Building indoor air quality detection method and system, medium and program product

Abstract

The invention discloses a building indoor air quality detection method and system, a medium and a program product, and relates to the field of indoor air quality detection.The method comprises the steps that air quality detection data of multiple detection point positions in a target building are obtained, and a detection data set is generated; when pollution warning data appears in the detection data set, a data sharing request is sent to surrounding buildings in a preset communication range, and a verification data set is received; according to the detection data set, the verification data set and the environmental meteorological data, calculating the pollution confidence of the pollution warning data and the pollution correlation coefficient of the pollutant concentration between the buildings; determining the pollution source type of the pollution warning data according to the pollution confidence coefficient and the pollution correlation coefficient; and generating an air pollution prompt and a pollution prevention and control scheme according to the pollution warning data and the pollution source type. By implementing the application, the accuracy of building indoor air quality detection can be improved, and false alarm of equipment is avoided.

Description

[0001] This application relates to the field of indoor air quality detection, and in particular, to a method, system, medium, and program product for detecting the indoor air quality of buildings. Background Art

[0002] With the acceleration of the urbanization process and the increase in building density, the indoor air quality of buildings has received increasing attention. Indoor air quality directly affects people's health and work efficiency, and the spread of pollutants between buildings exacerbates the complexity of air quality management. Therefore, accurately identifying pollution sources and taking effective prevention and control measures have become important issues in building air quality management.

[0003] In the related art, the method for detecting the indoor air quality of buildings mainly adopts the method of single-point fixed detection. Independent detection devices are set in the building, and the indoor air quality is detected by collecting parameters such as temperature, humidity, and particulate matter in real time. When abnormal data is detected, the system will issue an alarm and start the corresponding ventilation equipment for air purification.

[0004] However, it is difficult to perform data self-checking only relying on the detection data in a fixed area in the related art, and there may be a situation of false alarms of the equipment. Summary of the Invention

[0005] This application provides a method, system, medium, and program product for detecting the indoor air quality of buildings, which is used to improve the accuracy of indoor air quality detection of buildings and avoid false alarms of equipment.

[0006] In a first aspect, this application provides a method for detecting the indoor air quality of buildings, which is applied to an air quality detection system. The method includes: obtaining air quality detection data at multiple detection points inside a target building to generate a detection data set; when pollution warning data appears in the detection data set, sending a data sharing request to surrounding buildings within a preset communication range and receiving a verification data set returned by the surrounding buildings; calculating the pollution confidence level of the pollution warning data and the pollution correlation coefficient of the pollutant concentration between buildings according to the detection data set, the verification data set, and environmental meteorological data; determining the pollution source type of the pollution warning data according to the pollution confidence level and the pollution correlation coefficient; the pollution source type includes no pollution, endogenous pollution, and exogenous pollution; generating an air pollution prompt and a pollution prevention and control plan according to the pollution warning data and the pollution source type.

[0007] In the above embodiments, the air quality detection system establishes a triple verification mechanism for multi-detection point data collection, surrounding building data verification, and environmental meteorological data analysis. By combining the calculation of pollution confidence and pollution correlation coefficient, it can accurately determine the type of pollution source, effectively avoid false alarm problems that may be caused by single-point detection, distinguish among three types: pollution-free, endogenous pollution, and exogenous pollution, and generate prevention and control plans, improving the accuracy of air quality detection and the effectiveness of prevention and control measures.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the steps of obtaining air quality detection data of multiple detection points inside a target building and generating a detection data set specifically include: obtaining air quality detection data of multiple detection points inside the target building; obtaining growth monitoring images of multiple target plants inside the target building; the target plants are biological indicators for air quality detection; generating a detection data set based on the air quality detection data and the growth monitoring images.

[0009] In the above embodiments, the air quality detection system introduces target plants as biological indicators, combines traditional physical sensor data with biological monitoring data to form a dual verification mechanism. Since biological indicators have the characteristic of cumulative response to air pollution and can reflect long-term pollution conditions, they supplement the limitations of real-time detection data and improve the reliability of detection results.

[0010] Combined with some embodiments of the first aspect, in some embodiments, after the step of generating a detection data set based on the air quality detection data and the growth monitoring images, the method further includes: extracting the apparent characteristics of the target plants in the growth monitoring images; generating pollution warning data when the apparent characteristics meet the air pollution conditions.

[0011] In the above embodiments, the air quality detection system establishes a biological response early warning mechanism by analyzing the correlation between the apparent characteristics of target plants and air pollution, can timely capture the potential pollution risks reflected by the apparent changes of plants, realize early pollution warning, and provide a basis for the timely initiation of prevention and control measures.

[0012] In some embodiments in combination with some embodiments of the first aspect, the steps of calculating the pollution confidence level of pollution warning data and the pollution correlation coefficient of pollutant concentration between buildings according to the detection data set, the verification data set, and the environmental meteorological data specifically include: constructing a heat map of pollutant concentration distribution of the target building based on the detection data set; constructing a heat map of pollutant diffusion distribution of surrounding buildings according to the verification data set; obtaining environmental meteorological data including wind direction, wind speed, temperature, and humidity within a target time period; calculating the influence path of environmental meteorological data on pollutant diffusion based on the heat map of pollutant concentration distribution, the heat map of pollutant diffusion distribution, and the environmental meteorological data to generate the pollution confidence level; and calculating the pollution correlation coefficient of pollutant concentration between buildings according to the influence path when the pollution confidence level is higher than a preset confidence threshold.

[0013] In the above embodiments, the air quality detection system uses heat map visualization technology to display the pollutant distribution status, analyzes the pollutant diffusion path in combination with environmental meteorological data, constructs a pollutant dynamic tracking model, and realizes the accurate positioning of pollution sources and the accurate prediction of pollution diffusion trends by calculating the pollution confidence level and the pollution correlation coefficient.

[0014] In some embodiments in combination with some embodiments of the first aspect, before the step of obtaining air quality detection data at multiple detection points inside the target building to generate a detection data set, the method further includes: constructing an air circulation network based on the structural characteristics, usage functions, and surrounding environment of the target building; dividing the target building into multiple detection areas based on the air circulation network and determining multiple preset detection points in each detection area; and binding a data collection frequency and a pollution alarm threshold to the preset detection points according to the building orientation, the floor height of the detection area, and the personnel density.

[0015] In the above embodiments, the air quality detection system constructs an air circulation network based on the structural characteristics, usage functions, and surrounding environment of the building, realizes the layout of detection points, and improves the pertinence and resource utilization efficiency of the detection system by setting different data collection frequencies and alarm thresholds for different areas.

[0016] In some embodiments in combination with some embodiments of the first aspect, the steps of binding a data collection frequency and a pollution alarm threshold to the preset detection points according to the building orientation, the floor height of the detection area, and the personnel density specifically include: calculating the natural ventilation coefficient of the detection area based on the building orientation and the floor height of the detection area; determining the human pollution coefficient of the change in air quality and the personnel density in the detection area according to historical detection data; binding a detection priority to each preset detection point in the detection area based on the natural ventilation coefficient and the human pollution coefficient; and adjusting the data collection frequency and the pollution alarm threshold of the preset detection points according to the detection priority.

