An indoor environment adaptive adjustment system based on the Internet of Things

Abstract

The present invention provides an indoor environment adaptive adjustment system based on the Internet of Things, which relates to the field of Internet of Things technology and includes: a data acquisition module for dividing the indoor space into three functional areas, and deploying a multi-parameter sensor group in each functional area through the Internet of Things network to collect raw environmental data in real time, including temperature, relative humidity, and air pollutant concentration data; a spatial heterogeneity analysis module for calculating the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area as the regional range. When the regional range of any parameter exceeds a set threshold, a spatial heterogeneity correction factor K is generated, where the K value is proportional to the maximum regional range. The present invention realizes adaptive adjustment of the indoor environment through precise perception of zoning, dynamic correction, multi-parameter fusion evaluation, equipment collaborative control, and continuous optimization, effectively improving comfort, ensuring air quality, and reducing energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an indoor environment self-adaptive adjustment system based on the Internet of Things. Background Art

[0002] Traditional indoor environmental control technologies mostly use single-point monitoring and fixed-mode adjustment, which can usually only obtain environmental parameters (such as temperature and humidity) at a single location, and have limited ability to respond to the environmental heterogeneity of indoor spaces.

[0003] For example, indoor areas like corners, door and window openings can experience localized environmental parameter anomalies due to air stagnation or pollutant infiltration. However, traditional single-point monitoring methods risk missing detection, resulting in some pollution scenarios not being identified in a timely manner. When multiple environmental issues arise, such as poor thermal comfort in areas where people are active and excessive concentrations of pollutants in areas where they accumulate, traditional systems struggle to achieve differentiated adjustments, resulting in wasted energy and insufficient comfort. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an indoor environment adaptive adjustment system based on the Internet of Things, breaking through the limitations of traditional single-point monitoring and realizing refined perception of the heterogeneity of the indoor environment.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] In a first aspect, an indoor environment adaptive adjustment system based on the Internet of Things comprises:

[0007] The data acquisition module is used to divide the indoor space into three functional areas and deploy a multi-parameter sensor group in each functional area through the IoT network to collect real-time raw environmental data, including temperature, relative humidity, and air pollutant concentration data;

[0008] The spatial heterogeneity analysis module is used to calculate the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area as the regional range. When the regional range of any parameter exceeds the set threshold, a spatial heterogeneity correction factor K is generated, where the K value is proportional to the maximum regional range.

[0009] The quality evaluation module is used to input the original environmental data and the spatial heterogeneity correction factor K into the preset fuzzy comprehensive evaluation model through the Internet of Things platform, calculate the initial indoor environmental quality index M, and perform degradation weighting processing on the initial indoor environmental quality index M using the spatial heterogeneity correction factor K to generate a corrected comprehensive quality evaluation index M';

[0010] A control instruction module is used to independently generate control instructions for three types of equipment through the Internet of Things control center based on the revised comprehensive quality evaluation index M';

[0011] The closed-loop feedback module is used to re-monitor the data of each functional area through the Internet of Things network after executing the equipment control instructions. If the parameter range of the same functional area is not reduced to within the threshold, the degradation weighted intensity is adjusted and the revised comprehensive quality evaluation index M' is regenerated. If the range of all areas is lower than the threshold, the revised comprehensive quality evaluation index M' is continuously monitored and the fluctuation exceeds the preset warning threshold.

[0012] Furthermore, the indoor space is divided into three functional areas, and a multi-parameter sensor group is deployed in each functional area through the Internet of Things network to collect real-time raw environmental data, including temperature, relative humidity and air pollutant concentration data, including:

[0013] Functional areas are divided according to the indoor physical layout, including core areas for human activity, areas with high pollution risk, and areas with airflow obstruction. The core areas for human activity, areas with high pollution risk, and areas with airflow obstruction include:

[0014] The core area for personnel activities is the entire space from the ground to a height of 1.8 meters;

[0015] The high-risk pollution area is the three-dimensional passage within 0.5 meters inside and outside all door and window openings;

[0016] The airflow obstruction area is the L-shaped space in the indoor concave corner with a depth greater than or equal to 0.5 meters;

[0017] Sensor groups are deployed in various functional areas through the Internet of Things network to collect raw environmental data including temperature, relative humidity and air pollutant concentrations in real time.

[0018] Furthermore, the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area is calculated as the regional range. When the regional range of any parameter exceeds the set threshold, a spatial heterogeneity correction factor K is generated, where the K value is proportional to the maximum regional range, including:

[0019] The real-time collected temperature, relative humidity and air pollutant concentration data are classified and stored according to functional areas into core area data packets, high-incidence area data packets and congestion area data packets;

[0020] Directional calculations are performed on each data packet, where the core area data packet calculates the extreme difference in carbon gas pollutant concentration; the high-incidence area data packet calculates the extreme difference in suspended particulate pollutant concentration; and the blocked area data packet calculates the extreme difference in volatile organic pollutant concentration.

[0021] When any range exceeds the corresponding threshold, the maximum value among all ranges is selected to generate a spatial heterogeneity correction factor K that is proportional to the maximum value.

[0022] Furthermore, directional calculations are performed on each data packet, where the core area data packet calculates the extreme difference in carbon gas pollutant concentration; the high-incidence area data packet calculates the extreme difference in suspended particulate pollutant concentration; and the blocked area data packet calculates the extreme difference in volatile organic pollutant concentration, including:

[0023] Extract the carbon-containing gas pollutant concentration data set from the core area data package, calculate the difference between the maximum and minimum values, and obtain the carbon-containing gas pollutant concentration range; extract the suspended particle pollutant concentration data set from the high-incidence area data package, calculate the difference between the maximum and minimum values, and obtain the suspended particle pollutant concentration range; extract the volatile organic pollutant concentration data set from the blocked area data package, calculate the difference between the maximum and minimum values, and obtain the volatile organic pollutant concentration range;

[0024] When the range exceeds the corresponding threshold, the maximum value of all ranges is output. The corresponding threshold includes:

[0025] The extreme difference of carbon-containing gas in the core area is greater than 300 ppm, the extreme difference of suspended particles in the high-incidence area is greater than 20 μg / m³, and the extreme difference of volatile organic compounds in the blocked area is greater than 0.05 mg / m³.

