtain the wind load of the aluminum alloy doors and windows; Based on the real-time meteorological data set and the wind load of the aluminum alloy doors and windows, it is determined whether to close the aluminum alloy doors and windows.

2. The aluminum alloy door and window control method of smart home according to claim 1, characterized in that: Performing position embedding coding on the position sensing information to obtain a position sensing embedded coding vector includes: performing position embedding coding on the position sensing information using a position sensing embedded coding matrix to obtain the position sensing embedded coding vector.

3. The aluminum alloy door and window control method of smart home according to claim 2, characterized in that: Arranging the wind speed values ​​and wind direction values ​​in the real-time meteorological data set and extracting time series features to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector, including: Arrange the wind speed values ​​and wind direction values ​​in the real-time meteorological data set according to the time dimension to obtain a wind speed time series input vector and a wind direction time series input vector; The wind speed time series input vector and the wind direction time series input vector are input into a time series association encoder based on a backward LSTM model to obtain the wind speed time series association feature vector and the wind direction time series association feature vector.

4. The aluminum alloy door and window control method of smart home according to claim 3, characterized in that: Performing a wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature, including: Performing feature decoupling on the wind direction time series associated feature vectors to obtain a sequence of wind direction local time series associated feature vectors; Performing a nonlinear transformation on the wind speed time series associated characteristic vector to obtain a nonlinearly transformed wind speed time series associated characteristic vector; Calculating the correlation matrix between the wind speed time series correlation feature vector after the nonlinear transformation and each wind direction local time series correlation feature vector in the sequence of the wind direction local time series correlation feature vector to obtain a sequence of wind speed-wind direction local time series correlation matrices; A local-global interaction analysis is performed on the sequence of the wind speed-wind direction local time series association matrix to obtain the wind speed-wind force interaction response characteristics.

5. The aluminum alloy door and window control method of smart home according to claim 4, characterized in that: Performing a local-global interaction analysis on the sequence of the wind speed-wind direction local time series association matrix to obtain the wind speed-wind force interaction response characteristics, including: Calculating the characteristic interaction energy factor of each wind speed-wind direction local time series association matrix in the sequence of wind speed-wind direction local time series association matrices to obtain a sequence of wind speed-wind direction local time series association characteristic interaction energy factors; Inputting the sequence of wind speed-wind direction local time series correlation feature interaction energy factors into a Sigmoid function to obtain a sequence of normalized wind speed-wind direction local time series correlation feature interaction energy factors; Taking the sequence of normalized wind speed-wind direction local time series correlation feature interaction energy factors as the sequence of weights, the position-weighted sum of the sequence of wind speed-wind direction local time series correlation matrices is calculated to obtain a wind speed-wind force interaction response feature matrix as the wind speed-wind force interaction response feature.

6. The aluminum alloy door and window control method of smart home according to claim 5, characterized in that: The position sensing embedded coding vector and the wind speed-wind force interactive response feature are modulated and decoded to obtain the wind load of the aluminum alloy door and window, including: The position sensing embedded coding vector is used as an auxiliary modal vector, and the auxiliary modal vector and the wind speed-wind force interaction response feature matrix are input into a modulation module based on a projection layer to obtain a wind effect modulation feature vector; The wind effect modulation feature vector is input into a decoder-based wind load estimation module to obtain the wind load of the aluminum alloy door and window.

7. The aluminum alloy door and window control method of smart home according to claim 6, characterized in that: Determining whether to close the aluminum alloy door and window based on the real-time meteorological data set and the wind load of the aluminum alloy door and window includes: The temperature value, air pressure value and rainfall in the real-time meteorological data set are regularized according to the parameter sample dimension and the time dimension to obtain a rainfall-related data time series joint representation matrix; Performing time series correlation analysis and rainfall decoding estimation on the rainfall related data time series joint representation matrix to obtain rainfall estimation decoding value; Based on the rainfall estimation decoded value and the wind load of the aluminum alloy door and window, it is determined whether to close the aluminum alloy door and window.

8. The method for controlling aluminum alloy doors and windows of a smart home according to claim 7, characterized in that: Performing time series correlation analysis and rainfall decoding estimation on the rainfall related data time series joint representation matrix to obtain rainfall estimation decoding value, including: Inputting the rainfall-related data time series joint representation matrix into a rainfall-related data time series association encoder based on a converter structure to obtain a rainfall-related data time series association feature vector; The rainfall-related data time series correlation feature vector is input into a decoder-based rainfall estimation module to obtain the rainfall estimation decoded value.

9. The aluminum alloy door and window control method of smart home according to claim 8, characterized in that: Determining whether to close the aluminum alloy door and window based on the rainfall estimation decoded value and the wind load of the aluminum alloy door and window includes: The rainfall estimate decoded value is multiplied by the wind load of the aluminum alloy door and window to obtain a hazard factor; Based on the comparison between the risk factor and the preset threshold, it is determined whether to close the aluminum alloy door and window.

10. A smart home aluminum alloy door and window control system, characterized in that: include: A position sensing information acquisition module, used to acquire position sensing information of aluminum alloy doors and windows using the position sensing module, wherein the position sensing information includes door and window orientation data and floor data; A real-time meteorological data set acquisition module is used to acquire a real-time meteorological data set using the meteorological data acquisition module, wherein each meteorological data in the real-time meteorological data set includes a temperature value, an air pressure value, a wind speed value, a wind direction value and a rainfall amount; A wind load calculation module, used to calculate the wind load of the aluminum alloy door and window based on the real-time meteorological data set and the position sensing information; Wherein, the wind load calculation module includes: a position embedding coding unit, which is used to perform position embedding coding on the position sensing information to obtain a position sensing embedded coding vector; a time series feature extraction unit, which is used to perform data arrangement and time series feature extraction on the wind speed value and wind direction value in the real-time meteorological data set to obtain a wind speed time series associated feature vector and a wind direction time series associated feature vector; a wind speed-wind direction interactive response analysis unit, which is used to perform a wind speed-wind direction interactive response analysis based on feature decoupling on the wind speed time series associated feature vector and the wind direction time series associated feature vector to obtain a wind speed-wind force interactive response feature; a modulation and decoding processing unit, which is used to perform modulation and decoding processing on the position sensing embedded coding vector and the wind speed-wind force interactive response feature to obtain the wind load of the aluminum alloy doors and windows; The aluminum alloy door and window control unit is used to determine whether to close the aluminum alloy door and window based on the real-time meteorological data set and the wind load of the aluminum alloy door and window.

Citation Information

Cited By

  • Intelligent commodity vending machine system with machine intelligence

    CN119206939A

  • Risk control intelligent door and window switch supporting mobile phone APP control

    CN120540167A