[0017] In the above embodiments, the air quality detection system establishes a priority management mechanism for detection points by calculating the natural ventilation coefficient and the human pollution coefficient, and dynamically adjusts the detection strategy according to the actual environmental characteristics, which not only ensures the monitoring intensity of key areas but also avoids waste of detection resources.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating an air pollution prompt and a pollution prevention and control plan according to the pollution warning data and the pollution source type, the method further includes: collecting the pollutant concentration change data of each detection point to generate an execution score of the prevention and control measures; adjusting the pollution prevention and control plan according to the pollutant concentration change data and the execution score.

[0019] In the above embodiments, the air quality detection system establishes an effect evaluation and dynamic optimization mechanism for prevention and control measures. By real-time tracking the change of pollutant concentration, it evaluates the execution effect of the prevention and control measures and adjusts the prevention and control plan accordingly, forming a closed-loop optimized prevention and control system.

[0020] In a second aspect, embodiments of the present application provide an air quality detection system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions to cause the air quality detection system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, embodiments of the present application provide a computer program product containing instructions. When the computer program product runs on an air quality detection system, it causes the air quality detection system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, including instructions. When the instructions run on an air quality detection system, it causes the air quality detection system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the air quality detection system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of a linkage mechanism for multi-point detection data acquisition, verification of surrounding building data, and analysis of environmental meteorological data, source tracking is carried out by calculating the pollution confidence level and pollution correlation coefficient. Therefore, it is able to accurately identify and distinguish among three types: pollution-free, endogenous pollution, and exogenous pollution, effectively solving the problems in related technologies where single-point fixed detection cannot perform data self-checking and is prone to false alarms. Furthermore, it realizes the high reliability of detection results and the precision of prevention and control measures, improves the accuracy of building indoor air quality detection, and provides reliable data support for subsequent pollution prevention and control.

[0025] 2. Due to the adoption of a biological monitoring mechanism based on the apparent characteristics of target plants, using the changes in the growth state of plants as biological indicators for pollution warning, and combining computer vision technology for feature extraction and analysis, it is able to timely detect abnormal changes in plant apparent characteristics and generate warning signals, effectively solving the problem in related technologies that it is difficult to achieve continuous cumulative effect monitoring relying solely on physical sensors. Furthermore, it realizes the organic combination of early pollution warning and long-term monitoring, providing supplementary verification from a biological dimension for the comprehensive assessment of air quality.

[0026] 3. Due to the adoption of the calculation of natural ventilation coefficients based on building orientation and floor height, as well as the analysis of human pollution coefficients based on historical data, and setting differential detection priorities for detection points through these two key parameters, it is able to achieve reasonable allocation of detection resources and priority monitoring of key areas, effectively solving the problems in related technologies where the configuration of detection points lacks a scientific basis and the allocation of monitoring resources is unreasonable. Furthermore, it realizes the improvement of the operation efficiency of the detection system, ensures the monitoring quality of key areas, and avoids waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic flowchart of a method for detecting indoor air quality in a building according to an embodiment of the present application; Figure 2 is another schematic flowchart of a method for detecting indoor air quality in a building according to an embodiment of the present application; Figure 3 is a schematic structural diagram of a physical device of an air quality detection system according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "an", "the above", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any and all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0030] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0031] With the acceleration of the urbanization process, high-density office building areas are increasing day by day. Taking a business district as an example, multiple office buildings over 30 floors are densely distributed, and the building spacing is only 20 - 30 meters. Due to the large building density and limited ventilation conditions, indoor air quality problems occur from time to time. After a certain office building was renovated, the formaldehyde exceeded the standard, and the traditional single-point fixed detection equipment issued an alarm, but the management party could not determine whether it was a false alarm or the location of the pollution source. Multiple tenants complained of symptoms such as dizziness and eye discomfort, but the detection equipment showed intermittent data, resulting in the inability to take effective prevention and control measures. This situation is common in densely built-up areas, and there is an urgent need for an accurate and reliable air quality detection method.

[0032] In the related art, the automatic detection of indoor air quality can be achieved by using single-point fixed detection equipment for real-time monitoring. The detection equipment collects parameters such as temperature, humidity, and particulate matter through sensors, and triggers an alarm and starts the ventilation equipment when the data exceeds the preset threshold. The scenario of using the building indoor air quality detection method in the related art is introduced below.

[0033] In a group of office buildings, the property management uses the traditional single-point fixed detection method for air quality monitoring. 2 - 4 detection devices are installed on each floor, and the devices include sensors for temperature, humidity, PM2.5, formaldehyde, etc. When formaldehyde exceeding the standard is detected on a certain floor, the system automatically alarms and starts the fresh air system. However, due to the lack of a data verification mechanism, false alarms often occur. For example, when the cleaner uses aldehyde-containing cleaning agents, the sensor is triggered to exceed the standard alarm for a short time, resulting in the emergency ventilation of the entire floor being started; while the real continuous pollution is ignored due to the fluctuation of single-point data. At the same time, when pollution is found, it is impossible to determine whether it comes from internal decoration or external diffusion, resulting in blind prevention and control measures, wasting resources and having poor effects.

[0034] By adopting the indoor air quality detection method in the embodiments of the present application, through establishing a triple verification mechanism of multi-detection point data collection, surrounding building data verification, and environmental meteorological data analysis, the accurate positioning and classification of pollution sources are realized, which can not only avoid false alarms, but also formulate targeted prevention and control plans according to the types of pollution sources. The following introduces the scenarios where the indoor air quality detection method in the present application is used.

[0035] After adopting this solution, a multi-dimensional air quality detection network has been established in an office building. According to the building structure characteristics, the system divides each floor into multiple detection areas and arranges differentiated detection points. At the same time, ornamental plants are placed as biological indicators in key areas. When it is detected that the formaldehyde exceeds the standard, the system automatically requests data sharing from surrounding buildings and conducts comprehensive analysis in combination with environmental meteorological data. For example, when it is detected that the formaldehyde in the southwestern corner area exceeds the standard, the system immediately analyzes that the surrounding data is normal and that the area has just been renovated, accurately determines it as endogenous pollution, and timely activates the directional ventilation measure, avoiding false alarms and improving the prevention and control efficiency.

[0036] It can be seen that by adopting the air quality detection system in the embodiments of the present application, while accurately detecting the indoor air quality, it can also effectively solve the problems of false alarms caused by single-point detection and the difficulty in locating pollution sources, thereby achieving high reliability of detection results and accuracy of prevention and control measures.

[0037] For the convenience of understanding, the method provided in this embodiment will be described in terms of its process in combination with the above scenarios. Please refer to Figure 1 , which is a schematic flow diagram of the indoor air quality detection method in the embodiments of the present application.

[0038] S101. Obtain the air quality detection data of multiple detection points inside the target building and generate a detection data set.

