Intelligent indoor health risk assessment method based on dynamic multi-parameter feedback

Abstract

The invention discloses an intelligent indoor health risk assessment method based on dynamic multi-parameter feedback, and the method comprises the steps: building an environment state simulation model after collecting environment parameters, obtaining an environment state indication parameter at a detection time point in real time, and selecting a corresponding assessment standard grade in real time according to the type of an actor in a current environment, the method comprises the following steps: performing balanced segmentation on an environment state simulation curve by an evaluation standard grade straight line, obtaining an area S of the environment state simulation curve whose y value is greater than the evaluation standard grade straight line, obtaining an area S of the environment state simulation curve whose y value is less than the evaluation standard grade straight line, constructing a state determination model, inputting S and S in real time, and obtaining a state value in real time. Whether the indoor environment state reaches the standard or not is judged according to the state value obtained in real time, the problem of data islands is solved, real-time health risk assessment is achieved by dynamically fusing the environment parameters and the actor data in combination with the self-adaptive machine learning model, and more accurate health risk assessment can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor environmental health monitoring, and specifically to a method for achieving real-time health risk assessment by dynamically fusing environmental parameters and behavioral data in combination with an adaptive machine learning model. The present invention particularly relates to an intelligent indoor health risk assessment method based on dynamic multi-parameter feedback. Background Art

[0002] Deficiencies of existing indoor environmental health monitoring technologies: 1. Single parameter: Traditional systems only monitor environmental parameters such as PM2.5 and CO2, ignoring the interaction between human physiological state and the environment; 2. Static threshold determination: After collecting environmental parameters, a fixed threshold is used to trigger an early warning, which cannot adapt to individual differences; 3. Data silo problem: Environmental and behavioral data are processed independently, lacking multimodal fusion analysis. Summary of the Invention

[0003] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0004] In view of the above problems existing in the existing indoor environmental health monitoring methods, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is to solve the problems that existing indoor environmental health monitoring methods ignore the interaction effect between human physiological state and environment, cannot adapt to individual differences and lack multimodal fusion analysis.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent indoor health risk assessment method based on dynamic multi-parameter feedback, comprising the following steps: S1: acquiring various environmental health data at the detection time point in real time through a series of sensors arranged indoors; S2: acquiring the environmental state parameters at the detection time point in real time based on the constructed environmental state simulation model; S3: using the environmental state parameters acquired in step S2 as the vertical coordinates and the detection point time in the time sequence as the horizontal coordinates, acquiring the positions of the reference points in the coordinate system, connecting the reference points with a smooth curve, and acquiring the environmental state simulation curve; S4: According to the category of the actor in the current environment, the corresponding evaluation standard level is selected in real time; S5: the evaluation standard level obtained in step S4 is matched with the coordinate system in step S3; S6: in the coordinate system, the environmental state simulation curve is evenly divided by the evaluation standard level straight line, and the area S of the environmental state simulation curve where the y value is greater than the evaluation standard level straight line is obtained, and the area S' of the environmental state simulation curve where the y value is less than the evaluation standard level straight line is obtained; S7: construct a state judgment model, input S and S' in real time, obtain the state value in real time, and judge whether the indoor environmental state meets the standard based on the state value obtained in real time.

[0007] As a preferred solution of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback described in the present invention, it is characterized in that: the various environmental health data obtained in step S1 specifically include: formaldehyde concentration a, mg / m³ detected by the laser spectral sensor; CO2 concentration b, mg / m³ detected by the NDIR (non-dispersive infrared) sensor; PM2.5 concentration c, μg / m³ detected by the anti-wet sensor array.

[0008] As a preferred solution of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback described in the present invention, the environmental state simulation model constructed is specifically:

[0009] Wherein, η is the environmental parameter; a is the formaldehyde concentration, mg / m³; b is the CO2 concentration, mg / m³; c is the PM2.5 concentration, μg / m³; ln2.1 is the adjustment constant.