[0026] Furthermore, the original environmental data and the spatial heterogeneity correction factor K are input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environmental quality index M. The initial indoor environmental quality index M is then subjected to degradation weighting processing using the spatial heterogeneity correction factor K to generate a revised comprehensive quality evaluation index M', which includes:

[0027] The partition data package and the spatial heterogeneity correction factor K are input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environment quality index M;

[0028] Based on the value of the spatial heterogeneity correction factor K, the initial indoor environmental quality index M is dynamically degraded and weighted. When the K value increases, the degradation weighted intensity is adjusted proportionally to generate a dynamic degradation weighted value. The degradation weighted intensity is associated with the regional type, that is, the weighted intensity of the airflow obstruction area is greater than that of the high-risk pollution area and the core area of ​​human activity;

[0029] The dynamic degradation weighted value is superimposed on the initial indoor environmental quality index M to generate a comprehensive quality evaluation index M' after degradation weighting.

[0030] The partition data package and the spatial heterogeneity correction factor K are further input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environment quality index M, including:

[0031] Bind the core area data packets, high-incidence area data packets and congestion area data packets with the spatial heterogeneity correction factor K to form a fused data unit;

[0032] Perform degradation direction unification processing on the environmental parameters in the fused data unit. After the conversion, the increase in the value of all parameters indicates that the environmental quality is deteriorating, and the parameter data after direction unification processing is obtained;

[0033] Based on the parameter data after direction unification, the membership weighted operation is performed in combination with the regional type weight matrix to generate the initial indoor environment quality index M.

[0034] Furthermore, based on the revised comprehensive quality evaluation index M', the IoT control center independently generates three types of device control instructions, including:

[0035] According to the degradation direction of the comprehensive quality evaluation index M' after degradation weighting processing, three types of independent control instructions are generated by the Internet of Things control center. The three types of device control instructions include:

[0036] If M' indicates that the thermal comfort of the core area of ​​personnel activities has deteriorated, then the air conditioning temperature adjustment instruction bound to this area is generated;

[0037] If M' indicates that the concentration of suspended particulate matter in a high-pollution risk area exceeds the standard, a ventilation instruction for the fresh air system associated with that area is generated;

[0038] If M' indicates that the concentration of volatile organic compounds in the airflow obstruction area exceeds the standard, a disinfection instruction for the purification equipment bound to the area is generated;

[0039] When multiple areas deteriorate at the same time, instructions are triggered in sequence: purification instructions for airflow-blocked areas, ventilation instructions for areas with high pollution risks, and air-conditioning instructions for core areas where people move.

[0040] Furthermore, after executing the equipment control instruction, the data of each functional area is re-monitored through the Internet of Things network. If the parameter range of the same functional area is not reduced to within the threshold, the degradation weighted intensity is adjusted and the revised comprehensive quality evaluation index M' is regenerated. If the range of all areas is lower than the threshold, the revised comprehensive quality evaluation index M' is continuously monitored and the fluctuation exceeds the preset warning threshold, including:

[0041] Re-collect data from each functional area through the IoT network, generate new partition data packets and calculate parameter ranges;

[0042] If the parameter range of the same functional area does not fall within the threshold, the proportional adjustment intensity in the degradation weighted processing is adjusted, and the corrected comprehensive quality evaluation index M' is regenerated to trigger a new round of equipment control instructions; if the range of all areas is lower than the threshold, the fluctuation of the correction index M' is continuously monitored. When the fluctuation amplitude of M' exceeds the preset warning threshold, the environmental adaptive adjustment process is automatically restarted.

[0043] In a second aspect, a computing device includes:

[0044] one or more processors;

[0045] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the system.

[0046] According to a third aspect, a computer-readable storage medium stores a program, which implements the system when executed by a processor.

[0047] The above solution of the present invention includes at least the following beneficial effects:

[0048] The indoor area is divided into core areas for human activity, areas with high pollution risk, and areas with airflow obstruction. Sensors are deployed in a targeted manner to address issues such as missed corner pollution control and difficulty in timely handling of pollutant intrusion through doors and windows under the traditional uniform monitoring mode, thereby accurately capturing the environmental heterogeneity of different areas. A spatial heterogeneity correction factor is generated through regional range calculation, and the environmental quality index is dynamically weighted for degradation using a fuzzy comprehensive evaluation model to make the evaluation results more consistent with the actual spatial pollution conditions and avoid evaluation bias caused by uneven distribution of environmental parameters. Based on the corrected quality index, device instructions are independently triggered according to the priority of "purification of airflow obstruction areas → ventilation of high pollution risk areas → thermal comfort adjustment of core areas for human activity", achieving non-bundled operation. While ensuring environmental quality, it avoids energy waste caused by fully operating all equipment in the house and improves control efficiency.

[0049] After implementing regulation, regional parameter extremes are continuously monitored. If the threshold is not reached, the weighted intensity of degradation is increased and readjusted, forming a closed-loop mechanism of "monitoring-evaluation-control-re-monitoring" to ensure the sustainability and dynamic adaptability of environmental regulation. Focusing on core pollution factors in different regions (such as carbon-containing gases in core areas, particulate matter in high-incidence areas, and volatile organic compounds in obstructed areas), combined with thermal and humidity environmental regulation, this precisely improves air quality while also addressing human thermal comfort needs, creating a healthier and more livable indoor environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of an indoor environment adaptive adjustment system based on the Internet of Things provided by an embodiment of the present invention.

[0051] Figure 2 This is a flow chart of an embodiment of the present invention, which provides a method for inputting a partition data packet and a spatial heterogeneity correction factor K into a preset fuzzy comprehensive evaluation model through an Internet of Things platform to calculate an initial indoor environment quality index M. DETAILED DESCRIPTION

[0052] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0053] like Figure 1 As shown, an embodiment of the present invention provides an indoor environment adaptive adjustment system based on the Internet of Things, comprising:

[0054] The data acquisition module is used to divide the indoor space into three functional areas and deploy a multi-parameter sensor group in each functional area through the IoT network to collect real-time raw environmental data, including temperature, relative humidity, and air pollutant concentration data;

[0055] The spatial heterogeneity analysis module is used to calculate the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area as the regional range. When the regional range of any parameter exceeds the set threshold, a spatial heterogeneity correction factor K is generated, where the K value is proportional to the maximum regional range.

[0056] The quality evaluation module is used to input the original environmental data and the spatial heterogeneity correction factor K into the preset fuzzy comprehensive evaluation model through the Internet of Things platform, calculate the initial indoor environmental quality index M, and perform degradation weighting processing on the initial indoor environmental quality index M using the spatial heterogeneity correction factor K to generate a corrected comprehensive quality evaluation index M';

[0057] A control instruction module is used to independently generate control instructions for three types of equipment through the Internet of Things control center based on the revised comprehensive quality evaluation index M';

[0058] The closed-loop feedback module is used to re-monitor the data of each functional area through the Internet of Things network after executing the equipment control instructions. If the parameter range of the same functional area is not reduced to within the threshold, the degradation weighted intensity is adjusted and the revised comprehensive quality evaluation index M' is regenerated. If the range of all areas is lower than the threshold, the revised comprehensive quality evaluation index M' is continuously monitored and the fluctuation exceeds the preset warning threshold.