[0039] Among them, the target building refers to a specific building that needs to conduct air quality detection; the detection point refers to a fixed monitoring position set inside the building for collecting air quality data; the air quality detection data is used to represent a numerical set of air quality-related parameters including temperature, humidity, particulate matter concentration, carbon dioxide concentration, etc.; the detection data set refers to a structured data set formed by integrating the air quality detection data collected at multiple detection points according to the time series.

[0040] The air quality detection system continuously performs data collection during the daily operation of the building. Specifically, the air quality detection system first obtains real-time air quality parameter data from the sensor devices at each detection point, including temperature values, humidity values, particulate matter concentration values, etc.; then cleans and preprocesses the collected raw data, removing outliers and redundant data; finally, organizes and stores the processed data according to dimensions such as timestamp and detection point to form a detection data set in a standard format.

[0041] In some embodiments, the data collection and processing process can be implemented in various ways: Optionally, the air quality detection system adopts a distributed data collection architecture, with each detection point equipped with an independent data collection unit, and the data is uploaded to the central processing server in real time through a wireless network. After the server cleans and integrates the data, a detection data set is generated; Optionally, the air quality detection system adopts a centralized data collection architecture, and all detection points are connected to the central controller through a wired network. The controller uniformly collects and processes the data to directly generate a detection data set. It can be understood that other network topologies and data processing methods can also be used to achieve data collection and integration, which are not limited here.

[0042] S102. When pollution warning data appears in the detection data set, send a data sharing request to the surrounding buildings within the preset communication range and receive the verification data set returned by the surrounding buildings.

[0043] Among them, the pollution warning data represents abnormal data in the detection data set that exceeds the preset threshold; the preset communication range is the surrounding building coverage range determined according to the pollutant diffusion characteristics, usually a specific radius range centered on the target building; the data sharing request is used to represent the data exchange application initiated to the surrounding buildings; the verification data set refers to the set of air quality data obtained from the surrounding buildings for cross-verification.

[0044] The air quality detection system starts the data verification process when detecting abnormal data. Specifically, when data exceeding the preset pollution threshold appears in the detection data set, the air quality detection system first determines all the buildings within the preset communication range that have the ability to share data; then sends a data sharing request containing information such as time period and data type to these buildings; after obtaining the authorization of the buildings, an encrypted data transmission channel is established; finally, it receives and verifies the integrity and validity of the verification data set returned by the surrounding buildings, and incorporates the verified data set into subsequent analysis.

[0045] In some embodiments, the data sharing and verification process can be implemented in various ways: Optionally, the air quality detection system constructs a data sharing network between buildings using blockchain technology, and automatically executes data exchange and verification through smart contracts to ensure the security and credibility of data sharing; Optionally, the air quality detection system establishes an instant communication network between buildings based on the Internet of Things protocol, uses asymmetric encryption to protect the security of data transmission, and verifies the reliability of the data source through digital signatures. It can be understood that other data sharing protocols and security authentication mechanisms can also be used to implement data exchange and verification between buildings, which are not limited here.

[0046] S103. According to the detection data set, the verification data set, and the environmental meteorological data, calculate the pollution confidence level of the pollution warning data and the pollution correlation coefficient of the pollutant concentration between buildings.

[0047] Among them, the environmental meteorological data represents the external environmental factors affecting the diffusion of pollutants, including wind direction, wind speed, temperature, humidity, etc.; the pollution confidence level refers to the reliability score of the pollution warning data; the pollution correlation coefficient is used to represent the correlation index of the pollutant concentration between different buildings; the pollutant concentration represents the content level of specific pollutants in the air.

[0048] The air quality detection system conducts comprehensive analysis after obtaining complete data. Specifically, first construct a spatio-temporal distribution model of pollutants by combining the detection data set and the verification data set; then introduce the environmental meteorological data to establish a pollutant diffusion prediction model considering the influence of meteorological factors; based on the calculation results of the two models, use a multi-dimensional evaluation method to calculate the pollution confidence level; finally, through the correlation analysis method, calculate the temporal variation law of the pollutant concentration between buildings to obtain the pollution correlation coefficient.

[0049] It should be noted that the pollutant diffusion prediction model adopts a hybrid architecture combining a physical model and deep learning. Among them, the physical model describes the diffusion process of pollutants in the building complex based on the Navier-Stokes equations, including the continuity equation, the momentum equation, and the pollutant concentration transport equation. The deep learning part adopts a graph neural network (GNN) structure to optimize the parameters in the physical model and process the complex spatial relationships between buildings. The training data includes: three-dimensional geometric data of buildings, records of historical pollution diffusion processes, meteorological observation data, etc. The model training adopts an end-to-end method, and the physical model provides a benchmark prediction result, and the GNN learns to correct the parameters by minimizing the prediction error. The verification standard requires that the average relative error of the diffusion prediction within 15 minutes is less than 20%, and the prediction error within 30 minutes is less than 30%.

[0050] In some embodiments, the data analysis and calculation processes can be implemented in various ways: Optionally, the air quality detection system adopts machine learning methods, learns the pollution characteristics and diffusion laws in historical data through a deep neural network model, combines real-time data to predict the pollutant diffusion trend, and calculates various indicators; Optionally, the air quality detection system is based on a fluid dynamics model and an atmospheric diffusion model, and calculates the diffusion process of pollutants in the building complex through numerical simulation methods to evaluate various indicators. It can be understood that other mathematical models and calculation methods can also be used to implement the analysis and evaluation of pollution data, which are not limited here.

[0051] S104. Determine the pollution source type of the pollution warning data according to the pollution confidence level and the pollution correlation coefficient.

[0052] Among them, the pollution source types include no pollution, endogenous pollution, and exogenous pollution.

[0053] Among them, the pollution source type represents the source category causing air pollution, including no pollution, endogenous pollution, and exogenous pollution; endogenous pollution refers to the pollution generated inside the building; exogenous pollution is used to represent the pollution introduced from the external environment.

[0054] After obtaining the evaluation indicators, the air quality detection system conducts pollution source determination. Specifically, first analyze the pollution confidence level to confirm the authenticity of the pollution event; then evaluate the spatial correlation of pollutant diffusion according to the pollution correlation coefficient; then match the two indicators with the preset determination rules; finally, comprehensively consider the determination results of each item to obtain the final determination conclusion of the pollution source type. During the determination process, the system will consider the characteristic manifestations of different types of pollution sources. For example, endogenous pollution usually shows high local concentration, while exogenous pollution shows characteristics such as regional distribution.

[0055] It should be noted that the preset determination rules here are a multi-level decision tree established based on the pollutant diffusion dynamics model and historical data analysis. During the rule construction process, first, through the characteristic clustering analysis of historical pollution events, extract the typical characteristic patterns of different types of pollution sources; then, combined with the diffusion law of pollutants in the building complex, establish a discriminant function including multiple dimensions such as time series, spatial distribution, and concentration gradient; finally, optimize the discriminant threshold through machine learning methods to form a complete set of determination rules. This set of rule systems can accurately identify the characteristic manifestations of pollution source types. For example, when a sudden high-concentration pollution occurs at a certain detection point while the detection values of surrounding buildings are normal, the system will determine it as endogenous pollution according to this local characteristic; when the detection values of multiple buildings show a concentration gradient consistent with the wind direction, it will be determined as exogenous pollution.