[0010] As a preferred solution of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback described in the present invention, in which: in step S4, the different assessment standard levels selected according to the category of the actor are specifically as follows: the number of infants and young children ≥1, the standard level is defined as level one, corresponding to y=799.258 in the coordinate system of step S3; the number of infants and young children = 0, the number of elderly people ≥4, the standard level is defined as level two, corresponding to y=2399.258 in the coordinate system of step S3; the number of infants and young children = 0, 1≤the number of elderly people≤3, the standard level is defined as level three, corresponding to y=6299.258 in the coordinate system of step S3; the number of infants and young children = 0, the number of elderly people = 0, the standard level is defined as level four, corresponding to y=15999.258 in the coordinate system of step S3.

[0011] As a preferred solution of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback described in the present invention, the state determination model is specifically:

[0012] Among them, δ is the state value; S1 is the first area of the environmental state simulation curve where the y value is greater than the evaluation standard level straight line; S m is the area of the mth block where the y value of the environmental state simulation curve is greater than the evaluation standard level straight line; S1' is the area of the first block where the y value of the environmental state simulation curve is less than the evaluation standard level straight line; S n ´ is the area of the nth block in the environmental state simulation curve where the y value is less than the evaluation standard level straight line.

[0013] As a preferred solution of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback described in the present invention, when the state value δ is less than or equal to 1, it is defined that the environmental state detection meets the standard in the current state, otherwise the environmental state detection does not meet the standard.

[0014] As a preferred embodiment of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback described in the present invention, in step S6, when obtaining area S or area S', the environmental state simulation curve is evenly divided. If the environmental state simulation curve intersects with the assessment standard level straight line at the initial endpoint or the final endpoint, straight lines perpendicular to the X-axis are drawn from the first and last endpoints of the environmental state simulation curve and connected to the X-axis. The intersection of the X-axis, the environmental state simulation curve, and the straight line perpendicular to the X-axis is taken as the measured area at the initial endpoint or the final endpoint, and is included in the state determination model according to the standard.

[0015] The present invention provides an intelligent indoor health risk assessment method based on dynamic multi-parameter feedback, which has the following beneficial effects: Solving the problem of single parameters: Traditional systems only monitor environmental parameters such as PM2.5 and CO2, ignoring the interaction between human physiological state and the environment. This method uses a series of sensors deployed indoors to obtain real-time environmental health data at the time of detection, including formaldehyde concentration, CO2 concentration, PM2.5 concentration, etc., thus solving the problem of single parameters.

[0016] Solve the problem of static threshold determination: After collecting environmental parameters, using a fixed threshold to trigger an alert cannot adapt to individual differences. This method uses a constructed environmental state simulation model to obtain real-time environmental state parameters at the detection time point, and selects the corresponding evaluation standard level in real time based on the type of actor in the current environment, thus solving the static threshold determination problem.

[0017] This method solves the data silo problem: Environmental and behavioral data are processed independently, lacking multimodal fusion analysis. This method evenly divides the environmental state simulation curve into sections using the assessment standard grade line. It then obtains the area S where the y value of the environmental state simulation curve exceeds the assessment standard grade line, and the area S' where the y value of the environmental state simulation curve is less than the assessment standard grade line. A state determination model is then constructed, using S and S' as real-time inputs to obtain state values. Based on these real-time state values, the model determines whether the indoor environmental state meets the standards, thus solving the data silo problem.

[0018] Provide more accurate health risk assessment: This method dynamically integrates environmental parameters and behavioral data, and combines them with adaptive machine learning models to achieve real-time health risk assessment, which can provide more accurate health risk assessment.

[0019] Adaptability to individual differences: This method selects different levels of evaluation criteria based on the type of actor, which can adapt to individual differences.

[0020] Multimodal fusion analysis: This method evenly divides the environmental state simulation curve by the evaluation standard grade straight line, obtains the area S in the environmental state simulation curve where the y value is greater than the evaluation standard grade straight line, and obtains the area S' in the environmental state simulation curve where the y value is less than the evaluation standard grade straight line. A state judgment model is constructed, S and S' are input in real time, and the state value is obtained in real time. Based on the state value obtained in real time, it is determined whether the indoor environmental state meets the standard, thus realizing multimodal fusion analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them: Figure 1This is a flow chart of the overall method of the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback provided by the present invention.

