Building door and window smart cloud platform with outdoor environment meteorological integrated monitoring function

Abstract

The invention provides a building door and window intelligent cloud platform with an outdoor environment meteorological integrated monitoring function, and aims to solve the technical defects of single data acquisition dimension, imperfect decision logic, weak data storage and processing capability, scattered management and control architecture, multi-target decision conflicts and the like of a building door and window control system in the prior art. According to the invention, by constructing an integrated ecological perception layer, a data access layer, a cloud scheduling layer and a decision output layer, real-time monitoring and multi-dimensional fusion of outdoor ecological environment meteorological data and indoor environment data are realized, big data analysis is introduced and adopted, and a dynamic decision mechanism of safety, comfort and energy-saving priority is combined, so that the real-time monitoring and multi-dimensional fusion of the outdoor ecological environment meteorological data and the indoor environment data is realized. The opening / closing operation state of the building doors and windows is accurately controlled, and cooperative scheduling between the door and window equipment is realized through the cloud platform. The system supports multi-scene application of smart cities, smart communities and smart buildings, improves the intelligent level of building doors and windows, effectively reduces the building energy consumption, and enhances the living comfort.

Description

Technical Field

[0001] This invention relates to the fields of building intelligence and Internet of Things technology, and in particular to a smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring. Background Technology

[0002] With residents' increasing demands for comfort, safety, and energy efficiency in their living environments, smart buildings have seen significant development. Since doors and windows are crucial factors affecting building ventilation, lighting, insect control, safety, and convenience, intelligent door and window systems are gradually becoming an important component of building energy conservation and comfortable living. Their level of intelligence directly impacts living comfort, environmental adaptability, and urban management efficiency.

[0003] Existing building door and window control technologies generally suffer from poor monitoring accuracy, data latency, difficulty in control coordination, simplification, and rigidity. They often rely on distributed, independent sensing modules to achieve single-point control (such as simple rain-sensor closure), lacking a unified cloud-based central scheduling mechanism. This makes them difficult to adapt to the refined management requirements of complex scenarios. Specific technical shortcomings are as follows: Single perception dimension: Existing technologies only collect data from a local, single environment (such as installing distributed, independent mechanical rain sensors on the outside of doors and windows), failing to achieve integrated real-time monitoring of multi-dimensional ecological and meteorological parameters both indoors and outdoors. At the same time, they lack multi-dimensional integration of city-level instructions (such as red rainstorm warnings, typhoon warnings, and air quality warnings), resulting in a lack of global correlation and meteorological scenario prediction capabilities in control decisions.

[0004] Poor data correlation: The lack of a linkage analysis mechanism between outdoor ecological environment meteorological data and indoor environmental data leads to poor adaptability, insufficient intelligence, and low accuracy of door and window control strategies.

[0005] Insufficient compatibility and scalability: Monitoring equipment from different brands is difficult to interconnect with local control terminals and actuators for doors and windows, making it impossible to adapt to the personalized needs of complex building scenarios.

[0006] The decision-making process is one-sided: existing technologies use a single threshold triggering mechanism and fail to combine multi-dimensional parameters such as the climate of the building's location, building floor, season, and wind direction to construct differentiated control rules (for example, the differences in wind speed tolerance of different floors in high-rise residential buildings are not considered, resulting in low control accuracy and poor applicability); big data analysis is not introduced, making it impossible to make adaptive decisions based on historical data trends, environmental change characteristics, and urban management requirements, resulting in low decision accuracy and insufficient flexibility; a collaborative analysis framework for indoor and outdoor ecological environment data has not been built, and the control logic is rigid, making it unable to adapt to the diverse and personalized needs of different building floors, climate zones, and user habits.

[0007] The management and control architecture is fragmented and independent: lacking a unified cloud control center, most door and window devices operate independently locally, making it impossible to achieve community-level and city-level collaborative management and control, and difficult to adapt to the development needs of smart cities for "global collaboration and precise scheduling".

[0008] Poor real-time performance of data storage and processing: Existing systems mostly adopt local data storage and processing modes, which cannot achieve long-term data retention, massive analysis, and remote access. Moreover, control parameters need to be manually configured and adjusted, and the limited local processing units cannot meet the real-time analysis needs of massive multi-dimensional data. They lack cloud-based data backup, fault diagnosis, and remote upgrade capabilities, resulting in insufficient system stability and scalability. Without the introduction of big data computing technology, they cannot guarantee data authenticity verification, cannot adaptively adjust according to user habits and environmental change trends, and cannot achieve adaptive optimization of decision rules based on long-term operating data, resulting in poor scenario adaptability.

[0009] In existing technologies, smart building platforms are not adapted to the specific control needs of building doors and windows, and cannot solve the technical pain points of multi-dimensional data fusion, real-time intelligent autonomous decision-making control, and city-level collaborative scheduling in door and window control. Therefore, there is an urgent need to build a smart cloud platform for building doors and windows that integrates outdoor environmental meteorological monitoring. Summary of the Invention

[0010] This invention addresses the technical shortcomings of existing intelligent building door and window systems, such as single data collection dimensions, incomplete decision-making logic, weak data storage and processing capabilities, fragmented management and control architecture, and conflicts in multi-objective decision-making. Combining the development trend of "global collaboration, data-driven, intelligent and efficient" in smart cities, smart communities, and smart buildings, this invention provides a smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring.