[0056] In some embodiments, the pollution source determination process can be implemented in various ways: Optionally, the air quality detection system adopts a decision tree algorithm. By establishing multi-level determination rules, it gradually analyzes the numerical characteristics of pollution confidence and correlation coefficients, and finally obtains the pollution source type. Optionally, the air quality detection system is based on pattern recognition technology. By comparing the characteristic patterns of historical pollution events, it identifies the type characteristics of the current pollution event and determines the pollution source. It can be understood that other determination algorithms and recognition methods can also be used to determine the pollution source type, which is not limited here.

[0057] S105. Generate an air pollution alert and a pollution prevention and control plan according to the pollution warning data and the pollution source type.

[0058] Among them, the air pollution alert refers to the warning information sent to the building users; the pollution prevention and control plan refers to the set of response measures formulated for a specific pollution source type; the prevention and control measures are used to represent the specific execution actions for controlling and eliminating pollution.

[0059] The air quality detection system formulates a response strategy after determining the pollution source type. Specifically, first select the applicable prevention and control measure template according to the pollution source type; then adjust the execution parameters of the prevention and control measures in combination with the specific parameters of the pollution warning data; then generate a warning information including the description of the pollution situation, the influence range, the protection suggestions, etc.; finally, integrate to form a complete pollution prevention and control plan, and publish the warning information through multiple channels and start the corresponding prevention and control measures.

[0060] It should be noted that the specific parameters of the pollution warning data are a multi-dimensional data feature set, including quantitative and qualitative indicators for describing the pollution state. In the quantification dimension, it includes numerical parameters such as the multiple of pollutant concentration exceeding the standard, the pollution duration, and the pollution diffusion rate; in the spatial dimension, it includes spatial distribution characteristics such as the pollution influence range and the pollutant concentration gradient distribution; in the time dimension, it includes time series characteristics such as the change trend of the pollutant concentration and the time of peak value appearance. The air quality detection system can accurately evaluate the severity and development trend of the pollution by comprehensively analyzing these parameters, so as to provide accurate data support for the formulation of the prevention and control plan. For example, when it is detected that the concentration of a certain harmful gas exceeds the standard by 2 times and shows a continuous upward trend, the system will correspondingly increase the execution level and response speed of the prevention and control measures.

[0061] In addition, the air quality detection system can adopt a hierarchical linkage information release mechanism to achieve differential push according to the different roles and responsibilities of information recipients. At the building management level, the system pushes detailed pollution data and prevention and control instructions to management personnel through the building intelligent management platform; at the equipment control level, the system issues automatic adjustment instructions to equipment such as ventilation and air conditioning through the industrial control network; at the user service level, the system pushes personalized protection suggestions to building users through the building automation system. This multi-level information release mechanism ensures that all relevant parties can timely obtain pollution warning information that meets their needs. For example, when it is detected that the indoor formaldehyde exceeds the standard, the system will simultaneously activate the automatic adjustment of ventilation equipment, send a detailed test report to management personnel, and push precautions to users.

[0062] In some embodiments, the generation and execution of the prevention and control plan can be achieved in various ways: Optionally, the air quality detection system adopts expert system technology, matches the most suitable combination of prevention and control measures through a rule engine, and dynamically adjusts the execution strategy according to real-time feedback; Optionally, the air quality detection system is based on scenario deduction technology, optimizes the specific implementation steps of the prevention and control plan by simulating the execution effects of different prevention and control measures. It can be understood that other decision support methods can also be used to formulate and optimize the prevention and control plan, which is not limited here.

[0063] In the above embodiments, the air quality detection system effectively improves the detection accuracy by constructing a multi-level data verification system. In actual applications, the system can dynamically adjust the detection strategy according to the structural characteristics, usage functions, and environmental conditions of the building, realizing the optimal allocation of resources and the improvement of detection efficiency. The following supplements the scenarios of this embodiment.

[0064] Based on the continuous optimization of this solution, a business district has achieved regional-level air quality collaborative management. The detection systems of each building are interconnected through a secure data sharing mechanism, constructing a pollutant diffusion warning network covering the entire region. When pollution is detected in a certain building, the system automatically analyzes the real-time data and historical data of surrounding buildings, and combines the wind direction and wind speed data of the weather station to accurately predict the pollutant diffusion path. For example, in a decoration pollution incident, the system not only activates prevention and control measures for the pollution source building, but also notifies the downwind buildings that may be affected in advance to adjust their fresh air strategies, realizing regional joint prevention and control and minimizing the pollution impact range.

[0065] After combining the above scenarios, the following further describes the more specific process of the method provided in this embodiment in more detail. Please refer to Figure 2 , which is another process schematic diagram of the building indoor air quality detection method in the embodiment of the present application.

[0066] S201. Based on the structural characteristics, usage functions, and surrounding environment of the target building, construct an air circulation network.

[0067] Among them, the structural characteristics represent the physical structure characteristics such as the spatial layout, door and window distribution, and ventilation system of the building; the usage function refers to the usage purposes and activity types of different areas within the building; the surrounding environment is used to represent environmental factors such as the terrain, vegetation, and adjacent buildings outside the building; the air circulation network represents a topological structure model that describes the air flow paths and characteristics inside the building.

[0068] Before planning the detection points, the air quality detection system first constructs an air circulation network. Specifically, the system first obtains the CAD drawings and BIM models of the building, extracts the building structure information; then combines the usage function attributes of each area to determine the air quality management requirements of different areas; then analyzes the impact of the surrounding environment of the building on natural ventilation; finally, simulates the air flow path through the computational fluid dynamics model and establishes an air circulation network model including nodes and connection relationships, where the nodes represent key spatial positions and the connection relationships represent air circulation channels.

[0069] It should be noted that the computational fluid dynamics model uses a system of nonlinear partial differential equations to describe the air flow characteristics in the construction of the air circulation network. The model first establishes a mathematical expression of the internal airflow field of the building based on the Navier-Stokes equations, including the momentum equation, continuity equation, and energy equation; then discretizes the continuous domain into grid cells by the finite volume method and applies the conservation law to each cell; then uses the SIMPLE algorithm to solve the pressure-velocity coupling equation and iteratively calculates the steady-state airflow field distribution. In the boundary condition setting, the geometric characteristics and pressure boundaries of the building doors, windows, and ventilation openings, as well as the influence of heat sources and cold sources on the air flow, are considered. For example, when there is an atrium space in the building, the model will pay special attention to the vertical air flow movement caused by temperature stratification and the chimney effect, so as to accurately describe the air flow paths and characteristics inside the building.