[0059] In this embodiment of the present invention, the indoor environment is divided into a core area for human activity, a high-risk area for pollution, and an airflow obstruction area. Sensors are then deployed in targeted locations to capture real-time differences in temperature, humidity, and pollutant concentrations in different areas. For example, the core area focuses on monitoring CO2 concentrations at human breathing height, the high-risk area tracks particulate matter intrusion through door and window openings, and the obstruction area captures VOC accumulation in wall corners. This solves the problem of spatial heterogeneity missed detection under traditional uniform monitoring modes. By calculating the regional range to generate a spatial heterogeneity correction factor K, and applying a degradation weight to the initial indoor environmental quality index M of the fuzzy comprehensive evaluation model, the evaluation results are more closely aligned with the actual pollution distribution.

[0060] According to the corrected quality index M', the device instructions are independently triggered according to the priority of "purification of blocked areas → ventilation of high-incidence areas → temperature control in core areas" to achieve non-bundled operation. For example, the fresh air system is only started when the particulate matter in the high-incidence area exceeds the standard, avoiding energy waste caused by fully opening all the equipment in the house, and improving the control efficiency while ensuring environmental quality. After the execution of the control, the regional parameters are continuously monitored. If the threshold is not reached, the weighted intensity of the degradation is enhanced and readjusted to form a closed loop of "monitoring-evaluation-control-feedback". Focus on the core pollution factors in different areas (such as the hot and humid environment in the core area, particulate matter in the high-incidence area, and chemical pollution in the blocked area) and coordinate the adjustment to accurately improve the air quality while taking into account the thermal comfort needs of the human body.

[0061] In a preferred embodiment of the present invention, the indoor space is divided into three functional areas, and a multi-parameter sensor group is deployed in each functional area through the Internet of Things network to collect real-time raw environmental data, including temperature, relative humidity, and air pollutant concentration data, which may include:

[0062] Functional areas are divided according to the indoor physical layout, including core areas for human activity, areas with high pollution risk, and areas with airflow obstruction. The core areas for human activity, areas with high pollution risk, and areas with airflow obstruction include:

[0063] The core area for personnel activities is the entire space from the ground to a height of 1.8 meters;

[0064] The high-risk pollution area is the three-dimensional passage within 0.5 meters inside and outside all door and window openings;

[0065] The airflow obstruction area is the L-shaped space in the indoor concave corner with a depth greater than or equal to 0.5 meters;

[0066] Sensor groups are deployed in various functional areas through the Internet of Things network to collect raw environmental data including temperature, relative humidity and air pollutant concentrations in real time.

[0067] In this embodiment of the present invention, a three-dimensional space is formed, extending vertically upward to a height of 1.8 meters, using the indoor floor as the reference plane. This area covers the respiratory zone during standing and sitting, as well as major activity trajectories (such as daily walking and working). Based on the functional layout of the room, high-frequency activity areas (such as the living room sofa area, bedroom bed area, and office workstation area) are identified, ensuring that the core area completely covers these areas horizontally, without missing potential blind spots such as corners and gaps between furniture.

[0068] Delineate three-dimensional channels for areas with high pollution risk:

[0069] Using interior architectural drawings or on-site surveys, mark the location and dimensions (including height and width) of all doors and windows. Using the boundaries of the door and window openings as a baseline, extend 0.5 meters in both the indoor and outdoor directions to create a three-dimensional channel with a thickness of 1 meter. For example, for a window 2 meters high and 1.5 meters wide, the high-risk areas are: 0.5 meters inside the opening, 0.5 meters outside, and the 2m x 1.5m x 1m three-dimensional area formed by the opening itself, covering the main entry pathways for outdoor pollutants.

[0070] Identify airflow obstruction areas in an L-shaped space:

[0071] All indoor corners are traversed and geometric measurements are used to determine whether they are "recessed corners" (i.e., L-shaped structures with angles less than 180°). Starting from the intersection of the corners, the distance along both walls is measured to the edge of each wall. If the depth in at least one direction is ≥ 0.5 meters (e.g., the corner is concave more than 0.5 meters), the airflow is determined to be blocked. For example, a 0.6-meter-deep recessed corner would have a blockage area within the L-shaped space that is ≥ 0.5 meters deep, located in a corner with less furniture or a recessed area in the building structure.

[0072] Deployment and data collection of IoT sensor groups:

[0073] Within a 1.8-meter height range, sensor nodes are deployed with horizontal spacing no greater than 3 meters. Each node integrates sensors for temperature, humidity, and carbon-containing gas (e.g., CO2) concentration, ensuring coverage at human breathing height. Within the three-dimensional corridors surrounding door and window openings, suspended particulate matter (e.g., PM2.5) sensors are installed 0.25 meters inside and 0.25 meters outside the openings, forming a two-way monitoring barrier. A volatile organic compound (VOC) sensor is deployed at the deepest point of the L-shaped space (0.5 meters from the corner intersection) to mitigate pollutant accumulation caused by poor airflow. All sensors transmit data in real time via the IoT network, with a sampling interval of 1 minute to capture transient changes in environmental parameters (e.g., the influx of particulate matter when a door is opened and fluctuations in CO2 concentration caused by human activity).

[0074] By vertically dividing the "core activity zone," the system specifically captures the thermal and humid environment and carbon-containing gas concentrations in the human breathing zone, avoiding the "breathing zone data distortion" problem caused by traditional uniform whole-house monitoring. The three-dimensional channel design for "high-pollution risk areas" tracks the intrusion paths of pollutants through door and window openings in real time, more efficiently identifying the impact of outdoor pollution on indoor spaces than traditional single-point monitoring. L-shaped spatial identification for "airflow obstruction zones" eliminates blind spots in monitoring pollution accumulation in hidden areas such as corners and furniture gaps, filling the gap in traditional solutions where "poor airflow areas" are missed. Different types of sensors are deployed according to regional functions, avoiding sensor redundancy caused by uniform deployment throughout the house (for example, VOC sensors do not need to be densely deployed in core areas, and frequent temperature monitoring is not required in obstructed areas), reducing hardware costs and data processing load. Real-time, high-frequency data collection and IoT transmission ensure that dynamic changes in environmental parameters (such as sudden increases in particulate matter concentration and slow release of VOCs) are captured promptly.

