Integrated disinfection monitoring management system based on quantitative risk assessment

Abstract

The invention provides an integrated disinfection monitoring management system based on quantitative risk assessment, and belongs to the technical field of disinfection monitoring. Comprising an environment and behavior parameter acquisition module, a bacteria breeding risk analysis module and a disinfection quality analysis module, the environment and behavior parameter acquisition module is used for constructing a first data set, a second data set and a third data set, and constructing a prediction risk model by using a convolutional neural network; and based on the first data set, the second data set and the third data set, respectively constructing an environment bacterium breeding coefficient, a bacterium propagation coefficient and a behavior bacterium breeding coefficient of the ith area, combining the environment bacterium breeding coefficient and the behavior bacterium breeding coefficient of the ith area to construct a comprehensive disinfection behavior coefficient, and performing evaluation to generate a corresponding strategy. In-station bacteria monitoring is achieved through multi-dimensional linkage, and a proper disinfection scheme is adopted according to the bacterium breeding degree.

Description

Technical Field

[0001] The present invention relates to the technical field of disinfection monitoring, and in particular to an integrated disinfection monitoring and management system based on quantitative risk assessment. Background Art

[0002] Public places, such as stations, have become high-risk areas for bacterial growth and spread due to their dense crowds and frequent personnel flow. With the increasing demand for public health and safety, disinfection management in places such as stations has become particularly important. With the rapid development of intelligent technology, disinfection monitoring in public places such as stations has gradually become automated and intelligent. With the help of video surveillance, sensors and big data analysis, real-time collection and monitoring of environmental parameters and personnel behavior can be achieved.

[0003] Currently, disinfection monitoring in stations mostly uses a single sensor or decentralized monitoring methods. By monitoring the flow of people inside the station, detecting the body temperature of people, and disinfecting fixed locations in the station, the station will be disinfected according to the preset disinfection plan. However, this method cannot change the disinfection method according to changes in the flow of people. For example, during peak holiday periods, the flow of people in the station will increase, and people will sneeze in the station, carrying their own bacteria, which will increase the amount of pathogens in the station. If the original plan is followed, the bacteria cannot be suppressed. Conversely, when the flow of people is small, the disinfectant water will be wasted if the original plan is still followed.

[0004] In summary, the existing disinfection method for public areas adopts static disinfection, which cannot change the disinfection method according to changes in the flow of people. It can no longer meet the actual use and this problem needs to be solved urgently. Summary of the Invention

[0005] In order to remedy the above deficiencies, the present invention provides an integrated disinfection monitoring and management system based on quantitative risk assessment, which overcomes the above technical problems or at least partially solves the above problems.

[0006] The present invention is achieved in that:

[0007] The present invention provides an integrated disinfection monitoring and management system based on quantitative risk assessment, including an environmental and behavioral parameter acquisition module, a bacterial growth risk analysis module, and a disinfection quality analysis module;

[0008] The environmental and behavioral parameter acquisition module is used to divide the station into several disinfection monitoring areas, conduct real-time video capture and data acquisition of public transportation passenger flow and the distance between people, and continuously monitor the surface humidity of public transportation handrails using humidity sensors. Furthermore, the dynamic behavioral characteristics of people in the station are collected using camera equipment to construct the first, second, and third data sets respectively, where the dynamic behavioral characteristics include walking speed and the number of sneezes.

[0009] The bacterial growth risk analysis module is used to construct a prediction risk model using a convolutional neural network, and input the first data set, the second data set, and the third data set into the prediction risk model for analysis, output the bacterial growth prediction risk result for the disinfection detection area, and construct the i-th regional environmental bacterial growth coefficient E based on the first data set, the second data set, and the third data set. i , bacterial transmission coefficient K i and behavioral bacterial growth coefficient B i .

[0010] The disinfection quality analysis module is used to receive the output of the bacterial growth prediction risk result of the disinfection detection area, and combine it with the bacterial growth coefficient E of the i-th area environment i and behavioral bacterial growth coefficient B i , construct comprehensive disinfection behavior coefficient D total , and evaluate and generate corresponding strategies.

[0011] In a preferred solution, the environment and behavior parameter collection module includes an area division unit, an environment bacteria collection unit, a personnel behavior breeding bacteria collection unit, and a bacteria transmission collection unit;

[0012] The area division unit is used to divide the station into several disinfection monitoring areas, establish three-dimensional coordinates, and obtain the coordinates x, y, z of the i-th area;

[0013] The environmental bacteria collection unit is used to capture the flow of people on public transportation through a multi-angle camera device set in the disinfection detection area of ​​the i-th area in the station, and obtain the flow of people in the i-th area P i , and based on the camera equipment to collect the distance between people on public transportation, obtain the distance between people in the i-th area D i , the humidity change on the handrail surface caused by the jth person in the i-th area contacting the public handrail is collected, and the humidity value H generated by the jth person in the i-th area contacting the public handrail on the handrail surface is obtained i,j , construct the first data set;

[0014] The first data set also includes the dust area G in the i-th region. 1,i , solid waste type G 2,i and the number of waste collection bins in the i-th area B i Based on the camera equipment, the ground image of the i-th area is captured, and the image recognition algorithm is combined to perform image dust texture recognition to obtain the ground dust area G of the i-th area. 1,i; and based on the camera equipment, take an image of the i-th area, and identify the waste texture and waste collection box texture in the image to obtain the solid waste type G of the i-th area 2,i and the number of waste collection boxes B i , where solid waste types include disposable packaging bags, beverage bottles and toilet paper;

[0015] The bacterial transmission collection unit is used to install temperature sensors at multiple locations in the i-th area of ​​the station, detect the temperature through the temperature sensors, and take the average to obtain the local temperature T of the i-th area. i By distributing wind speed sensors at different locations in the i-th region and analyzing the convection path, the air circulation rate V of the i-th region is derived. i , and construct the second data set;

[0016] The personnel behavior breeding bacteria collection unit is used to set a multi-angle camera device in the i-th area, detect the distance walked by the j-th person according to the three-dimensional coordinate system, and use a timer to detect the walking time, and collect the speed of the j-th person in the i-th area to obtain the walking speed v of the j-th person in the i-th area. i,j By using a camera to capture images of people in the i-th area and identifying the motion features of people in the images, combined with the audio collection of people by the camera, the number of sneezes of the j-th person in the i-th area is obtained. i,j , construct the third data set;

[0017] The third data set also includes the mask wearing rate of people in the i-th area of ​​the station. Based on the camera equipment taking images of the faces of people in the i-th area from multiple angles and identifying the mask texture in the image, the number of people wearing masks in the i-th area is collected. Combined with the total number of people in the i-th area, the mask wearing rate m of people in the i-th area is obtained by ratio calculation. i .