[0022] Figure 2 This is a simulation diagram of the environmental state simulation curve and the evaluation standard level straight line provided by the present invention. DETAILED DESCRIPTION

[0023] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0024] Deficiencies of existing indoor environmental health monitoring technologies: 1. Single parameter: Traditional systems only monitor environmental parameters such as PM2.5 and CO2, ignoring the interaction between human physiological state and the environment; 2. Static threshold determination: After collecting environmental parameters, a fixed threshold is used to trigger an early warning, which cannot adapt to individual differences; 3. Data silo problem: Environmental and behavioral data are processed independently, lacking multimodal fusion analysis.

[0025] Therefore, please refer to Figure 1 The present invention provides an intelligent indoor health risk assessment method based on dynamic multi-parameter feedback, comprising the following steps: S1: A series of sensors placed indoors are used to obtain real-time environmental health data at the detection time point; S2: Obtain the environmental state parameters at the detection time point in real time based on the constructed environmental state simulation model; S3: Using the environmental state parameters obtained in step S2 as the ordinate and the detection point time in the time sequence as the abscissa, obtain the position of each reference point in the coordinate system, connect the reference points with a smooth curve, and obtain the environmental state simulation curve; S4: Select the corresponding evaluation standard level in real time based on the category of the actor in the current environment; S5: Matching the evaluation standard level obtained in step S4 to the coordinate system in step S3; S6: In the coordinate system, the environmental state simulation curve is evenly divided by the evaluation standard level line. The area S where the y value of the environmental state simulation curve is greater than the evaluation standard level line is obtained, and the area S' where the y value of the environmental state simulation curve is less than the evaluation standard level line is obtained. S7: Construct a state determination model, input S and S' in real time, obtain state values in real time, and determine whether the indoor environmental state meets the standard based on the state values obtained in real time.

[0026] Specifically, the environmental health data obtained in step S1 include: According to the formaldehyde concentration a detected by the laser spectrum sensor, mg / m³; CO2 concentration b, mg / m³, detected by NDIR (non-dispersive infrared) sensor; PM2.5 concentration c, μg / m³, detected by the moisture-resistant sensor array.

[0027] It should be noted that the laser spectrum sensor, NDIR (non-dispersive infrared) sensor and moisture-resistant sensor array used in the present invention are all existing conventional sensors, and the detection methods used are also relatively mature technical means.

[0028] A brief description is as follows: ① Formaldehyde concentration a detection: 1. Sensor module design Multi-range detection: Electrochemical sensor: detection range 0-10 ppm, resolution 0.01 ppm (corresponding to 0.0123 mg / m³); Laser spectrum sensor: detection limit 0.001 mg / m³ (0.0008 ppm), meeting the WHO chronic exposure guideline value (0.03 mg / m³); 2. Risk Assessment Thresholds (Table 1) Table 1

[0029] ②CO2 concentration b detection: 1. NDIR (Non-Dispersive Infrared) sensor: dual wavelength detection (4.26μm main absorption peak + 3.95μm reference channel); 2. Risk Assessment Thresholds (Table 2) Table 2

[0030] ③PM2.5 concentration c detection: 1. Anti-humidity sensor array - dual-channel redundant detection: Laser scattering sensor (main channel): Range: 0-1000 μg / m³ (resolution 1 μg / m³); Dynamic heating and dehumidification module (constant temperature at 60°C, humidity interference reduced by 83%); Beta ray sensor (calibration channel): Automatic monthly calibration to eliminate errors caused by differences in aerosol composition; 2. Risk Assessment Thresholds (Table 3) Table 3

[0031] Furthermore, the constructed environmental state simulation model is specifically as follows:

[0032] Wherein, η is the environmental parameter; a is the formaldehyde concentration, mg / m³; b is the CO2 concentration, mg / m³; c is the PM2.5 concentration, μg / m³; ln2.1 is the adjustment constant.

[0033] Furthermore, in step S4, the different evaluation criteria levels selected based on the actor category are as follows: If the number of infants and young children is ≥1, the standard level is defined as level 1, which corresponds to y=799.258 in the S3 step coordinate system; The number of infants and young children = 0, the number of elderly people ≥ 4, the standard level is defined as level 2, corresponding to y = 2399.258 in the S3 step coordinate system; The number of infants and young children = 0, 1≤the number of elderly people≤3, the standard level is defined as level 3, corresponding to y=6299.258 in the S3 step coordinate system; The number of infants and young children = 0, the number of elderly people = 0, and the standard level is defined as level four, which corresponds to y = 15999.258 in the S3 step coordinate system.