[0011] A smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring includes: The ecological sensing layer collects multi-dimensional outdoor ecological environment meteorological data, indoor environmental data, and door and window operation data, and transmits them to the cloud scheduling layer through the data access layer. The multi-dimensional outdoor ecological environment meteorological data is obtained by the integrated monitoring module, and the indoor environmental data is obtained by the indoor monitoring module. The data access layer uses a multi-protocol adaptation mechanism to access outdoor multi-dimensional ecological environment meteorological data, indoor environmental data, and city-level meteorological instructions and transmits them to the cloud scheduling layer. The cloud-based scheduling layer preprocesses the incoming data and generates door and window control commands using a multi-level computational logic combined with a dynamic priority decision-making mechanism. The multi-level computational logic includes basic rule threshold triggering and big data analysis, while the dynamic priority decision-making mechanism includes safety priority, comfort priority, and energy-saving priority. The decision output layer receives door and window control commands and transmits them to the local door and window control terminal to execute door and window actions. It then feeds back the execution results to the cloud scheduling layer, forming a closed-loop control.

[0012] Preferably, the cloud scheduling layer includes: Cloud storage module: Adopting a distributed cloud storage architecture, it retains outdoor ecological environment meteorological data, indoor environmental data, door and window operation data and user settings parameters for a long time. The storage capacity can be flexibly expanded according to user needs. Data preprocessing module: Cleans, denoises, normalizes, and fuses the raw data uploaded from the perception layer; Decision logic module: Based on preprocessed outdoor ecological environment meteorological data and indoor environmental data, combined with preset thresholds and adaptive learning algorithms, it generates door and window control decision instructions; User interaction module: Provides a web-based management platform, mobile APP, and cloud-based control program. Users can view outdoor ecological environment meteorological data, indoor environmental data, and door and window operation status in real time. It supports custom settings for meteorological parameter thresholds, decision-making strategies, and data storage cycles. It also has remote control functions, realizing multiple control modes of "intelligent decision-making + control intervention".

[0013] Preferably, the decision logic module includes: Basic rules and threshold triggering unit: Built-in configurable pre-made rule library and threshold parameter library to form a "rule-threshold" association mapping; Big Data Analytics Unit: Based on a streaming computing engine, a multi-dimensional data fusion and analysis model is built, including a priority and data feature correlation analysis module to achieve in-depth data mining and priority adaptation; Parameter data inference unit: Using massive historical stored outdoor ecological environment meteorological data, indoor environment data, urban instruction data, door and window control records, user preference settings (user usage habits), building feature data and priority decision labels as training samples, parameters are optimized through transfer learning to adapt to building door and window control scenarios.

[0014] Preferably, the basic rule and threshold triggering unit includes: The rule base contains the basic logic for door and window control; the threshold parameter base contains preset environmental and safety parameter thresholds based on different building types, building floors, and regional characteristics. Dynamic linkage decision-making: By analyzing the correlation between indoor and outdoor temperature and humidity differences, air quality differences and door and window opening status through adaptive learning algorithms, and combining the user's historical usage habits, personalized adjustment instructions are generated. Emergency Decision Making: When extreme weather conditions are detected, emergency control instructions are generated first to ensure building safety and indoor environmental comfort.

[0015] Preferably, the ecological sensing layer includes: The integrated monitoring module is used to collect outdoor multi-dimensional ecological and environmental meteorological data in real time. The outdoor multi-dimensional ecological and environmental meteorological data includes at least outdoor wind speed, outdoor wind direction, outdoor temperature, outdoor humidity, rainfall, outdoor noise, PM2.5, PM10, oxygen content, negative oxygen ions, solar radiation, and outdoor ozone content. The indoor monitoring module is used to collect indoor environmental data in real time, including indoor temperature and / or indoor humidity. The door and window status monitoring module is used to monitor the opening (position status) / closing status of doors and windows and the operating status of door and window actuators in real time, and upload the door and window operating status data to the cloud scheduling layer through the data access layer.

[0016] Preferably, the data access layer includes: Supports multi-port communication redundancy transmission using protocols including but not limited to MQTT, HTTP, Modbus, and LoRa; As an interface for interaction between the cloud platform and external data sources, it accesses public meteorological data in real time and associates it with outdoor multi-dimensional ecological environment meteorological data and indoor environmental data, transmitting them to the cloud scheduling layer.

[0017] Preferably, the decision logic module also includes: A dynamic priority decision-making mechanism is adopted, which dynamically allocates the weights of safety priority, comfort priority, and energy-saving priority based on real-time data characteristics in the multi-level operation logic.

[0018] Preferably, the specific processing procedure of the parameter data inference unit is as follows: Feature encoding: A multi-head attention mechanism is used to extract key features from multi-dimensional data and incorporate them into a priority feature encoding branch, focusing on capturing security priority triggering conditions, multi-priority conflict features, and priority switching timing features. Multi-task learning: Simultaneously train four sub-tasks: "risk identification", "optimal control strategy generation", "equipment status adaptation" and "priority dynamic scheduling". The priority dynamic scheduling sub-task is responsible for outputting the optimal priority and weight allocation scheme based on real-time data characteristics. Decision optimization: Based on the fusion and comparison of multiple data parameters such as massive historical environmental data, city-level command data, door and window control records, user preference settings (user usage habits), and environmental and climate change of the geographical location, the system adaptively optimizes decision-making capabilities, making the decision logic more in line with actual usage scenarios and usage habits.

[0019] Preferably, the cloud scheduling layer also includes: The regional 3D modeling module is used to construct the regional 3D coordinates. By importing or obtaining the regional building distribution map and the drawings of each building, it generates a 3D model of the regional building layout and determines the 3D position of each door and window of each target building on the regional building layout 3D model. The regional wind field simulation module is used to collect outdoor wind direction and speed from three or more collection points set up in the area through the ecological sensing layer. Combined with the three-dimensional model of the regional building layout, it performs wind field simulation, predicts the wind force data of each door and window at three-dimensional position, and uses the wind force data of the doors and windows to generate corresponding control commands for the doors and windows through multi-level calculation logic combined with a dynamic priority decision-making mechanism.