[0018] In a preferred embodiment, the bacterial growth risk analysis module includes a model building unit, a recording unit, an extraction unit, and an evaluation unit;

[0019] The model construction unit is used to use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with the first data set and the second data set, and use the trained initial convolutional neural network model as a disinfection test evaluation model, and use the intermediate layer output of the disinfection test evaluation model as a feature vector to identify the bacterial breeding information of the i-th area in the station, and train and test the disinfection test evaluation model through the obtained feature information, and use the trained disinfection test evaluation model as data to run prediction, and respectively construct the environmental bacterial breeding coefficient E i , domain bacterial transmission coefficient Ki and behavioral bacterial growth coefficient B i and recorded by the recording unit.

[0020] In a preferred embodiment, the environmental bacterial growth coefficient is obtained as follows:

[0021] The extraction unit includes a first extraction subunit and a second extraction subunit;

[0022] The first extraction subunit is used to extract the pedestrian flow P in the i-th area based on the first data set. i 、Interval between people D i , the humidity value H generated by the jth person in the i-th area contacting the public handrail i,j And the dust area G in the i-th region 1,i , solid waste type G 2,i and the number of waste collection bins in the i-th area B i , after dimensionless processing, the bacterial growth coefficient E of the i-th region environment is calculated i .

[0023] In a preferred embodiment, the evaluation unit includes a first evaluation subunit, a second evaluation subunit, and a third evaluation subunit, which are used to preset an environmental bacteria growth threshold value A;

[0024] The environmental bacteria growth threshold value A is compared with the environmental bacteria growth coefficient E to generate a first evaluation instruction, including:

[0025] When E>A, it indicates that the amount of bacteria in the environment of the i-th area in the station is abnormal, and the first strategy is generated, including: increasing the number of waste collection boxes in the i-th area by 10%-15%, increasing the disinfection frequency of the i-th area in the station by 5%-8%, cleaning the floor of the i-th area, and increasing the disinfection frequency of public handrails by 5 times / three hours to 7 times / three hours, evacuating people from the i-th area, and generating an alarm unit when the flow of people in the i-th area reaches 1.2 times the preset number of people;

[0026] When E≤A, it means that the amount of bacteria growing in the environment of the i-th area in the station is normal. The currently set disinfection plan should be implemented and monitoring should continue.

[0027] In a preferred solution, the alarm unit is used to extract the local temperature T of the i-th region from the second data set. i and the air circulation rate V in the i-th area i , and combined with the flow of people in the i-th area P i , after dimensionless processing, the bacterial transmission coefficient K of the i-th region is obtained by calculation i ;

[0028] The second evaluation subunit is used to preset a bacteria transmission threshold value Y;

[0029] And the bacterial spread Y is combined with the bacterial spread coefficient K in the i-th region i Perform a comparison and generate a second evaluation instruction, including:

[0030] When K i When the value is greater than Y, it indicates that the initial velocity of bacterial spread in the i-th area is abnormal, generating the first danger level. Based on the first danger level, the second strategy is generated, including: evacuating the flow of people in the current area, reducing the number of people by 20%-30% to keep it within a safe and controllable range; adding 5-7 exhaust devices to speed up the air flow in the area, increasing the air flow rate by 30%-50%; increasing the number of disinfections in the area by 70%-80%; transmitting the danger level to the backend and initiating the emergency plan;

[0031] When K i When ≤Y, it means that the initial speed of bacterial transmission in the i-th area is abnormal, but the danger level is lower than the first danger level, and the second danger level is generated. Based on the second danger level, the third strategy is generated, including: improving the ventilation effect of the area by 10%-20%, evacuating the flow of people, increasing the concentration of disinfectant by 30%-40%, fully disinfecting the area, marking the area as a potential risk area, and continuously monitoring it.

[0032] In a preferred solution, the second extraction subunit is used to extract the walking speed v of the jth person in the i-th area from the third data set. i,j , the number of times the jth person in the i-th area sneezes i,j and the mask wearing rate m of people in the i-th area i , after dimensionless processing, the bacterial breeding coefficient B of the i-th region is obtained by calculation i .

[0033] In a preferred embodiment, the third evaluation subunit is used to preset a behavior-based bacteria breeding threshold W;

[0034] By collecting and analyzing historical behavior data and bacterial detection results at the station, and using statistical methods, we can obtain the behavioral bacterial breeding threshold W.

[0035] The behavioral bacterial growth threshold W is combined with the behavioral bacterial growth coefficient B in the i-th region. i Perform a comparison and generate a third evaluation instruction, including:

[0036] When B iWhen the value is greater than W, it indicates that the behavior of people in the i-th area is abnormal, resulting in the distance between people being between 0.3m and 0.7m. The fourth strategy is generated, including: improving the ventilation efficiency of the area by more than 30%, triggering a behavioral guidance mechanism based on pedestrian density, maintaining an average distance of more than 0.9m per person through broadcasting and station patrols, spraying disinfectant inside the station, increasing the disinfection frequency by 5%-7%, and having station staff distribute masks to passengers to increase the mask wearing rate to 80%-90%.

[0037] When B i When ≤W, it means that the behavior of people in the i-th area is normal and the flow of people in the area is also within the controllable range of 50%-80%. Continue to execute and monitor according to the pre-planned plan.

[0038] In a preferred embodiment, the disinfection quality analysis module includes a correlation unit and an optimization unit;

[0039] The associated unit is used to calculate the bacterial growth coefficient E of the i-th area environment. i and the bacterial breeding coefficient B of the i-th region i The comprehensive disinfection behavior coefficient D is obtained by calculation after dimensionless processing. total .