[0034] It should be noted that the solution of the present invention divides different environmental levels into 4 levels.

[0035] They are: Level 1: 0.08*1000*10-0.742=799.258; Level 2: 0.10*1200*20-0.742=2399.258; Level 3: 0.15*1400*30-0.742=6299.258; Level 4: 0.20*2000*40-0.742=15999.258; It should be noted that the above parameters are adaptively matched according to Tables 1, 2, and 3.

[0036] Of course, during specific use, users can make additional subdivisions or corrections based on local standards. After selecting the corresponding parameters according to the form, they can substitute them into the environmental state simulation model. The solution of the present invention only provides an exemplary example.

[0037] It is not difficult to understand that the first level 799.258, the second level 2399.258, the third level 6299.258 and the fourth level 15999.258 are all extreme range values.

[0038] Furthermore, the state determination model is specifically as follows:

[0039] Among them, δ is the state value; S1 is the first area of the environmental state simulation curve where the y value is greater than the evaluation standard level straight line; S m is the area of the mth block where the y value of the environmental state simulation curve is greater than the evaluation standard level straight line; S1' is the area of the first block where the y value of the environmental state simulation curve is less than the evaluation standard level straight line; S n ´ is the area of the nth block in the environmental state simulation curve where the y value is less than the evaluation standard level straight line.

[0040] It should be noted that if Figure 2 , which is a simulation schematic diagram of the environmental state simulation curve and the evaluation standard grade straight line provided by the present invention.

[0041] Specifically, when the state value δ is less than or equal to 1, it is defined that the environmental state detection meets the standard in the current state; otherwise, it is defined that the environmental state detection does not meet the standard.

[0042] Furthermore, in the actual operation process, after obtaining the environmental state simulation curve, in step S6, when obtaining the area S or area S', the environmental state simulation curve is evenly divided. If the environmental state simulation curve intersects with the evaluation standard level straight line at the initial endpoint or the final endpoint, a straight line perpendicular to the X-axis is drawn from the first and last endpoints of the environmental state simulation curve, and connected to the X-axis. The intersection of the X-axis, the environmental state simulation curve, and the straight line perpendicular to the X-axis is taken as the measurement area at the initial endpoint or the final endpoint, and is included in the state judgment model according to the standard. See Figure 2 .

[0043] In addition, in addition to the above solutions, the present invention can also adopt the following technical solutions when constructing the environmental state simulation model for reference and independent selection: 1. Data preprocessing module Concentration normalization: def normalize_params(a, b, c): # Normalized based on national standard limits (GB / T 18883-2022) a_norm = a / 0.08 # Formaldehyde limit 0.08 mg / m³ b_norm = b / 1793 # CO2 limit 1000ppm≈1793 mg / m³ c_norm = c / 75 # PM2.5 limit is 75 μg / m³ return a_norm, b_norm, c_norm Non-linear amplification processing (enhanced high concentration sensitivity):

[0044] 2. Dynamic Weight Allocation Algorithm Fuzzy logic controller (input: x, y, z): def calculate_weights(x, y, z): # Real-time priority judgment if max(x,y,z) > 2.5: # Emergency: Highest risk parameters dominate w = [0.6 if v==max(x,y,z) else 0.2 for v in (x,y,z)] else: # Normal distribution: Formaldehyde (0.5), CO2 (0.3), PM2.5 (0.2) w = [0.5, 0.3, 0.2] return w 3. Synergy Effect Correction Factor Multi-pollution coupling enhancement factor:

[0045] (When multiple pollutants coexist, risks are nonlinearly superimposed) 4. Comprehensive status value calculation