[0070] In some embodiments, the construction of the air circulation network can be achieved in multiple ways: Optionally, the air quality detection system uses graph theory methods to construct a network model, abstracts the spatial positions as nodes, abstracts the air circulation paths as edges, optimizes the network structure through the minimum spanning tree algorithm, and calculates the key nodes and paths; Optionally, the air quality detection system is based on the computational fluid dynamics model and calculates the internal airflow field distribution of the building through numerical simulation methods, identifies the airflow organization characteristics, and constructs a network model that reflects the actual air flow law. It can be understood that other network construction methods can also be used to model the air circulation characteristics, which are not limited here.

[0071] S202. Divide the target building into multiple detection areas based on the air circulation network, and determine multiple preset detection points in each detection area.

[0072] Among them, the detection area refers to an independent monitoring unit divided according to the air circulation characteristics; the preset detection point refers to a fixed monitoring position set within the detection area.

[0073] After constructing the air circulation network, the air quality detection system performs area division and point layout. Specifically, the system first identifies the natural zones of air circulation based on the network topology structure; then refines the zones according to the spatial functions and usage characteristics; then calculates the area, volume, and ventilation conditions of each zone; finally, according to the specification requirements and actual needs, determines the number and specific locations of the detection points in each zone to ensure the integrity and representativeness of the monitoring coverage.

[0074] In some embodiments, area division and point layout can be achieved in various ways: Optionally, the air quality detection system uses the clustering analysis method to divide the space into multiple independent zones based on the air circulation characteristics, and then determines the optimal detection point layout through the coverage optimization algorithm; Optionally, the air quality detection system is based on the partition control theory, and by establishing a multi-objective optimization model, comprehensively considering the detection effect and cost factors, generates the optimal area division and point layout scheme. It can be understood that other optimization algorithms can also be used to achieve the detection area division and point layout, which is not limited here.

[0075] S203. Bind the data collection frequency and pollution alarm threshold to the preset detection points according to the building orientation, the floor height of the detection area, and the personnel density.

[0076] Among them, the building orientation represents the angle between the main facade of the building and the due north direction; the floor height refers to the vertical position where the detection area is located; the personnel density is used to represent the number of personnel per unit area; the data collection frequency represents the sampling time interval of the detection data; the pollution alarm threshold refers to the critical value of the pollutant concentration that triggers the pollution alarm.

[0077] After completing the point layout, the air quality detection system configures the detection parameters. Specifically, the system first analyzes the influence degree of the building orientation on natural ventilation; then calculates the vertical temperature difference effect in combination with the floor height; then estimates the artificial pollution load according to the personnel density; finally, considering these factors comprehensively, sets appropriate data collection frequencies and pollution alarm thresholds for each detection point to achieve the differential configuration of detection resources.

[0078] It should be noted that the dynamic adjustment of the data acquisition frequency is achieved based on the adaptive sampling theory. The system first establishes a state evaluation model that includes factors such as the change rate of pollutant concentration, the intensity of personnel activities, and the fluctuation of environmental parameters. Then, it determines the minimum sampling rate required for signal reconstruction through the Shannon sampling theorem. Next, it uses a Kalman filter to predict the change trend of state variables and dynamically adjusts the sampling interval according to the prediction error. When a rapid change or abnormal trend is detected, the system will automatically increase the sampling frequency to capture more detailed information. For example, during the lunch break in the office area, due to the reduction of personnel activities, the system will appropriately reduce the sampling frequency to save resources. During periods of drastic changes in environmental parameters such as the start or stop of the air conditioning system, the system will increase the sampling frequency to accurately track the parameter changes.

[0079] In some embodiments, the configuration of the detection parameters can be achieved in various ways: Optionally, the air quality detection system adopts a fuzzy logic control method. By establishing a multi-factor evaluation model, it dynamically adjusts the detection parameters to achieve intelligent allocation of detection resources. Optionally, the air quality detection system is based on statistical methods. By analyzing the pollution characteristic laws in historical data, it establishes a parameter adaptive adjustment mechanism to optimize the detection efficiency. It can be understood that other parameter optimization methods can also be used to achieve the dynamic adjustment of the detection configuration, which is not limited here.

[0080] In some embodiments, the air quality detection system will be set based on historical data. That is, first, based on the building orientation and the floor height of the detection area, calculate the natural ventilation coefficient of the detection area. Then, according to the historical detection data, determine the human pollution coefficient of the change in air quality with the personnel density in the detection area. Then, based on the natural ventilation coefficient and the human pollution coefficient, bind the detection priority to each preset detection point in the detection area. Finally, according to the detection priority, adjust the data acquisition frequency and the pollution alarm threshold of the preset detection points.

[0081] Among them, the natural ventilation coefficient represents the degree of influence of the building orientation and height on air circulation; the human pollution coefficient refers to the intensity of the influence of personnel activities on air quality; the detection priority is used to represent the monitoring importance level of the detection point; the historical detection data represents the accumulated air quality monitoring records in the past; the data acquisition frequency refers to the sampling time interval of the detection data.

[0082] The air quality detection system optimizes the parameter configuration after completing the layout of the detection points. Specifically, the system first obtains the geometric parameters of the building and the historical monitoring data. Then, it establishes a multi-factor evaluation model that includes natural ventilation and personnel activities. Next, it calculates the environmental characteristic coefficients of each detection area. Then, it determines the priority ranking of the detection points based on the characteristic coefficients. Finally, it configures personalized monitoring parameters for each detection point according to the priority to achieve differential allocation of detection resources.

[0083] In some embodiments, the optimization of parameter configuration can be achieved in various ways: Optionally, the air quality detection system constructs a time series prediction model based on a multi-layer neural network. Through deep learning of historical data, it identifies the laws of air quality changes and adaptively adjusts the monitoring parameter configuration; Optionally, the air quality detection system adopts a fuzzy comprehensive evaluation method. By establishing a multi-level index system, it comprehensively evaluates the weights of various influencing factors and dynamically optimizes the monitoring configuration plan. It can be understood that other intelligent optimization algorithms can also be used to achieve the dynamic configuration of detection parameters, which is not limited here.

[0084] S204. Obtain the air quality detection data of multiple detection points inside the target building.

[0085] Among them, the air quality detection data represents the air environment parameters collected by sensors; the sensor type refers to the professional equipment used to detect different pollutants, including particulate matter sensors, gas sensors, etc.; the data collection period is used to represent the time interval between two consecutive data collections; the raw data refers to the unprocessed sensor output values.

[0086] The air quality detection system continuously performs data collection tasks during daily operation. Specifically, the system first checks the working status of the sensors at each detection point; then reads data from the sensors according to the preset collection frequency; then performs real-time calibration on the collected data to eliminate system errors such as sensors; then performs data integrity checks to identify and mark outliers; finally, packages the calibrated data in a unified format, adds a timestamp and a location identifier to form a standardized detection data record.