[0040] In a preferred embodiment, the optimization unit is used to preset a comprehensive disinfection behavior threshold L;

[0041] The comprehensive disinfection behavior threshold L includes L1 and L2, L1 represents the maximum value of the comprehensive disinfection behavior threshold, L2 represents the minimum value of the comprehensive disinfection behavior threshold, and satisfies L1>L2, and the comprehensive disinfection behavior threshold L is combined with the comprehensive disinfection behavior coefficient D total Perform a comparison and generate a fourth evaluation instruction, including:

[0042] When D total When the level is higher than L1, it indicates that bacteria are growing abnormally in the station, generating the first abnormality level. Based on the first abnormality level, the first optimization strategy is generated, including: increasing the disinfection frequency in the station by 25%-40%, increasing the ventilation equipment in the station to increase the air circulation rate in the station by 50%-60%, and having the station staff maintain the flow of people in each area of ​​the station. If the flow of people in each area exceeds the original set number of people by 20%, the people will be evacuated to other areas and masks will be distributed to increase the mask wearing rate of people in the station to more than 90%;

[0043] When L2≤D totalWhen the value is ≤L1, it indicates that the bacterial growth in the station is abnormal, but lower than the first abnormality level, and a second abnormality level is generated. Based on the second abnormality level, a second optimization strategy is generated, including: increasing the disinfection frequency in the station by 10%-15%, and increasing the disinfection frequency of high-contact areas in the station, including public handrails and waiting seats, to 3-5 times every three hours;

[0044] When D total When it is less than L2, it means that the hygiene inside the station is qualified, the original disinfection plan is maintained, and it is continuously monitored through the background.

[0045] The integrated disinfection monitoring and management system based on quantitative risk assessment provided by the present invention has the following beneficial effects:

[0046] 1. The environmental and behavioral parameter collection module uses real-time video technology and humidity sensors to accurately collect passenger flow, personal spacing, handrail humidity, and dynamic behavioral characteristics in the disinfection monitoring areas designated within the station. This allows for comprehensive quantification of environmental and behavioral bacterial growth factors, improving the scientific nature and real-time nature of monitoring data. Furthermore, the bacterial growth risk analysis module introduces a convolutional neural network, utilizing multidimensional dataset input for deep learning prediction. This effectively captures the impact of complex environments and behavioral patterns on bacterial growth, avoiding misjudgments and missed judgments caused by traditional static thresholds, and improving the accuracy of risk prediction and dynamic response capabilities. The collected environmental bacterial growth coefficient, bacterial transmission coefficient, and behavioral bacterial growth coefficient are used to construct a comprehensive disinfection behavior coefficient. Combined with dimensionless processing technology, this module achieves a multi-level, comprehensive quantitative assessment of bacterial risks, facilitating the implementation of differentiated disinfection strategies for different areas and situations.

[0047] 2. When the number of people in the i-th area of ​​the station is greater than the pre-designed number, the bacterial transmission coefficient of the i-th area will be expanded. By calculating the bacterial transmission coefficient, the bacterial transmission speed of the area can be known in time, and corresponding strategies can be taken to avoid dangerous situations.

[0048] 3. This system forms a closed loop from data collection, risk prediction to optimization strategy output, combining real-time monitoring with dynamic regulation to ensure the scientific nature and effectiveness of disinfection measures in stations, reduce the risk of bacterial transmission, and improve public health safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1It is a system block diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0052] Example 1, reference Figure 1 , the present invention provides a technical solution: an integrated disinfection monitoring and management system based on quantitative risk assessment, including an environmental and behavioral parameter acquisition module, a bacterial growth risk analysis module and a disinfection quality analysis module;

[0053] The environmental and behavioral parameter acquisition module is used to divide the station into several disinfection monitoring areas, conduct real-time video capture and data acquisition of public transportation passenger flow and the distance between people, and continuously monitor the surface humidity of public transportation handrails using humidity sensors. Furthermore, the dynamic behavioral characteristics of people in the station are collected using camera equipment to construct the first, second, and third data sets respectively, where the dynamic behavioral characteristics include walking speed and the number of sneezes.

[0054] The bacterial growth risk analysis module is used to construct a prediction risk model using a convolutional neural network, and input the first data set, the second data set, and the third data set into the prediction risk model for analysis, output the bacterial growth prediction risk result for the disinfection detection area, and construct the i-th regional environmental bacterial growth coefficient E based on the first data set, the second data set, and the third data set. i , bacterial transmission coefficient K i and behavioral bacterial growth coefficient B i .

[0055] The disinfection quality analysis module is used to receive the output of the bacterial growth prediction risk result of the disinfection detection area, and combine it with the bacterial growth coefficient E of the i-th area environment i and behavioral bacterial growth coefficient B i , construct comprehensive disinfection behavior coefficient D total , and evaluate and generate corresponding strategies.

[0056] In this embodiment, the environmental and behavioral parameter collection module accurately collects passenger flow, personal spacing, handrail humidity, and dynamic behavioral characteristics (such as walking speed and number of sneezes) by combining real-time video technology and humidity sensors in the disinfection monitoring areas designated within the station. This achieves comprehensive quantification of environmental and behavioral factors that influence bacterial growth, improving the scientific nature and real-time nature of the monitoring data. In addition, the bacterial growth risk analysis module introduces a convolutional neural network and uses multidimensional data set input for deep learning prediction, effectively capturing the impact of complex environments and behavioral patterns on bacterial growth, avoiding misjudgments and missed judgments caused by traditional static thresholds, and improving the accuracy of risk prediction and dynamic response capabilities.

[0057] Based on the collected environmental bacterial growth coefficient, bacterial transmission coefficient and behavioral bacterial growth coefficient, the system constructs a comprehensive disinfection behavior coefficient. Combined with dimensionless processing technology, it realizes a multi-level and comprehensive quantitative assessment of bacterial risks, making it convenient to implement differentiated disinfection strategies for different areas and situations.

[0058] This system forms a closed loop from data collection, risk prediction to optimization strategy output, combining real-time monitoring with dynamic regulation to ensure the scientific nature and effectiveness of disinfection measures in stations, reduce the risk of bacterial transmission, and improve public health safety.