[0075] In a preferred embodiment of the present invention, the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area is calculated as the regional range. When the regional range of any type of parameter exceeds a set threshold, a spatial heterogeneity correction factor K is generated, where the value of K is proportional to the maximum regional range and may include:

[0076] The real-time collected temperature, relative humidity and air pollutant concentration data are classified and stored according to functional areas into core area data packets, high-incidence area data packets and congestion area data packets;

[0077] Directional calculations are performed on each data packet. The core area data packet calculates the extreme difference in carbon gas pollutant concentration; the high-incidence area data packet calculates the extreme difference in suspended particulate pollutant concentration; and the blocked area data packet calculates the extreme difference in volatile organic pollutant concentration. Specifically, the calculations include:

[0078] Extract the carbon-containing gas pollutant concentration data set from the core area data package, calculate the difference between the maximum and minimum values, and obtain the carbon-containing gas pollutant concentration range; extract the suspended particle pollutant concentration data set from the high-incidence area data package, calculate the difference between the maximum and minimum values, and obtain the suspended particle pollutant concentration range; extract the volatile organic pollutant concentration data set from the blocked area data package, calculate the difference between the maximum and minimum values, and obtain the volatile organic pollutant concentration range;

[0079] When the range exceeds the corresponding threshold, the maximum value of all ranges is output. The corresponding threshold includes:

[0080] The extreme difference of carbon-containing gas in the core area is greater than 300ppm, the extreme difference of suspended particles in the high-incidence area is greater than 20μg / m³, and the extreme difference of volatile organic compounds in the blocked area is greater than 0.05mg / m³;

[0081] When any range exceeds the corresponding threshold, the maximum value among all ranges is selected to generate a spatial heterogeneity correction factor K that is proportional to the maximum value.

[0082] In this embodiment of the present invention, IoT sensors collect temperature, humidity, and pollutant concentration data on a minute-by-minute basis. The system automatically categorizes this data into corresponding functional areas based on the sensor's location. For example, data from sensors deployed between the ground and 1.8 meters above ground level is grouped into a "core area data package," data from sensors within 0.5 meters of door and window openings is grouped into a "high-incidence area data package," and data from sensors in L-shaped spaces within recessed corners is grouped into a "blocked area data package." Each data package stores data in a time series, forming a three-dimensional dataset. For example, a core area data package contains real-time sampled values ​​for the concentration of all carbon-containing gases (such as CO2) within that area, along with sampling timestamps and sensor location identifiers.

[0083] Calculation of the extreme difference of carbon-containing gas in the core area:

[0084] Filter the concentration data for carbon-containing gas pollutants (such as CO2) from the core area data packets to form an independent dataset. For example, extract the CO2 concentration values ​​collected by all sensors in the area over the past 10 minutes. Suppose the data points are [1200ppm, 1150ppm, 1300ppm, 1250ppm]. Traverse the dataset and find the maximum and minimum values. For example, if the maximum value in the above data is 1300ppm and the minimum value is 1150ppm, subtract the minimum value from the maximum value to obtain the range of carbon-containing gas concentration. For example, 1300ppm - 1150ppm = 150ppm.

[0085] Calculation of the range of suspended particles in high-incidence areas:

[0086] Filter suspended particulate matter (such as PM2.5) concentration data from high-incidence area data to form an independent dataset. For example, extract PM2.5 concentration values ​​collected by sensors inside and outside door and window openings over the past 10 minutes. Assume the data points are [35μg / m³, 40μg / m³, 28μg / m³, 32μg / m³] and find the maximum and minimum values ​​in the dataset. For example, if the maximum value in the above data is 40μg / m³ and the minimum value is 28μg / m³, the calculated range is 40μg / m³ - 28μg / m³ = 12μg / m³.

[0087] Calculation of the extreme value of volatile organic compounds in the blocked area:

[0088] Filter the concentration data of volatile organic compounds (such as formaldehyde) from the obstruction area data packets to form an independent data set. For example, extract the formaldehyde concentration values ​​collected by the L-shaped corner sensor over the past 10 minutes. Assume the data points are [0.08 mg / m³, 0.06 mg / m³, 0.07 mg / m³, 0.09 mg / m³] and find the maximum and minimum values ​​in the data set. For example, the maximum value of the above data is 0.09 mg / m³, and the minimum value is 0.06 mg / m³. The calculated range is 0.09 mg / m³ - 0.06 mg / m³ = 0.03 mg / m³.

[0089] Compare the range of each region with the preset threshold:

[0090] The extreme value threshold of carbon-containing gas in the core area is 300ppm. If the calculated value is 150ppm (not exceeding the threshold value),

[0091] The suspended particle threshold in high-incidence areas is 20 μg / m³. If the calculated value is 12 μg / m³ (not exceeding the threshold);

[0092] The VOCs threshold in the blocked area is 0.05 mg / m³, and the calculated value is 0.03 mg / m³ (not exceeding the threshold).

[0093] Maximum range determination: If all ranges do not exceed the threshold, the system will not generate a correction factor; if any range exceeds the threshold (for example, the range in the core area is 350ppm, the high-incidence area is 25μg / m³, and the blocked area is 0.06mg / m³), the maximum value (such as 350ppm) will be selected from the ranges that exceed the threshold.

[0094] Generate spatial heterogeneity correction factor K:

[0095] Based on the proportional relationship between the maximum range and the K value, a benchmark scaling factor is set (e.g., K = maximum range ÷ benchmark value). For example, if the maximum range is 350 ppm and the benchmark value is 100 ppm, then K = 350 ÷ 100 = 3.5. If the maximum range increases in subsequent calculations (e.g., to 400 ppm), the K value is proportionally increased to 4.0 to ensure that the K value always reflects the current maximum level of spatial heterogeneity.

[0096] It can quantify the fluctuations in environmental parameters within a region (e.g., whether CO2 concentrations in core areas are uniform, or whether there are localized peaks in particulate matter intrusion in high-incidence areas), avoiding the tendency to treat the entire home environment as "homogeneous" and overlook localized pollution concentrations. When the extreme difference in a particular region exceeds a threshold, a K factor is generated, which can be used to weight the degradation of that region's pollution in subsequent quality assessments. For example, if the extreme difference in VOCs in a congested area exceeds a threshold, an increase in the K value will cause the corrected quality index M' to more significantly reflect the pollution impact of that region, preventing distortion in the evaluation model due to uneven parameter distribution.