[0087] In some embodiments, the data collection process can be achieved in various ways: Optionally, the air quality detection system adopts a distributed collection architecture, deploys edge computing units at each detection point to achieve local preprocessing and quality control of data, and then transmits the processed data to the central server; Optionally, the air quality detection system is based on Internet of Things technology. By establishing a sensor mesh network, it realizes multi-path transmission and mutual backup mechanism of data, and improves the reliability of data collection. It can be understood that other data collection schemes can also be used to obtain detection data, which is not limited here.

[0088] S205. Obtain the growth monitoring images of multiple target plants inside the target building.

[0089] Among them, the target plant is a biological indicator for air quality detection, that is, an indicator plant specifically selected to be sensitive to specific pollutants; the growth monitoring image refers to the high-definition picture data recording the growth status of the plant; the biological indicator is used to represent an organism that can reflect environmental quality through morphological changes; the image acquisition device represents a professional camera device for shooting the growth status of the plant.

[0090] The air quality detection system conducts plant monitoring at fixed time intervals. Specifically, the system first activates the image acquisition device and adjusts the focal length and exposure parameters; then captures high-definition images of the target plant from multiple angles; next, preprocesses the images, including light correction, noise elimination, etc.; then extracts the morphological characteristic parameters of the plant, such as leaf area, leaf color, stem inclination angle, etc.; finally, correlates these biometric data with environmental parameters to establish plant response indicators.

[0091] In some embodiments, the plant monitoring process can be achieved in various ways: Optionally, the air quality detection system adopts computer vision technology and analyzes plant images through a deep learning model to automatically identify the health status and growth anomalies of plants, realizing early warning of pollution; Optionally, the air quality detection system is based on spectral analysis technology, collects the reflection spectral characteristics of plants through a multispectral camera, establishes a plant stress response model, and evaluates the air quality status. It can be understood that other biological monitoring methods can also be used to achieve air quality assessment based on plants, which is not limited here.

[0092] The image analysis of plant growth characteristics adopts the computer vision method of deep learning. The system first extracts the morphological characteristics of plants, including information such as leaf shape, area, and texture, through a multi-scale convolutional neural network; then uses an image segmentation algorithm to separate plant organs and establish a quantitative description of morphological parameters; next, analyzes the growth changes of plants through temporal contrast to construct a plant growth curve; finally, classifies and identifies growth anomalies in combination with an expert knowledge base. The model adopts a transfer learning method and quickly adapts to the feature extraction requirements of different plant varieties through a pre-trained network. For example, when abnormal morphologies such as chlorosis and curling appear in plant leaves, the system will evaluate the potential air pollution risk in combination with the spatio-temporal evolution law of these visual characteristics.

[0093] S206. Generate a detection dataset according to the air quality detection data and growth monitoring images.

[0094] Among them, the detection dataset refers to a comprehensive dataset integrating physical sensor data and biological monitoring data; data correlation refers to the corresponding relationship between physical parameters and biological responses; data timeliness is used to represent the effective usage period of data; data reliability represents the accuracy and confidence level of data.

[0095] The air quality detection system performs data integration after completing data acquisition. Specifically, the system first aligns the physical sensor data and plant monitoring data in time series; then analyzes the correlation between the two types of data and establishes a parameter mapping relationship; next, performs data fusion to convert discrete data points into continuous state curves; then conducts a quality assessment on the fused data to determine the reliability level of the data; finally, generates a comprehensive detection dataset containing multi-dimensional information.

[0096] In some embodiments, the data integration process can be implemented in various ways: Optionally, the air quality detection system adopts a data fusion algorithm to optimally combine data from different sources through methods such as Kalman filtering, improving the accuracy and reliability of the data; Optionally, the air quality detection system is based on time series analysis methods, and realizes intelligent integration and anomaly identification of data by establishing a dynamic correlation model of multi-source data. It can be understood that other data processing methods can also be used to achieve comprehensive analysis of the detection data, which is not limited here.

[0097] In some embodiments, the air quality detection system extracts the apparent characteristics of the target plant in the growth monitoring image; and generates pollution warning data when the apparent characteristics meet the air pollution conditions.

[0098] Among them, the apparent characteristics refer to the observable characteristics of the external morphology of the plant; the air pollution condition refers to the pollutant concentration threshold that causes abnormal plant morphology; the pollution warning data is used to represent the pollution warning information issued based on biological indicators; the image feature parameters refer to the numerical indicators that quantify the morphological changes of the plant; the biological response pattern refers to the typical response characteristics of the plant to specific pollutants.

[0099] The air quality detection system evaluates the plant status at fixed time intervals. Specifically, the system first preprocesses and enhances the collected plant images; then extracts the morphological characteristics of the plant, including parameters such as leaf area, leaf color, and stem angle; then compares and analyzes the current characteristics with the standard morphological baseline; then evaluates whether the characteristic changes reach the pollution response threshold; finally, generates warning data containing the pollution type and degree when anomalies are found, and initiates the corresponding verification process.

[0100] In some embodiments, plant monitoring and warning can be achieved in various ways: Optionally, the air quality detection system constructs a plant health status evaluation model based on a deep convolutional neural network, and quickly adapts to the feature extraction requirements of different plant varieties through transfer learning methods to achieve accurate identification of plant anomalies; Optionally, the air quality detection system adopts a spatio-temporal sequence analysis method, and evaluates the cumulative effect of pollution exposure by establishing a plant growth dynamic model to capture the time characteristics of morphological changes. It can be understood that other biological monitoring methods can also be used to achieve pollution warning based on plants, which is not limited here.

[0101] S207. When pollution warning data appears in the detection data set, send a data sharing request to the surrounding buildings within the preset communication range, and receive the verification data set returned by the surrounding buildings.

[0102] Referring to step S102, the air quality detection system will obtain the verification data set when pollution warning data appears.

[0103] S208. Calculate the pollution confidence level of the pollution warning data and the pollution correlation coefficient of the pollutant concentration between buildings based on the detection data set, the verification data set, and the environmental meteorological data.

[0104] Referring to step S103, the air quality detection system calculates the pollution confidence level and the pollution correlation coefficient.

[0105] It should be noted that the impact assessment of environmental meteorological data adopts the multivariate time series analysis method. The system first constructs a state vector including meteorological elements such as wind speed, wind direction, temperature, and humidity; then describes the dynamic correlation between meteorological elements through a vector autoregressive model; then uses the Granger causality test to analyze the impact degree of meteorological conditions on pollutant diffusion; finally, predicts the pollutant diffusion trend under specific meteorological conditions through a state space model. The model pays special attention to the lag effect and non-linear interaction of meteorological elements, and processes the impact characteristics of multiple time scales through methods such as wavelet transform. For example, when it is observed that the pollutant concentration of the upwind building increases, the system combines wind field data to predict the transmission path and arrival time of pollutants, providing support for prevention and control decisions.