[0059] Example 2: This example is an explanation of Example 1. Please refer to Figure 1 ,Specifically, the environment and behavior parameter collection module includes an area division unit, an ,environmental bacteria collection unit, a personnel behavior breeding bacteria ,collection unit, and a bacteria transmission collection unit;

[0060] The area division unit is used to divide the station into several disinfection monitoring areas, establish three-dimensional coordinates, and obtain the coordinates x, y, z of the i-th area;

[0061] The environmental bacteria collection unit is used to capture the flow of people on public transportation through a multi-angle camera device set in the disinfection detection area of ​​the i-th area in the station, and obtain the flow of people in the i-th area P i , and based on the camera equipment to collect the distance between people on public transportation, obtain the distance between people in the i-th area D i , the humidity change on the handrail surface caused by the jth person in the i-th area contacting the public handrail is collected, and the humidity value H generated by the jth person in the i-th area contacting the public handrail on the handrail surface is obtained i,j , construct the first data set;

[0062] The first data set also includes the dust area G in the i-th region. 1,i , solid waste type G 2,i and the number of waste collection boxes in the i-th area B iBased on the camera equipment, the ground image of the i-th area is captured, and the image recognition algorithm is combined to perform image dust texture recognition to obtain the ground dust area G of the i-th area. 1,i ; and based on the camera equipment, take an image of the i-th area, and identify the waste texture and waste collection box texture in the image to obtain the solid waste type G of the i-th area 2,i and the number of waste collection boxes B i , where solid waste types include disposable packaging bags, beverage bottles and toilet paper;

[0063] The bacterial transmission collection unit is used to install temperature sensors at multiple locations in the i-th area of ​​the station, detect the temperature through the temperature sensors, and take the average to obtain the local temperature T of the i-th area. i By distributing wind speed sensors at different locations in the i-th region and analyzing the convection path, the air circulation rate V of the i-th region is derived. i , and construct the second data set;

[0064] The personnel behavior breeding bacteria collection unit is used to set a multi-angle camera device in the i-th area, detect the distance walked by the j-th person according to the three-dimensional coordinate system, and use a timer to detect the walking time, and collect the speed of the j-th person in the i-th area to obtain the walking speed v of the j-th person in the i-th area. i,j By using a camera to capture images of people in the i-th area and identifying the motion features of people in the images, combined with the audio collection of people by the camera, the number of sneezes of the j-th person in the i-th area is obtained. i,j , construct the third data set;

[0065] The third data set also includes the mask wearing rate of people in the i-th area of ​​the station. Based on the camera equipment taking images of the faces of people in the i-th area from multiple angles and identifying the mask texture in the image, the number of people wearing masks in the i-th area is collected. Combined with the total number of people in the i-th area, the mask wearing rate m of people in the i-th area is obtained by ratio calculation. i .

[0066] In this embodiment, the three-dimensional coordinate division of the station space is performed through the area division unit, which can accurately define the location and scope of each disinfection monitoring area, provide a spatial benchmark for subsequent data collection, analysis and risk control, and realize the spatial digitization and refinement of disinfection management. The environmental bacteria collection unit not only collects traditional parameters such as pedestrian flow and personal spacing, but also combines with humidity sensors to collect changes in contact humidity on the surface of public handrails, constructing a first data set with a higher degree of biological risk relevance, improving the monitoring accuracy of potential bacterial breeding sources, and obtaining dust floor area, solid waste types and the number of waste collection boxes through image texture recognition algorithms, to achieve objective judgment of the ground environmental sanitation status, assist in constructing regional sanitation load indicators, and provide a quantitative basis for environmental cleaning scheduling.

[0067] The bacteria transmission collection unit avoids data distortion caused by single-point collection by deploying temperature and wind speed sensors at multiple points in the area, realizing dynamic assessment of air convection paths and air circulation rates, providing key input variables for the bacteria transmission model, and improving the real-time analysis capability of spatial air safety. The human behavior breeding bacteria collection unit combines video and time acquisition technology to accurately calculate individual walking speeds, judge the intensity of human gathering and movement behavior, and simultaneously analyze sneezing behavior through joint image and audio recognition to further capture potential high-risk individual behaviors and provide high-credibility data support for behavioral risk modeling.

[0068] Example 3, this example is the explanation in Example 1, please refer to Figure 1 ,Specifically, the bacterial growth risk analysis module includes a model building unit, a ,recording unit, an extraction unit and an evaluation unit;

[0069] The model construction unit is used to use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with the first data set and the second data set, and use the trained initial convolutional neural network model as a disinfection test evaluation model, and use the intermediate layer output of the disinfection test evaluation model as a feature vector to identify the bacterial breeding information of the i-th area in the station, and train and test the disinfection test evaluation model through the obtained feature information, and use the trained disinfection test evaluation model as data to run prediction, and respectively construct the environmental bacterial breeding coefficient E i , domain bacterial transmission coefficient K i and behavioral bacterial growth coefficient B i and recorded by the recording unit.

[0070] In this embodiment, the model construction unit uses a convolutional neural network (CNN) to conduct in-depth training on the collected multi-dimensional environmental and behavioral data, which not only enhances the model's ability to recognize the complex interaction patterns between high-dimensional parameters, but also greatly improves the accuracy and robustness of bacterial breeding risk prediction. The training data set is constructed using key indicators such as pedestrian flow, spacing, humidity, and air circulation rate in multiple monitoring areas, so that the model has the ability to adapt to multiple scenarios and time periods, thereby improving the promotion and applicability of the disinfection test evaluation model in real station environments.

[0071] By using the output of the intermediate layer of the convolutional neural network as the feature vector, not only can deep semantic information be extracted within the model, but the bacterial growth characteristics of specific areas can also be identified more accurately, optimizing subsequent evaluation and prediction performance. The system can continuously optimize the evaluation model based on the acquired intermediate layer feature information, realize a closed-loop mechanism of training and evaluation, ensure that the model continues to self-correct and improve during operation, and enhance its risk perception and response capabilities in a dynamically changing environment. Through the disinfection test evaluation model after training, the environmental bacterial growth coefficient, bacterial transmission coefficient and behavioral bacterial growth coefficient are quantified and output respectively, making the risk assessment not only operational, but also having clear physical meaning and interpretation capabilities, facilitating the precise implementation of subsequent management and intervention measures. All training, testing and prediction results are structured and stored by the recording unit, providing a data basis for model parameter tuning, strategy effect analysis and event tracing, and further enhancing the intelligence and maintainability of the system.

[0072] Example 4: This example is an explanation of Example 1. Please refer to Figure 1 Specifically, the environmental bacterial growth coefficient is obtained as follows:

[0073] The extraction unit includes a first extraction subunit and a second extraction subunit;

[0074] The first extraction subunit is used to extract the pedestrian flow P in the i-th area based on the first data set. i 、Interval between people D i , the humidity value H generated by the jth person in the i-th area contacting the public handrail i,j And the dust area G in the i-th region 1,i , solid waste type G 2,i and the number of waste collection boxes in the i-th area B i , after dimensionless processing, the average humidity value is obtained Where q i is the total number of people in the ith area, and the bacterial growth coefficient E in the ith area is calculated by the following formula i ;

[0075]

[0076] Where α1, α2, α3, α4 and α5 are weight coefficients.