[0020] Preferably, the decision output layer includes: The decision output uses encrypted communication to send decision instructions to the local control terminal of the door and window through the edge gateway. The local control terminal of the door and window then issues action instructions to the door and window actuator, and the actuator completes the action. In addition, the local control terminal for doors and windows feeds back the opening status and operating parameters of doors and windows to the cloud scheduling layer for storage, and reserves a normalized API interface to connect with the smart city management and control platform and the smart community management system to achieve cross-platform control command synchronization.

[0021] This platform uses the cloud as its control hub, integrating real-time outdoor ecological and meteorological data with city-level commands to construct a multi-level operational logic of "basic rules / threshold triggering + big data analysis." It incorporates a dynamic decision-making mechanism based on safety priority, comfort priority, and energy-saving priority (where safety priority covers external risks such as city-level red rainstorm warnings and typhoon warnings). This enhances the intelligent and autonomous decision-making capabilities of building doors and windows, enabling centralized cloud-based management, real-time data storage, analysis, processing, and collaborative scheduling of door and window equipment. It constructs a precise indoor-outdoor linkage decision-making logic, promoting the upgrade of building doors and windows from "passive response operation" to "active intelligent control." This adapts to the development needs of intelligent, networked, and collaborative building terminals in smart city construction, improving the intelligence level, scenario universality, operation and maintenance convenience, and large-scale application of building door and window management.

[0022] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this patent application.

[0023] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the architecture of a smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring, as described in an embodiment of the present invention. Figure 2 This is a block diagram of the cloud scheduling layer used in the smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring of the present invention. Figure 3 This is a block diagram of the decision logic module used in the cloud scheduling layer of the smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring of the present invention. Figure 4 This is a schematic diagram illustrating the application of the smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring according to the present invention. Figure 5 This is a schematic diagram of the communication relationships of the smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring according to the present invention; Figure 6 This is a schematic diagram of the mobile terminal APP interface that provides communication connectivity for the smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring of the present invention. Detailed Implementation

[0025] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0026] like Figure 1 As shown, this embodiment of the invention provides a smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring, specifically including: Ecological Sensing Layer: The sensing layer is the data collection part, which realizes the integrated monitoring of outdoor ecological environment meteorological data. At the same time, it collects indoor environmental data and door and window operation data to support linkage analysis. Among them, an integrated outdoor ecological environment meteorological monitoring module is used for integrated multi-parameter real-time monitoring. The integrated outdoor ecological environment meteorological monitoring module includes, but is not limited to, a wind speed monitoring unit, a wind direction monitoring unit, a temperature monitoring unit, a humidity monitoring unit, a rainfall monitoring unit, a noise monitoring unit, a PM2.5 monitoring unit, a PM10 monitoring unit, an oxygen content monitoring unit, a negative oxygen ion monitoring unit, a total solar radiation monitoring unit, and an ozone monitoring unit. The monitoring unit module adopts a special protection structure design to avoid interference with the monitoring accuracy caused by rain, snow, sand and dust, fallen leaves, etc. The data collection error rate is ≤±0.5%, and the collection frequency can be flexibly adjusted within the range of 1-60 seconds / time; the indoor monitoring module can include an indoor temperature monitoring unit and a humidity monitoring unit to realize the real-time collection of indoor environmental data. The sensing layer also sets a door and window status monitoring module to monitor the operation status of each monitoring unit and actuator in real time, ensuring the continuity and reliability of data collection. Through unified collection, it provides a data basis for subsequent centralized intelligent coordination and control, avoiding control conflicts or unreasonable energy consumption caused by inconsistent control directions that may occur in the independent control method.

[0027] Data Access Layer: The data access layer is responsible for data interaction between the ecological sensing layer and the cloud scheduling layer, and between the cloud scheduling layer and the decision output layer, including receiving outdoor multi-dimensional ecological environment meteorological data, indoor environmental data, and city-level meteorological instructions, and transmitting them to the cloud scheduling layer. Among them, the city-level meteorological instructions refer to the disaster weather warning signals issued by the meteorological department for the area where this building is located, including yellow and above warnings for disaster weather such as typhoons, heavy rains, and strong winds; the communication interaction can be as Figure 5 shown, adopting a multi-port communication redundancy design and a multi-protocol adaptation mechanism (supporting protocols such as MQTT, HTTP, Modbus, LoRa, etc.) to ensure transmission stability; as the interaction interface between the cloud platform and external data sources, it realizes the real-time access of outdoor ecological environment data parameters: including dozens of structured data such as outdoor temperature, outdoor humidity, outdoor wind speed, outdoor wind direction, rainfall, outdoor noise, outdoor oxygen content, outdoor negative oxygen ions, outdoor VOC concentration, outdoor PM2.5 concentration, outdoor PM10 concentration, outdoor ozone, outdoor light intensity, etc. collected in real time by the integrated multi-parameter monitoring module deployed inside and outside the building; through multi-port communication, it ensures the smoothness of data transmission required for centralized intelligent coordination and control.

[0028] Cloud-based scheduling layer: After preprocessing the incoming data, it uses multi-level computational logic combined with a dynamic priority decision-making mechanism to generate door and window control commands. The multi-level computational logic includes basic rule threshold triggering and big data analysis. The dynamic priority decision-making mechanism includes safety priority, comfort priority, and energy-saving priority. The cloud-based scheduling layer is the platform processing unit, realizing data storage, analysis, and decision-making functions. Through shareable cloud data processing, it is beneficial to improve the coordination of centralized intelligent management and control, and reduce local data processing needs and local equipment costs.