[0106] In some embodiments, the air quality detection system constructs a heat map for modeling and calculation, that is, the air quality detection system constructs a heat map of the pollutant concentration distribution of the target building based on the detection data set; constructs a heat map of the pollutant diffusion distribution of the surrounding buildings according to the verification data set; obtains the environmental meteorological data including wind direction, wind speed, temperature, and humidity within the target time period; calculates the impact path of the environmental meteorological data on pollutant diffusion based on the pollutant concentration distribution heat map, the pollutant diffusion distribution heat map, and the environmental meteorological data, and generates the pollution confidence level; when the pollution confidence level is higher than the preset confidence threshold, calculates the pollution correlation coefficient of the pollutant concentration between buildings according to the impact path.

[0107] Among them, the heat map represents a visualization model of the spatial distribution of pollutant concentration; the pollutant diffusion distribution refers to the migration law of pollutants in space; the impact path is used to represent the action mode of environmental factors on pollutant movement; the confidence threshold represents the credibility standard for pollution determination; the correlation coefficient refers to the correlation intensity of the pollution degree between buildings.

[0108] The air quality detection system conducts comprehensive modeling and analysis after obtaining multi-source data. Specifically, the system first performs spatial interpolation on the detection data and the verification data to generate a continuous concentration distribution field; then constructs a pollutant transport model in combination with the environmental meteorological data; then calculates the diffusion trajectory of pollutants through numerical simulation methods; then determines the pollution confidence level based on the consistency evaluation of multi-source data; finally, establishes the pollution correlation relationship between buildings through diffusion path analysis when the confidence level meets the requirements.

[0109] In some embodiments, pollution diffusion modeling can be achieved in various ways: Optionally, the air quality detection system uses the computational fluid dynamics method to simulate the diffusion process of pollutants in a complex building environment by solving the Navier-Stokes equations and evaluate the influence degree of environmental factors; Optionally, the air quality detection system is based on the Gaussian diffusion model and constructs a pollutant transport model adapted to the urban environment by introducing terrain and meteorological correction factors. It can be understood that other numerical simulation methods can also be used to accurately describe the pollution diffusion characteristics, which are not limited here.

[0110] S209. Determine the pollution source type of the pollution warning data according to the pollution confidence level and the pollution correlation coefficient.

[0111] Referring to step S104, the air quality detection system will determine the pollution source type.

[0112] It should be noted that the application of the pattern recognition technology of the pollution source type in pollution source determination is based on a multi-level feature extraction and classification recognition framework. First, the system performs time-frequency domain decomposition on the pollution data to extract key feature parameters including the concentration change rate, periodic characteristics, spatial distribution gradient, etc.; then the principal component analysis method is used to reduce the dimension of the feature space and retain the most discriminative feature combination; then a deep learning network is used to construct a pollution source classification model. This model learns the feature expressions of different pollution source types through multi-layer non-linear transformations. The input layer of the model receives the preprocessed feature vectors, the hidden layer captures the complex associations between features through activation functions, and the output layer gives the probability distribution of the pollution source type.

[0113] In practical applications, the model continuously optimizes the network parameters through the backpropagation algorithm to improve the classification accuracy. For example, when the abnormal formaldehyde concentration in a certain area is detected, the system will analyze the characteristics of its concentration change curve: if it shows the characteristics of exponential decay after a stepwise increase and has obvious spatial locality, the model will determine it as an indoor source pollution caused by the release of decoration materials; if the concentration change shows a progressive diffusion characteristic along the air flow direction, it is more likely to be determined as an external pollution source. The application of the pattern recognition technology of the pollution source type in pollution source determination is based on a multi-level feature extraction and classification recognition framework.

[0114] First, the system performs time-frequency domain decomposition on the pollution data to extract key feature parameters including the concentration change rate, periodic characteristics, spatial distribution gradient, etc.; then the principal component analysis method is used to reduce the dimension of the feature space and retain the most discriminative feature combination; then a deep learning network is used to construct a pollution source classification model. This model learns the feature expressions of different pollution source types through multi-layer non-linear transformations. The input layer of the model receives the preprocessed feature vectors, the hidden layer captures the complex associations between features through activation functions, and the output layer gives the probability distribution of the pollution source type.

[0115] In practical applications, the model continuously optimizes the network parameters through the backpropagation algorithm to improve the classification accuracy. For example, when the formaldehyde concentration in a certain area is detected to be abnormal, the system will analyze the characteristics of its concentration change curve: if it shows the characteristics of exponential decay after a stepwise increase and has obvious spatial locality, the model will determine it as an indoor source pollution caused by the release of decoration materials; if the concentration change shows a progressive diffusion characteristic along the air flow direction, it is more likely to be determined as an external pollution source.

[0116] S210. Generate an air pollution alert and a pollution prevention and control plan based on the pollution warning data and the type of pollution source.

[0117] Referring to step S105, the air quality detection system will generate an air pollution alert and a pollution prevention and control plan.

[0118] It should be noted that the classification of the emergency response level adopts a multi-index decision-making method based on fuzzy comprehensive evaluation. The system first constructs a decision matrix including multiple evaluation indexes such as the multiple of pollutant concentration exceeding the standard, the influence range, the duration, and the health risk; then determines the weight coefficients of each index through the analytic hierarchy process to establish a weighted scoring model; then standardizes each index and substitutes it into the fuzzy membership function to calculate the comprehensive evaluation score; finally, determines the corresponding response level according to the score interval. This evaluation system processes the uncertainty and interactive influence between indexes through fuzzy mathematics methods, realizing the scientific classification of the response level. For example, when the concentration of a certain harmful gas exceeds the standard value by 5 times, and the influence range covers the entire office floor and the duration exceeds 30 minutes, the system will calculate a relatively high comprehensive risk score, trigger a higher-level emergency response, and initiate a series of mandatory prevention and control measures including personnel evacuation and emergency ventilation. The dynamic adjustment of the response level will also consider the pollution development trend and control effect to ensure the timeliness and effectiveness of the prevention and control measures.

[0119] In some embodiments, the air quality detection system will collect the pollutant concentration change data at each detection point to generate an execution score for the prevention and control measures; and adjust the pollution prevention and control plan according to the pollutant concentration change data and the execution score.

[0120] Among them, the execution score represents the evaluation index of the implementation effect of the prevention and control measures; the pollutant concentration change data refers to the monitoring results reflecting the prevention and control effect; the prevention and control measures refer to the specific actions used to control and eliminate pollution; the adjustment strategy is used to represent the modification method for optimizing the prevention and control plan; the implementation effect refers to the degree of the role of the prevention and control measures in pollution control.

[0121] The air quality detection system continuously conducts effectiveness evaluation during the implementation of the prevention and control plan. Specifically, the system first establishes a pollutant concentration monitoring network covering multiple time scales; then calculates the change trend of pollutant concentration before and after the implementation of prevention and control measures; next, evaluates the effectiveness of the measures based on the change trend and control objectives; then scores the prevention and control measures based on the evaluation results; and finally, dynamically adjusts the prevention and control strategy according to the execution score to optimize resource allocation and implementation plan.