[0077] Set α1 to 0.02, α2 to 0.5, α3 to 0.3, α4 to 0.05 and α5 to 0.1. The weight coefficients here are obtained by inputting data into the training model;

[0078] The following is the bacterial growth coefficient E of the i-th area environment i The example table is shown in Table 1:

[0079]

[0080] In this embodiment, the first extraction subunit systematically extracts core environmental parameters directly related to bacterial growth from the first data set, including pedestrian flow, personal spacing, handrail surface humidity, ground dust area, solid waste types, and the number of waste collection bins. This ensures that the model input data is comprehensive and multidimensional, effectively improving the accuracy of bacterial growth analysis. The various original environmental indicators are dimensionlessly converted to solve the modeling interference problem caused by inconsistent parameter units and large differences in orders of magnitude. This makes the various feature items comparable in the formula, which helps to improve the stability and scalability of the model.

[0081] An adjustable weight coefficient is set in the calculation formula to scientifically assign weights to the degree of influence of different parameters on bacterial growth. It can be adjusted according to different scenarios or seasonal characteristics to improve the adaptability and prediction flexibility of the model. Taking into account the humidity change caused by the interaction between the jth person and the handrail in the ith area as one of the influencing factors, it can identify potential high-contact and high-risk areas, assist in analyzing the causes of bacterial growth from the micro-behavioral level, and increase the model recognition accuracy.

[0082] Example 5, this example is the explanation in Example 1, please refer to Figure 1 Specifically, the evaluation unit includes a first evaluation subunit, a second evaluation subunit and a third evaluation subunit, which are used to preset an environmental bacteria growth threshold value A;

[0083] Through statistical analysis of historical station environmental data and corresponding bacterial load level samples, the empirical value obtained after fitting with the machine learning algorithm is output as the environmental bacterial growth threshold A;

[0084] The environmental bacteria growth threshold value A is compared with the environmental bacteria growth coefficient E to generate a first evaluation instruction, including:

[0085] When E>A, it indicates that the amount of bacteria in the environment of the i-th area in the station is abnormal, and the first strategy is generated, including: increasing the number of waste collection boxes in the i-th area by 10%-15%, increasing the disinfection frequency of the i-th area in the station by 5%-8%, cleaning the floor of the i-th area, and increasing the disinfection frequency of public handrails by 5 times / three hours to 7 times / three hours, evacuating people from the i-th area, and generating an alarm unit when the flow of people in the i-th area reaches 1.2 times the preset number of people;

[0086] When E≤A, it means that the amount of bacteria growing in the environment of the i-th area in the station is normal. The currently set disinfection plan should be implemented and monitoring should continue.

[0087] The following is an example table comparing the environmental bacterial growth threshold A and the environmental bacterial growth coefficient E, as shown in Table 2:

[0088]

[0089] In this embodiment, by using historical station environmental data and bacterial load level samples to construct a machine learning model, the fitted environmental bacterial growth threshold A has the characteristics of data-driven and experience-based, avoiding the limitations of traditional reliance on expert subjective judgment or manually set fixed thresholds, making the evaluation system more objective and verifiable. By comparing the environmental bacterial growth coefficient calculated in real time with the threshold A, it is possible to quickly identify whether there is abnormal bacterial growth in the current area, provide a clear basis for subsequent decision-making, and improve the system's judgment efficiency and response speed. When the environmental bacterial growth coefficient exceeds the threshold, a multi-level refined response strategy is automatically triggered, such as increasing the number of waste collection bins, increasing the frequency of disinfection and the number of times public handrails are cleaned, and combined with intelligent early warning of pedestrian density, it effectively blocks the transmission chain and improves the emergency management effect.

[0090] When the bacterial growth level is within the normal range, the system can maintain the current disinfection rhythm and continue monitoring to avoid waste of resources; in the event of an abnormality, it will quickly switch to an enhanced prevention and control strategy to form a closed-loop control, improve resource allocation efficiency and public health protection capabilities. Once the environmental bacterial growth coefficient and the flow of people exceed the set upper limit simultaneously, the evaluation unit can link the alarm module to prompt the operator to intervene in time, realizing an integrated intelligent prevention and control mechanism of "discovery-response-control", and improving the real-time and accuracy of public health management.

[0091] Example 6, this example is the explanation in Example 1, please refer to Figure 1 Specifically, the alarm unit is used to extract the local temperature T of the i-th region from the second data set. i and the air circulation rate V in the i-th area i , and combined with the flow of people in the i-th area P iAfter dimensionless processing, the bacterial transmission coefficient K in the i-th region is calculated by the following formula: i ;

[0092]

[0093] The following is the bacterial transmission coefficient K in the i-th region i The sample table is shown in Table 3:

[0094]

[0095] The second evaluation subunit is used to preset a bacteria transmission threshold value Y;

[0096] By building a risk prediction model, the bacterial transmission threshold Y is obtained based on the classification boundary of the transmission coefficient as a dynamically adjusted warning threshold.

[0097] The bacterial transmission threshold Y and the bacterial transmission coefficient K in the i-th region are i Perform a comparison and generate a second evaluation instruction, including:

[0098] When K i When the value is greater than Y, it indicates that the initial velocity of bacterial spread in the i-th area is abnormal, generating the first danger level. Based on the first danger level, the second strategy is generated, including: evacuating the flow of people in the current area, reducing the number of people by 20%-30% to keep it within a safe and controllable range; adding 5-7 exhaust devices to speed up the air flow in the area, increasing the air flow rate by 30%-50%; increasing the number of disinfections in the area by 70%-80%; transmitting the danger level to the backend and initiating the emergency plan;

[0099] When K i When ≤Y, it means that the initial speed of bacterial transmission in the i-th area is abnormal, but the danger level is lower than the first danger level, and the second danger level is generated. Based on the second danger level, the third strategy is generated, including: improving the ventilation effect of the area by 10%-20%, evacuating the flow of people, increasing the concentration of disinfectant by 30%-40%, fully disinfecting the area, marking the area as a potential risk area, and continuously monitoring it.

[0100] The following is the bacterial transmission threshold Y and the bacterial transmission coefficient K in the i-th region i For a comparison example, see Table 4:

[0101] Bacterial transmission coefficient in the i-th region Bacterial transmission threshold Evaluation results 280 240 First danger level 260 240 First danger level 300 240 First danger level 150 240 Second Danger Level 207.7 240 Second Danger Level

[0102] In this embodiment, the present invention uses an alarm unit to perform multi-source fusion of the local temperature, air circulation rate and pedestrian flow in the area, and calculates the bacterial transmission coefficient after dimensionless processing, so that the bacterial transmission risk analysis no longer relies on a single indicator, and enhances the system's scientific modeling capabilities for bacterial diffusion paths and speeds. By constructing a risk prediction model and dynamically generating a bacterial transmission threshold Y based on the transmission coefficient classification boundary output by the model, the problem of easy failure of static thresholds is avoided, the system's adaptability to complex and changing environments is enhanced, and the accuracy and foresight of identifying the initial velocity of bacterial transmission are improved.