[0029] Decision Output Layer: Receives control commands from the cloud scheduling layer and transmits them to the local control terminal (edge ​​gateway) of building doors and windows via encrypted communication protocols (HTTPS / TLS) to achieve remote control of doors and windows. Simultaneously, it feeds back the execution results of the control commands (such as door / window opening / closing status and equipment operating parameters) to the cloud scheduling layer for data storage and maintenance decisions, forming a closed-loop control system of "command-execution-feedback". Furthermore, the decision output layer reserves a normalized API interface to support collaborative integration with smart city management platforms, smart community management systems, property maintenance platforms, building energy consumption monitoring systems, and other smart home systems, enabling cross-platform synchronization of control commands.

[0030] In one embodiment, such as Figure 2 As shown, the cloud scheduling layer includes a cloud storage module, a data preprocessing module, a decision logic module, and a user interaction module: Cloud storage module: Utilizing a distributed cloud storage architecture, it provides long-term storage for outdoor ecological and meteorological data, indoor environmental data, door and window operation data, and user-defined parameters. Storage capacity can be elastically expanded according to user needs. Data storage employs a hierarchical management model of "real-time data + historical data." The data preprocessing module cleans, denoises, normalizes, and fuses the raw data uploaded from the sensing layer. It removes invalid data caused by monitoring unit malfunctions, transforms meteorological parameters of different dimensions (such as temperature, wind speed, and PM2.5 concentration) into indicators of a unified dimension through data normalization, and integrates outdoor multi-parameter meteorological data with indoor environmental data through multi-source data fusion to improve data quality and provide reliable data support for the decision-making logic module. Decision logic module: Based on preprocessed indoor and outdoor environmental data, combined with preset thresholds and adaptive learning algorithms, it generates door and window control decision commands. The decision logic adopts a multi-level operation logic of "basic rules / threshold triggering - big data analysis" to realize progressive analysis of multi-dimensional data; User interaction module: Provides a web-based management platform, a mobile app, and a cloud-based management program. The mobile app can adopt, for example... Figure 6The interface design shown allows users to view outdoor ecological environment meteorological data, indoor environmental data, and the operating status of doors and windows in real time. It supports custom settings for meteorological parameter thresholds, decision-making strategies, and data storage cycles, and also has remote control functions, realizing multiple control modes of "intelligent decision-making + control intervention".

[0031] In one embodiment, such as Figure 3 As shown, the decision logic module includes: Basic rules and threshold triggering unit: Built-in configurable pre-made rule library and threshold parameter library to form a "rule-threshold" association mapping; Big Data Analytics Unit: Based on the streaming computing engine (Flink), a multi-dimensional data fusion and analysis model is built, including a priority and data feature correlation analysis module to achieve in-depth data mining and priority adaptation; The parameter data inference unit uses massive amounts of historically stored outdoor ecological environment meteorological data, indoor environmental data, urban instruction data, door and window control records, user preference settings (user usage habits), building feature data, and priority decision labels (including safety priority event records) as training samples. It uses reinforcement learning for fine-tuning, optimizes parameters through transfer learning, and injects priority decision labels. It adopts a triple structure of "priority label - multi-source data - optimal decision" to enable the pre-trained language model to understand the mapping logic of "condition → decision". It can also first evaluate the confidence of the control scheme output by the big data analysis unit. If the confidence of the control scheme output by the big data analysis unit is less than the set confidence threshold (e.g., <85%), the parameter data inference unit is automatically triggered.

[0032] In one embodiment, the basic rule and threshold triggering unit includes: The rule base contains the basic logic for door and window control (such as closing doors and windows during heavy rain); the threshold parameter base contains preset environmental and safety parameter thresholds based on different building types (residential, commercial, public buildings), building floors, and regional characteristics (such as: rainfall trigger threshold of ≥20mm rainfall in 1 hour, closing windows on floors 1-10 of a 34-story high-rise residential building when the summer wind speed is ≥6, closing windows on floors 11-20 when the summer wind speed is ≥4, closing windows on floors 21-34 when the summer wind speed is ≥2, closing doors and windows and turning on indoor air purification equipment when the PM2.5 concentration is ≥75μg / m³, etc.). Dynamic linkage decision-making: By analyzing the correlation between indoor and outdoor temperature and humidity differences, air quality differences and the opening status of doors and windows through adaptive learning algorithms, and combining the user's historical usage habits, personalized adjustment instructions are generated (such as automatically opening doors and windows for ventilation and cooling when the outdoor temperature is 2℃ lower than the indoor temperature and the wind speed is ≤3m / s in summer). Emergency Decision Making: When extreme weather conditions are detected (such as wind speed ≥15m / s, precipitation ≥50mm / h), emergency control commands will be generated first to ensure building safety and indoor environmental comfort.

[0033] This invention can optimize decision-making based on users' different usage habits, user-defined preferences, and environmental and climate data from different regions, comprehensively analyzing and learning the decision-making basis; for example: Scenario 1: User A lives in a northern region (hot summers and cold winters). The current season is spring. The outdoor temperature is 27℃, and the outdoor air quality is good. The indoor temperature is 24℃. User A's daily routine is from 9:00 PM to 6:30 AM. User A's habit is to close bedroom doors and windows and open windows in the living room, dining room, and kitchen for slight ventilation before going to bed. The cloud platform comprehensively analyzes user usage data, preference settings, and the local environmental climate (combining public meteorological data and real-time monitored ecological parameters) to learn and formulate decision-making criteria consistent with User A's usage habits.

[0034] Scenario 2: User B's home is located in the north (cold region), the current season is winter, the current time is 7:00 AM, the current outdoor temperature is 1℃, the indoor temperature is 24℃ (underfloor heating), and the doors and windows are closed to reduce indoor heat loss. At 12:30 PM, the current outdoor temperature is 13℃, the indoor temperature is 25℃, the outdoor air quality is good, and the total solar radiation intensity is moderate. At this time, the cloud platform, based on the user's usage habits, autonomously decides whether to open the windows to ventilate and ensure indoor air quality, and analyzes which room to open the windows for ventilation and the opening angle.