[0097] like Figure 2 As shown, in a preferred embodiment of the present invention, the original environmental data and the spatial heterogeneity correction factor K are input into a preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environmental quality index M. The initial indoor environmental quality index M is then subjected to degradation weighting processing using the spatial heterogeneity correction factor K to generate a corrected comprehensive quality evaluation index M', which may include:

[0098] The partition data package and the spatial heterogeneity correction factor K are input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environment quality index M, specifically including:

[0099] Bind the core area data packets, high-incidence area data packets and congestion area data packets with the spatial heterogeneity correction factor K to form a fused data unit;

[0100] Perform degradation direction unification processing on the environmental parameters in the fused data unit. After the conversion, the increase in the value of all parameters indicates that the environmental quality is deteriorating, and the parameter data after direction unification processing is obtained;

[0101] Based on the parameter data after direction unification, the initial indoor environment quality index M is generated by performing membership weighted calculation in combination with the regional type weight matrix;

[0102] Based on the value of the spatial heterogeneity correction factor K, the initial indoor environmental quality index M is dynamically degraded and weighted. When the K value increases, the degradation weighted intensity is adjusted proportionally to generate a dynamic degradation weighted value. The degradation weighted intensity is associated with the regional type, that is, the weighted intensity of the airflow obstruction area is greater than that of the high-risk pollution area and the core area of ​​human activity;

[0103] The dynamic degradation weighted value is superimposed on the initial indoor environmental quality index M to generate a comprehensive quality evaluation index M' after degradation weighting.

[0104] In this embodiment of the present invention, real-time data packets for core areas, high-incidence areas, and congestion areas are retrieved from the IoT platform. Each data packet contains environmental parameters for the corresponding area (e.g., CO2 concentration in the core area, PM2.5 concentration in the high-incidence area, and formaldehyde concentration in the congestion area) and a timestamp. For example, a core area data packet contains 10-minute CO2 concentration data of [1200ppm, 1150ppm, 1300ppm], a high-incidence area data packet contains PM2.5 concentration data of [35μg / m³, 40μg / m³, 28μg / m³], and a congestion area data packet contains formaldehyde concentration data of [0.08mg / m³, 0.06mg / m³, 0.09mg / m³]. A ​​K value (e.g., 3.5) is associated with these three types of data packets to form a fused data unit. Each unit structure is "{regional data, K value}." For example, the core area fused unit is "{[1200, 1150, 1300], 3.5}," ensuring that the K value can be traced back to the degree of heterogeneity in a specific area.

[0105] Unified processing of environmental parameter degradation direction:

[0106] Distinguish the relationship between each parameter and environmental quality, such as:

[0107] Positive degradation parameters: pollutant concentration (the higher the concentration, the worse the environment), temperature (the higher the temperature, the worse the thermal comfort);

[0108] Reverse degradation parameter: relative humidity (in some scenarios, the higher the humidity, the worse the comfort, but it needs to be converted according to the threshold).

[0109] Unified conversion: convert all parameters to the unified direction of "increase in value = environmental degradation":

[0110] Forward parameter: directly retain the original value (for example, CO2 concentration of 1300ppm is worse than 1200ppm);

[0111] Reverse parameter: The threshold is used to convert the deterioration direction. For example, if the relative humidity threshold is 60% and the measured value is 70%, the value is converted to "70% - 60% = 10%." A larger value indicates a greater deviation from the comfort zone.

[0112] For example, if the core area temperature is 28°C (comfort threshold 26°C), it is converted to "28-26=2", and the value 2 represents the degree of temperature degradation; if the humidity is 65% (threshold 60%), it is converted to "65-60=5", which represents the degree of humidity degradation.

[0113] Membership weighted operation based on regional weights:

[0114] Weights are set based on the health impact of the region, for example:

[0115] The weight of the airflow obstruction area is α = 0.4 (pollutants tend to accumulate and have a lasting impact);

[0116] The weight of high-pollution risk areas is β = 0.3 (directly related to outdoor pollution intrusion);

[0117] The weight of the core area of ​​personnel activities γ=0.3 (directly affects human comfort).

[0118] The unified parameter values ​​are mapped to preset degradation levels (e.g., "Excellent," "Good," "Fair," and "Poor"), and the degree of membership of each parameter to each level is calculated. For example, if the CO2 concentration in the core area is 1300 ppm and the "Poor" threshold is 1200 ppm, then its degree of membership to "Poor" is 1 and to all other levels is 0.

[0119] Multiply the membership results of each area by the corresponding weight and add them together to generate the initial indoor environment quality index M. For example:

[0120] The membership degree of formaldehyde concentration in the blocked area to “poor” is 0.8, and the weighted contribution value = 0.8 × 0.4 = 0.32;

[0121] The membership degree of PM2.5 in high-incidence areas to “general” is 0.6, and the weighted contribution value = 0.6 × 0.3 = 0.18;

[0122] The membership degree of CO2 in the core area to “poor” is 1, and the weighted contribution value = 1×0.3=0.3;

[0123] The initial indoor environment quality index M=0.32+0.18+0.3=0.8 (the larger the value, the worse the environment).

[0124] Adjust the weighting amplitude according to the K value, and preset the weighting coefficient λ=K×0.1 (for example, when K=3.5, λ=0.35). Assign weighted intensity in the order of "blocked area > high-incidence area > core area":

[0125] Weighted increment of the blocking area = λ × 0.5 (50% of the total weight);

[0126] Weighted increment of high-incidence areas = λ × 0.3;

[0127] The weighted increment of the core area = λ × 0.2.

[0128] Calculate the dynamic degradation value: For example, when K=3.5, λ=0.35, the weighted increment of the blocking area = 0.35×0.5=0.175, the high-incidence area = 0.35×0.3=0.105, and the core area = 0.35×0.2=0.07.

[0129] The initial indoor environmental quality index M is added to the weighted increments of each region to obtain the revised comprehensive index M'. For example, if M = 0.8, the sum of the weighted increments = 0.175 + 0.105 + 0.07 = 0.35, and M' = 0.8 + 0.35 = 1.15, indicating that spatial heterogeneity leads to an increase in the degree of environmental degradation.