[0046] 5. Health Status Classification and Response (Table 4) Table 4

[0047] Example Description Scenario simulation: Input parameters: Formaldehyde concentration a=0.12 mg / m³ → a_norm=1.5 → x=1.5^1.8≈2.4; CO2 concentration b=2200 mg / m³ → b_norm≈1.23 → y=1.23^1.2≈1.3; PM2.5 concentration c=110 μg / m³ → c_norm≈1.47 → z=1.47^1.5≈1.8; Weight distribution: max(2.4,1.3,1.8)=2.4 → w=[0.6, 0.2, 0.2]; Synergy coefficient: K syn =1+0.2*tanh(0.5×2.4×1.3+0.3×2.4×1.8+0.2×1.3×1.8)=1.27; Comprehensive status value: S=1.27×(0.6×2.4+0.2×1.3+0.2×1.8)=1.27×2.0=2.54; Response measures: Trigger level 4 response, activate sound and light alarms and recommend evacuation.

[0048] In order to verify the beneficial effects of the present invention, the following simulation experiment is performed: 1. Purpose of the Test Verify whether the intelligent indoor health risk assessment method based on dynamic multi-parameter feedback can accurately evaluate the indoor environmental status, and its excellent technical effect in solving the shortcomings of existing indoor environmental health monitoring technology.

[0049] 2. Test environment and equipment Test environment: Select different types of indoor spaces for testing, including home living rooms, offices, kindergarten classrooms, etc., to simulate different actual usage scenarios.

[0050] Test equipment: A series of sensors deployed indoors include laser spectrum sensors (used to detect formaldehyde concentration), NDIR (non-dispersive infrared) sensors (used to detect CO2 concentration), and moisture-resistant sensor arrays (used to detect PM2.5 concentration).

[0051] The data acquisition system is used to record various environmental health data obtained by sensors in real time.

[0052] Model props used to simulate different behavioral categories (such as mannequins simulating infants, young children, and the elderly).

[0053] 3. Test steps In each test environment, data collection and processing were performed according to the steps of the intelligent indoor health risk assessment method.

[0054] 4. Test data table

[0055] The present invention provides an intelligent indoor health risk assessment method based on dynamic multi-parameter feedback, which has the following beneficial effects: Solving the problem of single parameters: Traditional systems only monitor environmental parameters such as PM2.5 and CO2, ignoring the interaction between human physiological state and the environment. This method uses a series of sensors deployed indoors to obtain real-time environmental health data at the time of detection, including formaldehyde concentration, CO2 concentration, PM2.5 concentration, etc., thus solving the problem of single parameters.

[0056] Solve the problem of static threshold determination: After collecting environmental parameters, using a fixed threshold to trigger an alert cannot adapt to individual differences. This method uses a constructed environmental state simulation model to obtain real-time environmental state parameters at the detection time point, and selects the corresponding evaluation standard level in real time based on the type of actor in the current environment, thus solving the static threshold determination problem.

[0057] This method solves the data silo problem: Environmental and behavioral data are processed independently, lacking multimodal fusion analysis. This method evenly divides the environmental state simulation curve by the assessment standard grade line. It then obtains the area S where the y value of the environmental state simulation curve exceeds the assessment standard grade line, and the area S' where the y value of the environmental state simulation curve is less than the assessment standard grade line. A state determination model is then constructed, using S and S' as real-time inputs to obtain state values. This real-time state value is then used to determine whether the indoor environmental state meets the standards, thus solving the data silo problem.

[0058] Provide more accurate health risk assessment: This method dynamically integrates environmental parameters and behavioral data, and combines them with adaptive machine learning models to achieve real-time health risk assessment, which can provide more accurate health risk assessment.

[0059] Adaptability to individual differences: This method selects different levels of evaluation criteria based on the type of actor, which can adapt to individual differences.