[0035] Scenario 3: User C's home is located in the south (subtropical monsoon climate region), currently in spring, on the 20th floor. The current outdoor temperature is 24℃, outdoor humidity is 60%, indoor temperature is 26℃, and indoor humidity is 80%. The cloud platform collects environmental parameters in real time through indoor and outdoor environmental monitoring units, and combines them with public meteorological data parameters of the area to accurately adjust the decision-making basis. For example, if User C's home is on the 20th floor, when the outdoor wind speed is level 4, close the doors and windows to a slightly ventilated state; when the wind speed is greater than level 5, close all doors and windows.

[0036] In one embodiment, the big data analytics unit includes: Multi-source data fusion: Using an improved DS evidence theory and introducing a priority weighting factor, outdoor ecological environment meteorological data, city-level instructions, safety priority monitoring data and connected public meteorological data in the region are correlated and fused to solve the problem of heterogeneous data processing from different data sources. Temporal trend prediction algorithm: A Long Short-Term Memory (LSTM) network is used to perform time-series analysis on historically stored outdoor ecological and meteorological data, indoor environmental data, safety event records, corresponding priority decision records, and historical public meteorological data (last 30 days and 90 days). This predicts the changing trends of environmental parameters, the evolution of safety risks, and the changing trends of meteorological conditions over the next 1-24 hours (e.g., predicting wind speed increases by combining air pressure changes with public meteorological data). Simultaneously, it outputs the optimal priority adaptation scheme (e.g., switching the priority from comfort priority to safety priority in advance by combining precipitation forecasts with public meteorological data). Through fusion analysis and trend prediction, priority-oriented intermediate control suggestions are output. If the suggestions still have uncertainties (e.g., the timing of priority switching at the beginning of an improvement in extreme weather conditions), the fused data, prediction results, and priority labels are pushed to the parameter data inference unit.

[0037] In one embodiment, the specific processing procedure of the parameter data inference unit includes: Feature encoding: A multi-head attention mechanism is used to extract key features from multi-dimensional data and incorporate them into a priority feature encoding branch, focusing on capturing security priority triggering conditions, multi-priority conflict features, and priority switching timing features. Multi-task learning: Simultaneously train four sub-tasks: "risk identification", "optimal control strategy generation", "equipment state adaptation" and "priority dynamic scheduling". Among them, the priority dynamic scheduling sub-task is responsible for outputting the optimal priority and weight allocation scheme based on real-time data characteristics (especially security risk characteristics). Decision optimization: Based on the fusion and comparison of multiple data parameters such as massive historical environmental data, city-level command data, door and window control records, user preference settings (user usage habits), and environmental and climate change of the geographical location, the system adaptively optimizes decision-making capabilities, making the decision logic more in line with actual usage scenarios and usage habits.

[0038] In one embodiment, the cloud scheduling layer further includes: Region 3D modeling module: such as Figure 4The building cluster area shown is for the area where the target doors and windows need to be controlled. For example, it can be a community in a city, a factory area in an industrial park, or a village. Multiple adjacent communities, industrial parks, factories and / or villages can be regarded as the same area. The three-dimensional coordinates of the area are constructed. This is done by importing existing electronic regional building distribution maps and building drawings, or by obtaining regional building distribution maps and building drawings within the area (e.g., from the city's electronic building archive). Alternatively, drones equipped with cameras and laser scanning can be used in advance to perform auxiliary imaging to obtain regional building distribution maps and building drawings. Door and window identification and positioning are then performed. A three-dimensional model of the regional building layout is generated based on the regional building distribution map and building drawings. The three-dimensional positions of each door and window of each target building are determined on the three-dimensional model of the regional building layout. The three-dimensional positions of the doors and windows include the orientation, location and height of the doors and windows. Regional wind field simulation module: Based on multiple distributed data collection points for outdoor wind force data set in the ecological sensing layer, the module collects outdoor wind direction and speed data from three or more data collection points set up in the region's outdoor area by the ecological sensing layer. Priority is given to collecting outdoor wind force data from three or more data collection points that are not on the same straight line, such as three data collection points arranged in a triangle or four data collection points arranged in a quadrilateral. The spacing between data collection points can be limited, for example, the distance between any two points should not be less than 30 meters. Furthermore, priority can be given to using data collection points at different heights; specifically, based on the height of the tallest building in the area, the height range below the highest doors and windows can be reasonably determined. Three or more data collection points at different heights and not on the same straight line were set up. Using a 3D model of the regional building layout, CFD simulation software was employed. A turbulence model was selected, and boundary conditions were set to simulate the wind field. The wind field simulation could utilize wind direction and force data from local meteorological information, combined with outdoor wind force data (outdoor wind direction and force data) from at least one data collection point. This fully simulated and examined the changes in the wind field under the obstruction of regional buildings. During the simulation, outdoor wind force data from other different data collection points could be used for verification, i.e., the outdoor wind force data obtained from the wind field simulation at that data collection point was compared with the measured outdoor wind force data. The comparison is performed. If the difference between the two values ​​is within the set allowable deviation range, the verification is considered successful. Multiple different data collection points can be used for verification, and all verification data collection points must pass to be considered successful. If the verification fails, one or more verification data collection points are swapped with the original simulation data collection points. The outdoor wind field simulation is then performed again using the swapped data collection points (i.e., the previous verification data collection points), and the original simulation data collection points are included in the verification data collection points for verification. If the verification still fails, based on the deviation of the verification results, combined with regional image acquisition and recognition, it is determined whether there are any changes in obstacles near the data collection points with large deviations in the regional environment (e.g., [example]). If temporary structures are added, the changes in obstacles will be incorporated into the 3D model of the regional building layout for a new wind field simulation. This ensures the simulation results closely match the actual wind field in the region. For doors and windows of different buildings in the same area, or doors and windows on different walls of the same building, or doors and windows at different locations on the same wall of the same building, the same regional wind field simulation can be used. Through wind field simulation, the wind force data of each door and window at different 3D locations in different buildings is predicted, and the wind force data of doors and windows is used in multi-level computational logic combined with a dynamic priority decision-making mechanism to generate corresponding control commands for doors and windows, thereby ensuring the personalized implementation of control commands for doors and windows.