[0122] In some embodiments, the prevention and control effectiveness evaluation can be achieved in various ways: Optionally, the air quality detection system adopts the reinforcement learning method, and through establishing a state-action-reward model, learns the optimal prevention and control strategy to realize the adaptive optimization of the prevention and control plan; Optionally, the air quality detection system is based on the multi-objective decision-making theory, and through establishing a comprehensive evaluation system considering control effect and resource consumption, dynamically adjusts the implementation plan of prevention and control measures. It can be understood that other optimization algorithms can also be used to realize the dynamic adjustment of the prevention and control plan, which is not limited here.

[0123] In the embodiments of the present application, due to the adoption of technologies such as the construction of an air circulation network based on building structure characteristics, multi-dimensional data collection and verification, and intelligent pollution source identification, etc., the scientific layout of detection points, the accurate verification of pollution data, and the generation of prevention and control plans can be realized, effectively solving the problems of many detection blind spots, high false alarm rate, and difficult pollution source tracing in traditional methods, and thus realizing the high precision and high reliability of building indoor air quality detection. This solution establishes a triple verification mechanism of multi-detection point data collection, surrounding building data verification, and environmental meteorological data analysis, combined with the long-term cumulative effect monitoring of biological indicators, which can not only accurately distinguish the three types of pollution-free, endogenous pollution, and exogenous pollution, but also formulate targeted prevention and control plans based on the characteristics of pollution sources, significantly improving the scientificity and effectiveness of air quality management. The adaptive optimization mechanism of the system ensures the reasonable allocation of detection resources and the continuous improvement of prevention and control measures, realizing collaborative prevention and control at the building complex scale.

[0124] The air quality detection system in the embodiments of the present invention application will be described from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the air quality detection system in the embodiments of the present application.

[0125] It should be noted that Figure 3 The structure of the air quality detection system shown is only an example, and should not bring any limitations to the functions and usage scopes of the embodiments of the present invention.

[0126] As Figure 3As shown in the figure, the air quality detection system includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) 302 or the program loaded from the storage section 308 into the Random Access Memory (RAM) 303, such as executing the methods described in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 304.

[0127] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a Liquid Crystal Display (LCD), an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0128] Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the Central Processing Unit (CPU) 301, various functions defined in the present invention are executed.

[0129] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings.

[0131] Specifically, the air quality detection system of this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, it implements the building indoor air quality detection method provided in the above embodiment.

[0132] On the other hand, the present invention also provides a computer-readable storage medium. This storage medium can be included in the air quality detection system described in the above embodiment; or it can exist separately and not be assembled into the air quality detection system. The above storage medium carries one or more computer programs. When the above one or more computer programs are executed by a processor of the air quality detection system, the air quality detection system is enabled to implement the building indoor air quality detection method provided in the above embodiment.

[0133] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present application.

[0134] As used in the foregoing embodiments, depending on the context, the term "when" may be interpreted to mean "if", "after", "in response to determining", or "in response to detecting". Similarly, depending on the context, the phrase "when determining" or "if (the stated condition or event) is detected" may be interpreted to mean "if determined", "in response to determining", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by a computer program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the foregoing method embodiments. The foregoing storage media include various media that can store program codes, such as ROM, random access memory (RAM), magnetic disks, or optical discs.

Claims

1. A method for detecting indoor air quality in a building, characterized in that: Applied to an air quality detection system, the method comprises: Obtain air quality test data from multiple test points inside the target building and generate a test data set; When pollution warning data appears in the detection data set, a data sharing request is sent to surrounding buildings within a preset communication range, and a verification data set returned by the surrounding buildings is received; Calculating the pollution confidence of the pollution warning data and the pollution correlation coefficient of the pollutant concentration between buildings according to the detection data set, the verification data set and the environmental meteorological data; Determining the pollution source type of the pollution warning data according to the pollution confidence and the pollution correlation coefficient; the pollution source type includes no pollution, endogenous pollution and exogenous pollution; Based on the pollution warning data and the pollution source type, air pollution prompts and pollution prevention and control plans are generated.

2. The method according to claim 1, characterized in that: The step of obtaining air quality detection data of multiple detection points inside the target building and generating a detection data set specifically includes: Obtain air quality test data from multiple test points inside the target building; Acquiring growth monitoring images of a plurality of target plants in the target building; the target plants are biological indicators used for air quality detection; A detection data set is generated according to the air quality detection data and the growth monitoring image.

3. The method according to claim 2, characterized in that After the step of generating a detection data set according to the air quality detection data and the growth monitoring image, the method further comprises: Extracting the apparent features of the target plant in the growth monitoring image; When the apparent characteristics meet air pollution conditions, pollution warning data is generated.

4. The method according to claim 1, characterized in that: The step of calculating the pollution confidence of the pollution warning data and the pollution correlation coefficient of the pollutant concentration between buildings according to the detection data set, the verification data set and the environmental meteorological data specifically includes: Based on the detection data set, construct a pollutant concentration distribution thermodynamic map of the target building; Constructing a pollutant diffusion distribution heat map of the surrounding buildings according to the verification data set; Obtain environmental meteorological data including wind direction, wind speed, temperature and humidity within the target time period; Based on the pollutant concentration distribution thermodynamic map, the pollutant diffusion distribution thermodynamic map and the environmental meteorological data, calculating the impact path of the environmental meteorological data on pollutant diffusion, and generating pollution confidence; When the pollution confidence is higher than a preset confidence threshold, a pollution correlation coefficient of pollutant concentrations between buildings is calculated according to the impact path.

5. The method according to claim 1, characterized in that Before the step of acquiring air quality detection data of multiple detection points inside the target building and generating a detection data set, the method further includes: Construct an air circulation network based on the structural characteristics, usage functions and surrounding environment of the target building; Dividing the target building into a plurality of detection areas based on the air circulation network, and determining a plurality of preset detection points in each of the detection areas; According to the building orientation, the floor height and the population density of the detection area, the data collection frequency and the pollution alarm threshold are bound to the preset detection points.

6. The method according to claim 5, characterized in that The step of binding the data collection frequency and the pollution alarm threshold to the preset detection point according to the building orientation, the floor height and the population density of the detection area specifically includes: Calculating the natural ventilation coefficient of the detection area based on the building orientation and the floor height of the detection area; Determine the artificial pollution coefficient of the density of people and the change of air quality in the detection area according to the historical detection data; Based on the natural ventilation coefficient and the artificial pollution coefficient, binding a detection priority for each preset detection point in the detection area; According to the detection priority, the data collection frequency and pollution alarm threshold of the preset detection point are adjusted.

7. The method according to claim 1, characterized in that After the step of generating an air pollution reminder and a pollution prevention and control plan according to the pollution warning data and the pollution source type, the method further includes: Collect pollutant concentration change data at each detection point and generate execution scores for prevention and control measures; The pollution prevention and control plan is adjusted according to the pollutant concentration change data and the execution score.

8. An air quality detection system, characterized in that: The air quality detection system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the air quality detection system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the air quality detection system, the air quality detection system is caused to execute the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on an air quality detection system, the air quality detection system is enabled to perform the method according to any one of claims 1 to 7.

Images