[0060] Multimodal fusion analysis: This method evenly divides the environmental state simulation curve by the evaluation standard grade line, obtains the area S where the y value of the environmental state simulation curve is greater than the evaluation standard grade line, and obtains the area S' where the y value of the environmental state simulation curve is less than the evaluation standard grade line. A state judgment model is constructed, S and S' are input in real time, and the state value is obtained in real time. Based on the real-time obtained state value, it is determined whether the indoor environmental state meets the standard, thus realizing multimodal fusion analysis.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent indoor health risk assessment method based on dynamic multi-parameter feedback, characterized by: The steps include: S1: A series of sensors placed indoors are used to obtain real-time environmental health data at the detection time point; S2: Obtain the environmental state parameters at the detection time point in real time based on the constructed environmental state simulation model; S3: Using the environmental state parameters obtained in step S2 as the ordinate and the detection point time in the chronological order as the abscissa, the positions of the reference points in the coordinate system are obtained, and smooth curves are connected to connect the reference points to obtain an environmental state simulation curve; S4: Select the corresponding evaluation standard level in real time based on the category of the actor in the current environment; S5: Matching the evaluation standard level obtained in step S4 to the coordinate system in step S3; S6: In the coordinate system, the environmental state simulation curve is evenly divided by the evaluation standard level straight line, and the area S of the environmental state simulation curve where the y value is greater than the evaluation standard level straight line is obtained, and the area S' of the environmental state simulation curve where the y value is less than the evaluation standard level straight line is obtained; S7: Construct a state determination model, input S and S' in real time, obtain state values in real time, and determine whether the indoor environmental state meets the standard based on the state values obtained in real time.

2. The intelligent indoor health risk assessment method based on dynamic multi-parameter feedback according to claim 1 is characterized in that: The environmental health data obtained in step S1 specifically include: According to the formaldehyde concentration a detected by the laser spectrum sensor, mg / m³; CO2 concentration b, mg / m³, detected by NDIR (non-dispersive infrared) sensor; PM2.5 concentration c, μg / m³, detected by the moisture-resistant sensor array.

3. The intelligent indoor health risk assessment method based on dynamic multi-parameter feedback according to claim 2 is characterized in that: The environmental state simulation model constructed is specifically: ； Wherein, η is the environmental parameter; a is the formaldehyde concentration, mg / m³; b is the CO2 concentration, mg / m³; c is the PM2.5 concentration, μg / m³; ln2.1 is the adjustment constant.

4. The intelligent indoor health risk assessment method based on dynamic multi-parameter feedback according to claim 3 is characterized in that: In step S4, the different evaluation criteria levels selected based on the actor type are as follows: If the number of infants and young children is ≥1, the standard level is defined as level 1, which corresponds to y=799.258 in the S3 step coordinate system; The number of infants and young children = 0, the number of elderly people ≥ 4, the standard level is defined as level 2, corresponding to y = 2399.258 in the S3 step coordinate system; The number of infants and young children = 0, 1≤the number of elderly people≤3, the standard level is defined as level 3, corresponding to y=6299.258 in the S3 step coordinate system; The number of infants and young children = 0, the number of elderly people = 0, and the standard level is defined as level four, which corresponds to y = 15999.258 in the S3 step coordinate system.

5. The intelligent indoor health risk assessment method based on dynamic multi-parameter feedback according to claim 4 is characterized in that: The state determination model is specifically: ； Among them, δ is the state value; S1 is the first area of the environmental state simulation curve where the y value is greater than the evaluation standard level straight line; S m is the area of the mth block where the y value of the environmental state simulation curve is greater than the evaluation standard level straight line; S1' is the area of the first block where the y value of the environmental state simulation curve is less than the evaluation standard level straight line; S n ´ is the area of the nth block in the environmental state simulation curve where the y value is less than the evaluation standard level straight line.

6. The intelligent indoor health risk assessment method based on dynamic multi-parameter feedback according to claim 5 is characterized by: When the state value δ is less than or equal to 1, it is defined that the environmental state detection in the current state meets the standard; otherwise, it is defined that the environmental state detection does not meet the standard.

7. The intelligent indoor health risk assessment method based on dynamic multi-parameter feedback according to claim 6, characterized in that: In step S6, when obtaining area S or area S', the environmental state simulation curve is evenly divided. If the environmental state simulation curve intersects with the evaluation standard level straight line at the initial endpoint or the end endpoint, straight lines perpendicular to the X-axis are drawn from the first and last endpoints of the environmental state simulation curve respectively and connected to the X-axis. The intersection of the X-axis, the environmental state simulation curve, and the straight line perpendicular to the X-axis is taken as the measured area at the initial endpoint or the end endpoint, and is included in the state judgment model according to the standard.

Images