[0130] By binding K values ​​to zone data, the model can quantitatively reflect the heterogeneous environment characterized by severe pollution in corners but good performance in core areas, avoiding the traditional evaluation model that treats the entire house as a homogeneous entity and underestimates local pollution risks. Unifying degradation directions ensures comparability among different parameters (such as temperature and pollutant concentration). Combined with dynamic K-value weighting, this model can respond in real time to changes in regional extremes. The weighted M' directly correlates to areas of high pollution. For example, when M' degradation is primarily due to congestion, the system prioritizes activating purification equipment in that area rather than uniformly controlling the entire house, achieving targeted treatment and reducing energy waste. The regional weight matrix and weighted priority (congestion > high-incidence areas > core areas) embody the evaluation logic of "pollution health risk > outdoor pollution intrusion > thermal comfort," ensuring that the model prioritizes comfort while protecting health. When K values ​​increase with regional extremes, M' deteriorates simultaneously, providing early warning of potential pollution concentration risks (such as the slow accumulation of VOCs in corners) and avoiding the lag of control measures after pollution spreads.

[0131] In a preferred embodiment of the present invention, based on the revised comprehensive quality evaluation index M', the IoT control center independently generates three types of device control instructions, which may include:

[0132] According to the degradation direction of the comprehensive quality evaluation index M' after degradation weighting processing, three types of independent control instructions are generated by the Internet of Things control center. The three types of device control instructions include:

[0133] If M' indicates that the thermal comfort of the core area of ​​personnel activities has deteriorated, then the air conditioning temperature adjustment instruction bound to this area is generated;

[0134] If M' indicates that the concentration of suspended particulate matter in a high-pollution risk area exceeds the standard, a ventilation instruction for the fresh air system associated with that area is generated;

[0135] If M' indicates that the concentration of volatile organic compounds in the airflow obstruction area exceeds the standard, a disinfection instruction for the purification equipment bound to the area is generated;

[0136] When multiple areas deteriorate at the same time, instructions are triggered in sequence: purification instructions for airflow-blocked areas, ventilation instructions for areas with high pollution risks, and air-conditioning instructions for core areas where people move.

[0137] In an embodiment of the present invention, a revised M' is obtained from the closed-loop feedback module. This index has integrated the spatial heterogeneity correction factor K and the extreme difference data of each region. Its numerical change directly reflects the degree of environmental degradation in different functional areas. For example, if M' shows that the weighted value of the temperature parameter in the core area is too high, it indicates that the thermal comfort in the core area of ​​personnel activities has deteriorated; if the weighted value of VOCs in the blocked area accounts for the largest proportion, it indicates that the pollution in the airflow blocked area exceeds the standard. The system identifies the area with the most significant deterioration based on the weighted contribution value of each area in M'. For example, when M'=1.15, the weighted contribution of the blocked area is 0.5, the high-incidence area is 0.3, and the core area is 0.35, then the blocked area is determined to be the primary deterioration area.

[0138] Core area thermal comfort adjustment instructions:

[0139] When M' indicates that the core zone temperature exceeds the preset comfort threshold (e.g., 26°C) and the degradation contribution exceeds the regional weight (e.g., 0.3), the system retrieves the address of the air conditioner bound to that zone and generates a temperature adjustment command. For example, if the current core zone temperature is 28°C, the command might be "Lower the air conditioner setpoint by 1°C," along with the device's operating time (e.g., 30 minutes of continuous operation).

[0140] Instructions for purification of suspended particles in high-incidence areas:

[0141] If the weighted value of suspended particulate matter (such as PM2.5) in a high-incidence area (M') exceeds a corresponding threshold (e.g., a baseline value of 1.0), the system triggers the associated fresh air system in that area. For example, if the PM2.5 concentration range in a high-incidence area is 25μg / m³ (exceeding the threshold of 20μg / m³), a command is generated to "operate the fresh air system at medium speed for 15 minutes," prioritizing the activation of ventilation fans near door and window openings.

[0142] Instructions for VOCs elimination in blocked areas:

[0143] When M' shows that the weighted value of VOCs (such as formaldehyde) in the blocked area exceeds the benchmark value (such as 0.8), the system locates the purification equipment deployed in the area (such as the air purifier in the corner) and generates an instruction to "start the high-intensity disinfection mode of the purification equipment", such as starting the activated carbon adsorption + ultraviolet disinfection combination function, and continuing to run until the VOCs concentration range is reduced to within the threshold.

[0144] Instruction priority triggering during multi-region degradation:

[0145] The system presets the triggering sequence of "congestion area purification → high-incidence area ventilation → core area temperature adjustment" to avoid equipment conflicts. For example, when VOCs in the congestion area and PM2.5 in the high-incidence area exceed the standard at the same time, a disinfection instruction for the purification equipment in the congestion area is first generated (such as starting purifier No. 1) and running it for 5 minutes; after the degradation weight value of the congestion area decreases, a ventilation instruction for the fresh air system in the high-incidence area is triggered (such as opening an external window for 10 minutes); finally, an air conditioning adjustment instruction is generated based on the core area temperature data (such as lowering the temperature by 0.5°C). Multi-area instructions are arranged into queues according to priority, and each instruction is accompanied by execution time and interval parameters. For example, after the congestion area instruction is executed for 10 minutes, the high-incidence area instruction is triggered after a 2-minute interval to avoid a sudden increase in energy consumption caused by the simultaneous operation of multiple devices.

[0146] Dynamic adjustment of instruction parameters:

[0147] If M' indicates a high degree of degradation (e.g., K = 4.0), the command parameters are enhanced. For example, when the core area temperature deteriorates, the standard command is "lower by 1°C." When K > 3.0, the command is adjusted to "lower by 2°C and increase the wind speed to high." The command includes device linkage parameters. For example, when the fresh air system is running, it automatically closes the windows on the same side to prevent airflow from impacting ventilation efficiency; when the purification equipment is turned on, it also adjusts the direction of the indoor fan to enhance air circulation.

[0148] Based on the degradation direction of M', the system directly targets problem areas. For example, it regulates air conditioning only in core areas where thermal comfort is deteriorating, and activates fresh air in high-incidence areas with excessive particulate matter. This avoids the "over-regulation" or "missed regulation" that can result from traditional, unified, whole-house control, ensuring that equipment resources are focused on addressing the actual problem areas. By triggering commands in a prioritized order (prioritizing congested areas for purification, followed by ventilation in high-incidence areas), it avoids energy waste caused by running multiple devices simultaneously. For example, when both a congested area and a core area deteriorate simultaneously, the congested area, which poses a higher pollution and health risk, is addressed first, followed by thermal comfort issues, reducing unnecessary equipment idling. A command queuing mechanism dynamically adapts to changes in the indoor environment (e.g., a sudden gathering of people causes a simultaneous increase in CO2 in the core area and VOCs in the congested area). By triggering commands in stages, it prevents control strategies from failing due to the cross-influence of environmental parameters, ensuring maximum control effectiveness for each type of equipment.