[0103] Based on the comparison between the transmission coefficient and the transmission threshold Y, the system automatically distinguishes between the first and second danger levels, and matches differentiated strategic responses respectively, promoting the evolution of bacterial transmission warning management from "single response" to "layered precise regulation", and improving the precision and flexibility of management. When the bacterial transmission coefficient significantly exceeds the threshold Y, the system can immediately trigger the evacuation of personnel, increase exhaust equipment, increase air circulation rate and disinfection frequency, and transmit the danger level data to the background in real time, and jointly activate the emergency response mechanism, greatly shortening the response time and reducing the risk of cross infection.

[0104] Example 7, this example is the explanation in Example 1, please refer to Figure 1 Specifically, the second extraction subunit is used to extract the walking speed v of the jth person in the i-th area from the third data set. i,j , the number of times the jth person in the i-th area sneezes i,j and the mask wearing rate m of people in the i-th area i , after dimensionless processing, we get Where n i Expressed as the total number of people in the i-th region, v max Expressed as the maximum speed value, Where s max Expressed as the maximum number of sneezes, the bacterial breeding coefficient B of the i-th area is calculated using the following formula i ;

[0105]

[0106] Where β1, β2 and β3 are weight coefficients.

[0107] The default values ​​of β1, β2 and β3 are 0.4, 0.3 and 0.3, respectively. The weight coefficients are obtained by training the model with the input data.

[0108] The following is the bacterial breeding coefficient B of the i-th area behavior i The example table is shown in Table 5:

[0109]

[0110] In this embodiment, the system extracts core behavioral variables such as walking speed, number of sneezes, and mask wearing rate of people in the area, and combines them with dimensionless normalization processing so that behavioral characteristics of different dimensions can be weighted modeled under a unified mathematical framework, thereby improving the ability to identify the causes of bacterial breeding behavior. By constructing a behavioral indicator system including three elements: "abnormal speed", "high-frequency sneezing" and "low mask wearing rate", it can quickly identify potential health risk behaviors in the crowd, realize early warning of individual-level transmission risks, and effectively make up for the blind spots of traditional environmental monitoring that relies only on physical data.

[0111] The key behavioral characteristics of all people in the i-th area are aggregated and normalized based on the total number of people. This allows the system to dynamically track the overall behavioral trends of the crowd and maintain high evaluation efficiency even in scenarios with dense passenger flow. The behavioral bacteria breeding coefficient, as an indispensable parameter indicator in the bacterial transmission mechanism, can serve as the input basis for the linkage analysis of the second and third evaluation sub-units, ensuring that the transmission risks caused by abnormal behavior can be responded to in a timely manner and accurately classified to support scientific decision-making.

[0112] Example 8, this example is the explanation in Example 1, please refer to Figure 1 Specifically, the third evaluation subunit is used to preset a behavior bacteria breeding threshold W;

[0113] By collecting and analyzing historical behavior data and bacterial detection results at the station, and using statistical methods, we can obtain the behavioral bacterial breeding threshold W.

[0114] The behavioral bacterial growth threshold W is combined with the behavioral bacterial growth coefficient B in the i-th region. i Perform a comparison and generate a third evaluation instruction, including:

[0115] When B i When the value is greater than W, it indicates that the behavior of people in the i-th area is abnormal, resulting in the distance between people being between 0.3m and 0.7m. The fourth strategy is generated, including: improving the ventilation efficiency of the area by more than 30%, triggering a behavioral guidance mechanism based on pedestrian density, maintaining an average distance of more than 0.9m per person through broadcasting and station patrols, spraying disinfectant inside the station, increasing the disinfection frequency by 5%-7%, and having station staff distribute masks to passengers to increase the mask wearing rate to 80%-90%.

[0116] When B i When ≤W, it means that the behavior of people in the i-th area is normal and the flow of people in the area is also within the controllable range of 50%-80%. Continue to execute and monitor according to the pre-planned plan.

[0117] The following are the behavioral breeding bacteria threshold W and the behavioral breeding bacteria coefficient B in the i-th region i For a comparison example, see Table 6:

[0118]

[0119] In this embodiment, by collecting historical station behavior data and conducting statistical regression analysis on bacterial detection results, a behavioral bacteria breeding threshold W is constructed, so that the system can realize quantitative behavioral anomaly identification based on the comparison of real-time behavior coefficients with historical patterns, thereby improving the discrimination accuracy. Once the behavioral bacteria breeding coefficient exceeds the threshold W, the system immediately generates an evaluation instruction, triggering the "fourth strategy" for intervention, so that station managers can respond quickly to abnormal personnel behavior in the early stage and reduce the potential risk of bacterial spread. The evaluation results not only trigger disinfection responses, but also link the ventilation system and evacuation mechanism, realize intelligent coordination between the broadcast system and manual patrols, accurately control the density and flow path of personnel, and effectively alleviate the transmission pressure in dense areas.

[0120] When the behavior coefficient is abnormal, the system automatically pushes a policy to require staff to distribute masks, and detects whether the wearing rate meets the standard through subsequent image recognition, realizing closed-loop supervision, improving the effect of public health intervention and quantifiable evaluation capabilities. When the behavior coefficient B of the i-th area is abnormal, the system automatically pushes a policy to require staff to distribute masks, and detects whether the wearing rate meets the standard through subsequent image recognition, realizing closed-loop supervision, improving the effect of public health intervention and quantifiable evaluation capabilities. i When ≤W, the system determines that the current behavior state is normal, that is, it does not trigger additional resource calls, but maintains the original disinfection and ventilation strategies, effectively avoiding resource waste due to misjudgment, and reflecting the system's energy saving and operational economy.

[0121] Example 9, this example is the explanation in Example 1, please refer to Figure 1 ,Specifically, the disinfection quality analysis module includes an ,associated unit and an optimization unit;

[0122] The associated unit is used to calculate the bacterial growth coefficient E of the i-th area environment. i and the bacterial breeding coefficient B of the i-th region i The comprehensive disinfection behavior coefficient D is obtained by the following calculation after being dimensionless. total ;

[0123]

[0124] Where C represents the total number of regions, γ1 and γ2 are weight coefficients, where γ1+γ2=1.