[0039] The beneficial effects of the technical solution of this invention: Compared with existing technologies, this invention aligns with the development trends of smart cities, smart communities, and smart buildings, and has the following beneficial effects: Achieve comprehensive monitoring of outdoor ecological environment meteorological data: Through multi-parameter monitoring modules and high-precision monitoring technology, it covers meteorological parameters such as wind speed, wind direction, temperature, humidity, noise, oxygen content, PM2.5, and PM10. The monitoring accuracy is high and the stability is strong, which solves the problem of single monitoring parameters in existing technologies and provides comprehensive data support for indoor and outdoor linkage control. Enhancing the accuracy of intelligent decision-making and risk prevention capabilities: Through the synergy of multi-level computational logic, dynamic priority decision-making mechanism, and public meteorological data fusion, it accurately identifies and predicts safety priority risk scenarios in advance (such as activating safety priority 30 minutes in advance by combining public meteorological precipitation forecasts), shortens the delay in handling safety incidents, and improves the accuracy of risk prediction; at the same time, it solves the problem of multi-objective decision-making conflicts, improves the decision-making accuracy in complex scenarios, and is significantly better than traditional fixed logic control.

[0040] Achieve global collaborative management and control: With a cloud platform as the core and a priority decision-making mechanism, it breaks the traditional independent operation mode of door and window equipment and realizes community-level and city-level collaborative scheduling of doors and windows (such as activating the safety priority across the entire area and simultaneously closing and locking doors and windows when a red rainstorm warning is issued), supporting the construction goal of "global perception and collaborative control" of smart cities.

[0041] Construct a precise indoor-outdoor linkage control mechanism: Based on the multi-source data fusion and intelligent decision-making logic of the cloud scheduling layer, it realizes deep linkage between outdoor ecological environment meteorological data and indoor environmental data, making the door and window control strategy more precise and personalized, which can effectively improve the livability of buildings and reduce the energy consumption of equipment such as air conditioning and fresh air systems; Achieving multi-objective optimization balance: Through priority dynamic scheduling, while ensuring safety, the system maximizes the balance between comfort and energy-saving needs, and reduces the energy consumption of building ventilation and air conditioning systems; It possesses powerful cloud data storage and processing capabilities: it adopts a distributed cloud storage architecture to achieve long-term data retention and elastic expansion, and combined with big data analysis technology, it provides data support for building environment optimization and weather trend forecasting, while ensuring data storage security.

[0042] This embodiment takes a smart community residential building as an example to deploy a smart cloud platform for building doors and windows: Sensing Layer Deployment: An integrated outdoor ecological environment meteorological monitoring module is installed outside the building (in a community center free from personnel and environmental interference). It is fixedly mounted on a bracket (it can be integrated with streetlights, landscaping, etc.). The installation height should be determined based on the actual site conditions (recommended installation height 3.5-6 meters) to avoid interference from ground obstacles and environmental factors. The outdoor ecological environment meteorological monitoring module adopts multiple power supply modes, including municipal power, battery power, and photovoltaic power generation, to ensure stable operation of the module. Different sensors within the module are connected via an industrial fieldbus and communicate using the PROFIBUS-DP protocol. The module communicates with the edge gateway via the standard Modbus-tcp protocol or a LoRa module. The edge gateway connects to the outdoor wireless base station via 4G / 5G or Ethernet.

[0043] Cloud Deployment: The cloud platform infrastructure is built using cloud servers, computing nodes are configured, and Flink streaming engine, MySQL 8.0 database, Redis 6.0 cache and MinIO object storage are deployed. Each functional module (data access, core computing, decision output, operation and maintenance monitoring) is deployed in a containerized manner using Docker to achieve independent upgrades and elastic expansion of the modules.

[0044] Data access configuration: The data access layer is adapted to outdoor ecological and environmental meteorological data, and deploys an integrated ecological and environmental meteorological monitoring unit, which integrates dozens of ecological and environmental meteorological monitoring units such as temperature monitoring unit, humidity monitoring unit, wind speed monitoring unit, wind direction monitoring unit, rainfall monitoring unit, noise monitoring unit, oxygen content monitoring unit, negative oxygen ion monitoring unit, PM2.5 monitoring unit, PM10 monitoring unit, total solar radiation monitoring unit, and ozone monitoring unit. It accesses the edge gateway through a 4G / 5G network, and the edge gateway accesses the data. The specific implementation of the core operation logic: Basic rules / threshold configuration: Pre-built rule base configuration rules and priority relationships: Safety priority rules: If a red rainstorm warning or a red typhoon warning is received, or the outdoor wind speed is ≥25m / s, or the 1-hour rainfall is ≥25mm, the doors and windows will be immediately locked and an alarm signal will be uploaded. Comfort priority rule: If there is no safety risk, and the indoor temperature is <22℃ or >26℃, the relative humidity is <40% or >60%, or the light intensity is >500 lux (summer), trigger the door / window opening / closing or shading adjustment command. Energy-saving priority rules: If there are no safety or comfort risks, and the indoor-outdoor temperature difference is ≤3℃ and outdoor PM2.5 <35μg / m³, a door and window opening ventilation command will be triggered, replacing air conditioning operation. Threshold parameter libraries are preset according to residential building characteristics: indoor temperature comfort threshold 22-26℃, relative humidity comfort threshold 40%-60%; priority switching threshold: After the safety priority trigger condition is lifted (e.g., 30 minutes after the warning is lifted), it can switch to comfort / energy-saving priority; if indoor comfort parameters are maintained for 1 hour, it can switch from comfort priority to energy-saving priority.