[0149] In a preferred embodiment of the present invention, after executing the device control instruction, the data of each functional area is re-monitored through the Internet of Things network. If the parameter range of the same functional area is not reduced to within the threshold, the degradation weighted intensity is adjusted and the revised comprehensive quality evaluation index M' is regenerated. If the range of all areas is lower than the threshold, the revised comprehensive quality evaluation index M' is continuously monitored to see if the fluctuation exceeds the preset warning threshold. This may include:

[0150] Re-collect data from each functional area through the IoT network, generate new partition data packets and calculate parameter ranges;

[0151] If the parameter range of the same functional area does not fall within the threshold, the proportional adjustment intensity in the degradation weighted processing is adjusted, and the corrected comprehensive quality evaluation index M' is regenerated to trigger a new round of equipment control instructions; if the range of all areas is lower than the threshold, the fluctuation of the correction index M' is continuously monitored. When the fluctuation amplitude of M' exceeds the preset warning threshold, the environmental adaptive adjustment process is automatically restarted.

[0152] In an embodiment of the present invention, after executing the device control instruction, the sensor group of each functional area is triggered through the Internet of Things network to re-collect temperature, humidity and pollutant concentration data at a frequency of minutes. For example, the core area sensor re-collects the CO2 concentration from the ground to a height of 1.8 meters, the high-incidence area sensor monitors the PM2.5 concentration inside and outside the door and window openings, and the blocked area sensor reads the VOCs concentration in the concave wall corners. The re-collected data is classified and stored according to the functional area to generate new core area data packets, high-incidence area data packets and blocked area data packets. Each data packet contains the real-time sampling values ​​and timestamps of all sensors in the area. For example, the core area data packet records the CO2 concentration data [1100ppm, 1050ppm, 1200ppm] at each point in the past 10 minutes.

[0153] Directional range calculation:

[0154] Extract carbon-containing gas concentration data from the core area data package and calculate the difference between the maximum and minimum values, such as 1200ppm - 1050ppm = 150ppm;

[0155] Extract suspended particle concentration data from the high-incidence area data package and calculate the range, such as 45μg / m³ - 28μg / m³ = 17μg / m³;

[0156] Extract VOCs concentration data from the blocked area data package and calculate the range, such as 0.07mg / m³-0.05mg / m³=0.02mg / m³.

[0157] Compare each range to the preset thresholds (300 ppm in the core area, 20 μg / m³ in the high-incidence area, and 0.05 mg / m³ in the obstruction area). For example, in the above calculation, the range of 150 ppm in the core area is less than 300 ppm, the range of 17 μg / m³ in the high-incidence area is less than 20 μg / m³, and the range of 0.02 mg / m³ in the obstruction area is less than 0.05 mg / m³, all of which meet the threshold requirements.

[0158] Degradation weighted intensity adjustment when threshold is not reached:

[0159] If the range in a particular area does not fall within the threshold (e.g., the range in the core area is 350ppm > 300ppm), the system proportionally increases the weighted intensity of degradation. For example, if the original weighting coefficient is K = 3.5 and the adjusted K = 4.0, the degradation contribution of that area in the comprehensive evaluation will increase. Based on the adjusted weighted intensity, the resampled data and the new K value are input into the quality evaluation module to recalculate the revised comprehensive quality evaluation index M'. For example, if the original M' = 1.15 and the adjusted M' = 1.3, a new round of equipment control instructions will be triggered (e.g., further lowering the core area air conditioning temperature).

[0160] If the ranges in all regions are below the threshold, the system enters the steady-state monitoring phase and continuously tracks the corrected M' fluctuations. For example, the M' value is recorded every 5 minutes to form a dynamic fluctuation curve. If the M' fluctuation exceeds the preset warning threshold (e.g., fluctuations exceeding 0.3), indicating an abnormal environmental fluctuation (such as sudden intrusion of outdoor pollution), the environmental adaptive adjustment process is automatically restarted, re-executing the entire process from data collection to command generation.

[0161] A closed-loop mechanism of repeated monitoring, evaluation, and regulation ensures continuous improvement in areas that fall short of standards. For example, if VOC concentrations in a congested area fail to reach the threshold after initial purification, the system increases the weighted intensity and readjusts to prevent pollution "leakages" until all environmental parameters uniformly meet standards. When the ranges in all areas are below the threshold, the system switches to dynamic monitoring rather than continuous regulation, restarting the process only when M' fluctuates abnormally, preventing unnecessary equipment operation. For example, when the indoor environment is stable, air conditioning does not need to be frequently adjusted, and the fresh air system does not need to operate continuously, reducing energy consumption and wear. Continuous monitoring of M' fluctuations can promptly detect sudden pollution events (such as a sudden increase in outdoor smog causing a rebound in particulate matter concentrations in a high-incidence area). Rapidly responding by restarting the regulation process ensures that the indoor environment is not affected by sudden external factors and maintains a healthy and comfortable state. This closed-loop mechanism not only addresses immediate pollution issues but also prevents environmental parameter rebounds through continuous monitoring. For example, if human activity causes temperature fluctuations in the core area after the temperature has been regulated to standard, the system can identify M' fluctuations and readjust, preventing periodic deterioration in environmental quality.

[0162] An embodiment of the present invention further provides a computing device comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, executes the system described above. All implementations in the above system embodiments are applicable to this embodiment and can achieve the same technical effects.

[0163] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the system described above. All implementations in the above system embodiments are applicable to this embodiment and can achieve the same technical effects.

[0164] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. An indoor environment adaptive adjustment system based on the Internet of Things, characterized in that: include: The data acquisition module is used to divide the indoor space into three functional areas and deploy a multi-parameter sensor group in each functional area through the Internet of Things network to collect raw environmental data in real time, including temperature, relative humidity and air pollutant concentration data. The functional areas are divided according to the indoor physical layout, including the core area of ​​human activity, the area with high pollution risk and the area with airflow obstruction. The core area of ​​human activity, the area with high pollution risk and the area with airflow obstruction include: the core area of ​​human activity is the entire space from the ground to a height of 1.8 meters; the area with high pollution risk is the three-dimensional passage within 0.5 meters inside and outside all door and window openings; the airflow obstruction area is the L-shaped space with a concave wall corner with a depth greater than or equal to 0.5 meters indoors. The sensor group is deployed in each functional area through the Internet of Things network to collect raw environmental data including temperature, relative humidity and air pollutant concentration in real time; The spatial heterogeneity analysis module is used to calculate the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area as the regional range. When the regional range of any parameter exceeds the set threshold, a spatial heterogeneity correction factor K is generated, where the K value is proportional to the maximum regional range. The real-time collected temperature, relative humidity and air pollutant concentration data are classified and stored according to functional areas as core area data packets, high-incidence area data packets and blocked area data packets; a directional calculation is performed on each data packet, where the core area data packet calculates the range of carbon-containing gas pollutant concentration; the high-incidence area data packet calculates the range of suspended particulate pollutant concentration; and the blocked area data packet calculates the range of volatile organic pollutant concentration; when any range exceeds the corresponding threshold, the maximum value of all ranges is selected to generate a spatial heterogeneity correction factor K that is proportional to the maximum value; The quality evaluation module is used to input the original environmental data and the spatial heterogeneity correction factor K into the preset fuzzy comprehensive evaluation model through the Internet of Things platform, calculate the initial indoor environmental quality index M, and perform degradation weighting processing on the initial indoor environmental quality index M using the spatial heterogeneity correction factor K to generate a corrected comprehensive quality evaluation index M'; A control instruction module is used to independently generate control instructions for three types of equipment through the IoT control center based on the revised comprehensive quality evaluation index M'; The closed-loop feedback module is used to re-monitor the data of each functional area through the Internet of Things network after executing the equipment control instructions. If the parameter range of the same functional area is not reduced to within the threshold, the degradation weighted intensity is adjusted and the revised comprehensive quality evaluation index M' is regenerated. If the range of all areas is lower than the threshold, the revised comprehensive quality evaluation index M' is continuously monitored and the fluctuation exceeds the preset warning threshold.

2. The indoor environment adaptive adjustment system based on the Internet of Things according to claim 1 is characterized in that: Directional calculations are performed on each data package. The core area data package calculates the extreme difference in carbon gas pollutant concentration; the high-incidence area data package calculates the extreme difference in suspended particulate pollutant concentration; and the blocked area data package calculates the extreme difference in volatile organic pollutant concentration, including: Extract the carbon-containing gas pollutant concentration data set from the core area data package, calculate the difference between the maximum and minimum values, and obtain the carbon-containing gas pollutant concentration range; extract the suspended particle pollutant concentration data set from the high-incidence area data package, calculate the difference between the maximum and minimum values, and obtain the suspended particle pollutant concentration range; extract the volatile organic pollutant concentration data set from the blocked area data package, calculate the difference between the maximum and minimum values, and obtain the volatile organic pollutant concentration range; When any range exceeds the corresponding threshold, the maximum value of all ranges is output. The corresponding thresholds include: The extreme difference of carbon-containing gas in the core area is greater than 300 ppm, the extreme difference of suspended particles in the high-incidence area is greater than 20 μg / m³, and the extreme difference of volatile organic compounds in the blocked area is greater than 0.05 mg / m³.

3. The indoor environment adaptive adjustment system based on the Internet of Things according to claim 2 is characterized in that: The original environmental data and the spatial heterogeneity correction factor K are input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environmental quality index M. The initial indoor environmental quality index M is then subjected to degradation weighting processing using the spatial heterogeneity correction factor K to generate the revised comprehensive quality evaluation index M', which includes: The partition data package and the spatial heterogeneity correction factor K are input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environment quality index M; Based on the value of the spatial heterogeneity correction factor K, the initial indoor environmental quality index M is dynamically degraded and weighted. When the K value increases, the degradation weighted intensity is adjusted proportionally to generate a dynamic degradation weighted value. The degradation weighted intensity is associated with the regional type, that is, the weighted intensity of the airflow obstruction area is greater than that of the high-risk pollution area and the core area of ​​human activity; The dynamic degradation weighted value is superimposed on the initial indoor environmental quality index M to generate a comprehensive quality evaluation index M' after degradation weighting.

4. The indoor environment adaptive adjustment system based on the Internet of Things according to claim 3 is characterized in that: The partition data package and the spatial heterogeneity correction factor K are input into the preset fuzzy comprehensive evaluation model through the Internet of Things platform to calculate the initial indoor environment quality index M, including: Bind the core area data packets, high-incidence area data packets and congestion area data packets with the spatial heterogeneity correction factor K to form a fused data unit; Perform degradation direction unification processing on the environmental parameters in the fused data unit. After the conversion, the increase in the value of all parameters indicates that the environmental quality is deteriorating, and the parameter data after direction unification processing is obtained; Based on the parameter data after direction unification, the membership weighted operation is performed in combination with the regional type weight matrix to generate the initial indoor environment quality index M.

5. The indoor environment adaptive adjustment system based on the Internet of Things according to claim 4 is characterized in that: According to the revised comprehensive quality evaluation index M', the IoT control center independently generates three types of device control instructions, including: According to the degradation direction of the comprehensive quality evaluation index M' after degradation weighting processing, three types of independent control instructions are generated by the Internet of Things control center. The three types of device control instructions include: If M' indicates that the thermal comfort of the core area of ​​personnel activities has deteriorated, then the air conditioning temperature adjustment instruction bound to this area is generated; If M' indicates that the concentration of suspended particulate matter in a high-pollution risk area exceeds the standard, a ventilation instruction for the fresh air system associated with that area is generated; If M' indicates that the concentration of volatile organic compounds in the airflow obstruction area exceeds the standard, a disinfection instruction for the purification equipment bound to the area is generated; When multiple areas deteriorate at the same time, instructions are triggered in sequence: purification instructions for airflow-blocked areas, ventilation instructions for areas with high pollution risks, and air-conditioning instructions for core areas where people move.

6. The indoor environment adaptive adjustment system based on the Internet of Things according to claim 5 is characterized in that: After executing the equipment control command, the data of each functional area is re-monitored through the Internet of Things network. If the parameter range of the same functional area is not reduced to within the threshold, the degradation weighted intensity is adjusted and the revised comprehensive quality evaluation index M' is regenerated. If the range of all areas is lower than the threshold, the revised comprehensive quality evaluation index M' is continuously monitored for fluctuations exceeding the preset warning threshold, including: Re-collect data from each functional area through the IoT network, generate new partition data packets and calculate parameter ranges; If the parameter range of the same functional area does not fall within the threshold, the proportional adjustment intensity in the degradation weighted processing is adjusted, and the corrected comprehensive quality evaluation index M' is regenerated to trigger a new round of equipment control instructions; if the range of all areas is lower than the threshold, the fluctuation of the correction index M' is continuously monitored. When the fluctuation amplitude of M' exceeds the preset warning threshold, the environmental adaptive adjustment process is automatically restarted.

7. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the system according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, which, when executed by a processor, implements the system according to any one of claims 1 to 6.

Images