[0045] Decision-making logic and output: The decision output transmits control commands issued by the cloud scheduling layer to the edge gateway of the smart building's doors and windows via encrypted HTTPS protocol. The edge gateway drives the door and window actuators (handle motors, drive motors, etc.) to complete the action. The execution results (door and window opening status, opening angle) are fed back to the cloud scheduling layer via protocols such as MQTT for data storage and operation and maintenance monitoring. Control commands and execution results are backed up in real time. The operation and maintenance monitoring module sets a load threshold (CPU utilization > 80% triggers an alarm). When data transmission of a certain monitoring unit is interrupted, an operation and maintenance work order is automatically generated and pushed to the community operation and maintenance terminal.

[0046] The decision logic module calls up preprocessed indoor and outdoor environmental data, combines it with preset thresholds (such as wind speed safety threshold ≤ 5m / s, PM2.5 safety threshold ≤ 75μg / m³, etc.) and user history usage habits (such as user habit of opening doors and windows for ventilation after 18:00 in summer), and generates control decision commands. For example, when the monitored outdoor temperature is 28℃, indoor temperature is 32℃, wind speed is 2.5m / s, and PM2.5 concentration is 35μg / m³, the decision logic module determines that the ventilation conditions are met and generates the command "open the exterior window 30° and turn off the air conditioner".

[0047] Emergency Scenario for Severe Smog: When the PM2.5 and PM10 sensors in the outdoor ecological environment monitoring module collect data in real time, and the PM2.5 concentration exceeds 250 μg / m³ and the PM10 concentration exceeds 350 μg / m³ for 15 consecutive minutes, the device will activate the severe smog emergency response procedure: Taking a severe smog scenario as an example, the PM2.5 / PM10 sensor transmits data to the integrated core control module via LoRa wireless communication. The information processing hardware module performs noise reduction and filtering on the data to ensure that the concentration data error is controlled within ±10%. In a strong wind warning scenario, the system connects to the drive motor via a UART interface, and the action completion time is no more than 10 seconds. Data Acquisition and Transmission: PM2.5 and PM10 sensors transmit real-time concentration data to the integrated core control module via a standardized interface (LoRa wireless communication). At the same time, environmental parameters such as temperature, humidity, wind direction, and wind speed are uploaded. The information processing hardware module performs noise reduction and filtering on the data, eliminates abnormal fluctuation data, and ensures that the concentration data error is controlled within ±10%.

[0048] Decision and control signal transmission: The core control module, combined with a preset threshold (PM2.5 > 250μg / m³ triggers Level 1 protection), generates a control signal of "all doors and windows closed + indoor home appliances and equipment system started (internal circulation mode)", which is transmitted to the indoor smart door and window control terminal and / or home appliances and equipment via wired communication, with the signal transmission delay controlled within 0.5 seconds.

[0049] Status feedback and alarm: After the door and window control terminal executes the window closing action, it sends a "door and window are locked" status signal to the core control module via NB-IoT wireless communication. At the same time, the display screen of the indoor integrated control terminal displays the outdoor PM2.5 and PM10 concentrations and the indoor fresh air operation status in real time. If the window closing signal fails to execute (such as the door and window getting stuck), the terminal immediately issues an alarm signal and transmits the fault information to the property management platform.

[0050] Strong wind warning scenario: When the wind speed sensor detects a wind speed of 15 m / s (level 7 wind) for 5 minutes, and the wind direction sensor determines that the wind direction is directly facing the building facade, the device activates the strong wind protection procedure: Data verification and analysis: The wind speed sensor collects data once every 2 seconds. After 10 consecutive data collections exceed 15m / s, the information processing hardware module combines the wind direction data to determine the degree of wind load on doors and windows (e.g., wind direction directly facing the balcony doors and windows should be prioritized for protection), and transmits the analysis results to the core control module.

[0051] Execution of graded control signals: The core control module transmits graded signals based on the angle between the door / window position and the wind direction: Doors / windows facing the wind direction execute the "fully closed + locked and reinforced" signal, while doors / windows at an angle to the wind direction execute the "closed to 1 / 4 opening degree" signal. After receiving the signals through the UART interface, the indoor door / window control terminal drives the motor to complete the corresponding action, and the action completion time does not exceed 10 seconds.

[0052] Real-time monitoring and adjustment: During strong winds, the wind speed sensor continuously monitors wind speed changes. If the wind speed rises to 20m / s (level 8 wind), the core control module will transmit the "all exterior windows are completely locked" signal again. If the wind speed drops to below 10m / s and lasts for 10 minutes, the strong wind protection status will be automatically deactivated, the normal control of doors and windows will be restored, and the signal will be synchronized to the user's mobile APP via wireless communication.

[0053] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring, characterized in that, include: The ecological sensing layer is used to collect multi-dimensional outdoor ecological environment meteorological data, indoor environmental data and door and window operation data, and transmit them to the cloud scheduling layer through the data access layer. The data access layer is used to receive outdoor multi-dimensional ecological and environmental meteorological data, indoor environmental data, and city-level meteorological instructions using a multi-protocol adaptation mechanism, and transmit them to the cloud scheduling layer. The cloud scheduling layer is used to preprocess the incoming data and then generate door and window control commands using multi-level computational logic combined with a dynamic priority decision-making mechanism. The decision output layer is used to receive the door and window control commands, transmit them to the local door and window control terminal to execute the door and window actions, and feed back the execution results to the cloud scheduling layer.

2. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 1, characterized in that, The cloud scheduling layer includes: The cloud storage module is used to retain outdoor ecological environment meteorological data, indoor environment data, door and window operation data and user settings parameters for a long time using a distributed cloud storage architecture. The storage capacity can be flexibly expanded according to user needs. The data preprocessing module is used to clean, denoise, normalize, and fuse the raw data uploaded by the perception layer. The decision logic module is used to generate door and window control decision instructions based on preprocessed outdoor ecological environment meteorological data and indoor environment data, combined with preset thresholds and adaptive learning algorithms. The user interaction module provides a web-based management platform, a mobile app, and a cloud-based control program. Users can view outdoor ecological environment meteorological data, indoor environmental data, and the operating status of doors and windows in real time. It supports custom settings for meteorological parameter thresholds, decision-making strategies, and data storage cycles, and has remote control capabilities.

3. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 2, characterized in that, The decision logic module includes: The basic rules and threshold triggering units are used to build a configurable pre-made rule library and threshold parameter library to form a "rule-threshold" association mapping; The big data analytics unit is used to build multi-dimensional data fusion and analysis models based on the streaming computing engine. It includes a priority and data feature correlation analysis module to achieve in-depth data mining and priority adaptation. Parameter data inference unit: It uses massive historical stored outdoor ecological environment meteorological data, indoor environment data, urban instruction data, door and window control records, user preference settings, building feature data and priority decision labels as training samples to optimize parameters through transfer learning and adapt to building door and window control scenarios.

4. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 3, characterized in that, The basic rules and threshold triggering units include: The rule base contains the basic logic for door and window control; Threshold parameter library, containing preset environmental and safety parameter thresholds based on different building types, building floors and regional characteristics; Dynamic linkage decision-making: Through adaptive learning algorithms, the correlation between indoor and outdoor temperature and humidity differences, air quality differences and the opening status of doors and windows is analyzed, and personalized adjustment instructions are generated by combining the user's historical usage habits. Emergency decision-making: When extreme weather conditions are detected, emergency control instructions are generated first to ensure building safety and indoor environmental comfort.

5. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 1, characterized in that, The ecological sensing layer includes: The integrated monitoring module is used to collect multi-dimensional outdoor ecological and environmental meteorological data in real time. The multi-dimensional outdoor ecological and environmental meteorological data includes outdoor wind speed, outdoor wind direction, outdoor temperature, outdoor humidity, rainfall, outdoor noise, PM2.5, PM10, oxygen content, negative oxygen ions, solar radiation, and outdoor ozone content. The indoor monitoring module is used to collect indoor environmental data in real time, including indoor temperature and / or indoor humidity. The door and window status monitoring module is used to monitor the opening / closing status of doors and windows and the operating status of door and window actuators in real time, and upload the door and window operating status data to the cloud scheduling layer through the data access layer.

6. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 1, characterized in that, The data access layer includes: It supports multi-port communication and redundant transmission using protocols including MQTT, HTTP, Modbus, and LoRa. As an interface for interaction between the cloud platform and external data sources, it accesses public meteorological data in real time and associates it with outdoor multi-dimensional ecological environment meteorological data and indoor environmental data, transmitting them to the cloud scheduling layer.

7. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 2, characterized in that, The decision logic module also includes: A dynamic priority decision-making mechanism is adopted, which dynamically allocates the weights of safety priority, comfort priority, and energy-saving priority based on real-time data characteristics in the multi-level operation logic.

8. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 3, characterized in that, The specific processing procedure of the parameter data inference unit is as follows: Feature encoding: A multi-head attention mechanism is used to extract key features from multi-dimensional data and incorporate them into a priority feature encoding branch, focusing on capturing security priority triggering conditions, multi-priority conflict features, and priority switching timing features. Multi-task learning: Simultaneously train four sub-tasks: "risk identification", "optimal control strategy generation", "equipment status adaptation" and "priority dynamic scheduling". The priority dynamic scheduling sub-task is responsible for outputting the optimal priority and weight allocation scheme based on real-time data characteristics. Decision optimization: Based on the fusion and comparison of multiple data parameters such as massive historical environmental data, city-level command data, door and window control records, user preference settings (user usage habits), and environmental and climate change of the geographical location, the system adaptively optimizes decision-making capabilities, making the decision logic more in line with actual usage scenarios and usage habits.

9. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 2, characterized in that, The cloud scheduling layer also includes: The regional 3D modeling module is used to construct the regional 3D coordinates. By importing or obtaining the regional building distribution map and the drawings of each building, it generates a 3D model of the regional building layout and determines the 3D position of each door and window of each target building on the regional building layout 3D model. The regional wind field simulation module is used to collect outdoor wind direction and speed from three or more collection points set up in the area through the ecological sensing layer. Combined with the three-dimensional model of the regional building layout, it performs wind field simulation, predicts the wind force data of each door and window at three-dimensional position, and uses the wind force data of the doors and windows to generate corresponding control commands for the doors and windows through multi-level calculation logic combined with a dynamic priority decision-making mechanism.

10. The smart cloud platform for building doors and windows with integrated outdoor environmental meteorological monitoring as described in claim 1, characterized in that, The decision output layer includes: Encrypted communication is used to send decision commands to the local control terminal of doors and windows through the edge gateway. The local control terminal of doors and windows then issues action commands to the door and window actuators, and the actuators complete the actions. In addition, the local control terminal for doors and windows feeds back the opening status and operating parameters of doors and windows to the cloud scheduling layer for storage, and reserves a normalized API interface to connect with the smart city management and control platform and the smart community management system to achieve cross-platform control command synchronization.

Images