[0125] The default value of γ1 is 0.6 and γ2 is 0.4. The weight coefficients here are obtained by inputting data into the training model; the following is the comprehensive disinfection behavior coefficient D total See Table 7 for an example table:

[0126]

[0127] In this embodiment, a unified comprehensive disinfection behavior coefficient is formed by weighted integration of the environmental bacterial growth coefficient and the behavioral bacterial growth coefficient of the i-th area, so that the system can consider the influence of both objective environmental pollution sources and subjective personnel behavior in the decision-making process, thereby improving the scientific nature and coverage of the overall disinfection strategy. Through dimensionless processing and normalized calculation, parameters with significant differences in physical dimensions (such as personnel speed, dust area, humidity value, etc.) are uniformly converted to the same evaluation scale, ensuring that the integrated comprehensive disinfection behavior coefficient has a stable numerical comparison basis, thereby improving the consistency and robustness of the index system.

[0128] Based on the comprehensive disinfection behavior coefficient generated for each area, the system can form a unified evaluation index system for all C areas, which is convenient for zoning management and hierarchical scheduling according to high-risk, medium-risk and controllable states within the station, and optimizes operation and maintenance efficiency. The integrated disinfection behavior coefficient is used as the input for subsequent optimization unit judgment, enabling the system to make intelligent decisions based on the actual risk intensity on whether to increase the disinfection frequency, adjust the disinfection concentration or guide the crowd, avoid excessive disinfection or blind control, and improve resource utilization efficiency. The set weight coefficient can be adjusted according to different stations or different operating time periods (such as peak and off-peak periods), enhancing the system's adaptability to specific scenarios and strategy flexibility, making the model more versatile and extensible.

[0129] Example 10: This example is an explanation of Example 1. Please refer to Figure 1 ,Specifically, the optimization unit is used to preset a comprehensive disinfection behavior threshold L;

[0130] The comprehensive disinfection behavior threshold L is obtained by statistically analyzing historical bacterial growth data and disinfection effect data in the station;

[0131] The comprehensive disinfection behavior threshold L includes L1 and L2, L1 represents the maximum value of the comprehensive disinfection behavior threshold, L2 represents the minimum value of the comprehensive disinfection behavior threshold, and satisfies L1>L2, and the comprehensive disinfection behavior threshold L is combined with the comprehensive disinfection behavior coefficient D total Perform a comparison and generate a fourth evaluation instruction, including:

[0132] When D totalWhen the level is higher than L1, it indicates that bacteria are growing abnormally in the station, generating the first abnormality level. Based on the first abnormality level, the first optimization strategy is generated, including: increasing the disinfection frequency in the station by 25%-40%, increasing the ventilation equipment in the station to increase the air circulation rate in the station by 50%-60%, and having the station staff maintain the flow of people in each area of ​​the station. If the flow of people in each area exceeds the original set number of people by 20%, the people will be evacuated to other areas and masks will be distributed to increase the mask wearing rate of people in the station to more than 90%;

[0133] When L2≤D total When the value is ≤L1, it indicates that the bacterial growth in the station is abnormal, but lower than the first abnormality level, and a second abnormality level is generated. Based on the second abnormality level, a second optimization strategy is generated, including: increasing the disinfection frequency in the station by 10%-15%, and increasing the disinfection frequency of high-contact areas in the station, including public handrails and waiting seats, to 3-5 times every three hours;

[0134] When D total When it is less than L2, it means that the hygiene inside the station is normal, the original disinfection plan is maintained, and continuous monitoring is carried out through the background.

[0135] The following are the comprehensive disinfection behavior threshold L and the comprehensive disinfection behavior coefficient D total For a comparison example, see Table 8:

[0136]

[0137] In this embodiment, by setting two-level thresholds L1 and L2, the comprehensive disinfection behavior coefficient is divided into three risk levels (high risk, medium risk, and low risk), effectively avoiding the "one-size-fits-all" static response mode, and realizing a management mode with hierarchical risk levels and differentiated strategic responses, thereby improving the pertinence and effectiveness of the response. By statistically modeling historical bacterial growth data and corresponding disinfection effect data, high-confidence upper and lower thresholds L1 and L2 are extracted, so that the threshold setting has a data support basis, overcoming the shortcomings of the existing system of setting thresholds based solely on experience and large judgment errors, and improving the accuracy and interpretability of anomaly detection.

[0138] When the comprehensive disinfection behavior coefficient exceeds L1, the system automatically identifies it as a high-risk area and promptly activates the first optimization strategy to significantly increase the ventilation rate and disinfection frequency. At the same time, it combines the crowd guidance mechanism and the mask distribution mechanism to strengthen multi-dimensional intervention measures, reduce the risk of pathogen transmission from the source, and effectively control sudden health incidents. When the comprehensive disinfection behavior coefficient is between L2 and L1, the system generates a locally enhanced second optimization strategy based on the second abnormality level, focusing on high-frequency contact areas such as public handrails and waiting seats, and increasing the local disinfection frequency per unit time to achieve a balance between refined zoning prevention and control and minimizing interference with operations. When the comprehensive disinfection behavior coefficient is lower than L2, the system judges that the current sanitary conditions meet the standards, maintains the established disinfection frequency and ventilation strategy, avoids waste of resources, and realizes the "low intervention + high alert" operation mechanism through continuous background monitoring and data tracking, thereby improving the system's economy and sustainable operation capabilities.

[0139] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An integrated disinfection monitoring and management system based on quantitative risk assessment, characterized by: It includes environment and behavior parameter collection module, bacteria breeding risk analysis module and disinfection quality analysis module; The environmental and behavioral parameter acquisition module is used to divide the station into several disinfection monitoring areas, conduct real-time video capture and data acquisition of public transportation passenger flow and the distance between people, and continuously monitor the surface humidity of public transportation handrails using humidity sensors. Furthermore, the dynamic behavioral characteristics of people in the station are collected using camera equipment to construct the first, second, and third data sets respectively, where the dynamic behavioral characteristics include walking speed and the number of sneezes. The bacterial growth risk analysis module is used to construct a prediction risk model using a convolutional neural network, and input the first data set, the second data set, and the third data set into the prediction risk model for analysis, output the bacterial growth prediction risk result for the disinfection detection area, and construct the i-th regional environmental bacterial growth coefficient E based on the first data set, the second data set, and the third data set. i , bacterial transmission coefficient K i and behavioral bacterial growth coefficient B i ; The disinfection quality analysis module is used to receive the output of the bacterial growth prediction risk result of the disinfection detection area, and combine it with the bacterial growth coefficient E of the i-th area environment i and behavioral bacterial growth coefficient B i , construct comprehensive disinfection behavior coefficient D total , and evaluate and generate corresponding strategies.

2. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 1, characterized in that: The environment and behavior parameter collection module includes an area division unit, an environmental bacteria collection unit, a personnel behavior breeding bacteria collection unit, and a bacteria transmission collection unit; The area division unit is used to divide the station into several disinfection monitoring areas, establish three-dimensional coordinates, and obtain the coordinates x, y, z of the i-th area; The environmental bacteria collection unit is used to capture the flow of people on public transportation using a multi-angle camera device located in the disinfection detection area of ​​the i-th area in the station, and obtain the flow of people in the i-th area P. i , and based on the camera equipment to collect the distance between people on public transportation, obtain the distance between people in the i-th area D i , the humidity change on the handrail surface caused by the jth person in the i-th area contacting the public handrail is collected, and the humidity value H generated by the jth person in the i-th area contacting the public handrail on the handrail surface is obtained i,j , construct the first data set; The first data set also includes the dust area G in the i-th region. 1,i , solid waste type G 2,i and the number of waste collection bins in the i-th area B i Based on the camera equipment, the ground image of the i-th area is captured, and the image recognition algorithm is combined to perform image dust texture recognition to obtain the ground dust area G of the i-th area. 1,i ; and based on the camera equipment, take an image of the i-th area, and identify the waste texture and waste collection box texture in the image to obtain the solid waste type G of the i-th area 2,i and the number of waste collection boxes B i , where solid waste types include disposable packaging bags, beverage bottles and toilet paper; The bacterial transmission collection unit is used to install temperature sensors at multiple locations in the i-th area of ​​the station, detect the temperature through the temperature sensors, and take the average to obtain the local temperature T of the i-th area. i By distributing wind speed sensors at different locations in the i-th region and analyzing the convection path, the air circulation rate V of the i-th region is derived. i , and construct the second data set; The personnel behavior breeding bacteria collection unit is used to set a multi-angle camera device in the i-th area, detect the distance walked by the j-th person according to the three-dimensional coordinate system, and use a timer to detect the walking time, and collect the speed of the j-th person in the i-th area to obtain the walking speed v of the j-th person in the i-th area. i,j By using a camera to capture images of people in the i-th area and identifying the motion features of people in the images, combined with the audio collection of people by the camera, the number of sneezes of the j-th person in the i-th area is obtained. i,j , construct the third data set; The third data set also includes the mask wearing rate of people in the i-th area of ​​the station. Based on the camera equipment taking images of the faces of people in the i-th area from multiple angles and identifying the mask texture in the image, the number of people wearing masks in the i-th area is collected. Combined with the total number of people in the i-th area, the mask wearing rate m of people in the i-th area is obtained by ratio calculation. i .

3. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 2, characterized in that: The bacterial growth risk analysis module includes a model building unit, a recording unit, an extraction unit and an evaluation unit; The model construction unit is used to use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with the first data set and the second data set, and use the trained initial convolutional neural network model as a disinfection test evaluation model, and use the intermediate layer output of the disinfection test evaluation model as a feature vector to identify the bacterial breeding information of the i-th area in the station, and train and test the disinfection test evaluation model through the obtained feature information, and use the trained disinfection test evaluation model as data to run prediction, and respectively construct the environmental bacterial breeding coefficient E i , domain bacterial transmission coefficient K i and behavioral bacterial growth coefficient B i and recorded by the recording unit.

4. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 3 is characterized in that: The environmental bacterial growth coefficient is obtained as follows: The extraction unit includes a first extraction subunit and a second extraction subunit; The first extraction subunit is used to extract the pedestrian flow P in the i-th area based on the first data set. i 、Interval between people D i , the humidity value H generated by the jth person in the i-th area contacting the public handrail i,j And the dust area G in the i-th region 1,i , solid waste type G 2,i and the number of waste collection bins in the i-th area B i , the bacterial growth coefficient E of the i-th region environment is obtained by calculation i .

5. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 4 is characterized in that: The evaluation unit includes a first evaluation subunit, a second evaluation subunit and a third evaluation subunit, which are used to preset an environmental bacteria growth threshold value A; The environmental bacteria growth threshold value A is compared with the environmental bacteria growth coefficient E to generate a first evaluation instruction, including: When E>A, it indicates that the amount of bacteria in the environment of the i-th area in the station is abnormal, and the first strategy is generated, including: increasing the number of waste collection boxes in the i-th area by 10%-15%, increasing the disinfection frequency of the i-th area in the station by 5%-8%, cleaning the floor of the i-th area, and increasing the disinfection frequency of public handrails by 5 times / three hours to 7 times / three hours, evacuating people from the i-th area, and generating an alarm unit when the flow of people in the i-th area reaches 1.2 times the preset number of people; When E≤A, it means that the amount of bacteria growing in the environment of the i-th area in the station is normal. The currently set disinfection plan should be implemented and monitoring should continue.

6. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 5, characterized in that: The alarm unit is used to extract the local temperature T of the i-th region from the second data set. i and the air circulation rate V in the i-th area i , and combined with the flow of people in the i-th area P i , the bacterial transmission coefficient K of the i-th region is obtained by calculation i ; The second evaluation subunit is used to preset a bacteria transmission threshold value Y; And the bacterial spread Y is combined with the bacterial spread coefficient K in the i-th region i Perform a comparison and generate a second evaluation instruction, including: When K i When the value is greater than Y, it indicates that the initial velocity of bacterial spread in the i-th area is abnormal, generating the first danger level. Based on the first danger level, the second strategy is generated, including: evacuating the flow of people in the current area, reducing the number of people by 20%-30% to keep it within a safe and controllable range; adding 5-7 exhaust devices to speed up the air flow in the area, increasing the air flow rate by 30%-50%; increasing the number of disinfections in the area by 70%-80%; transmitting the danger level to the backend and initiating the emergency plan; When K i When ≤Y, it means that the initial speed of bacterial transmission in the i-th area is abnormal, but the danger level is lower than the first danger level, and the second danger level is generated. Based on the second danger level, the third strategy is generated, including: improving the ventilation effect of the area by 10%-20%, evacuating the flow of people, increasing the concentration of disinfectant by 30%-40%, fully disinfecting the area, marking the area as a potential risk area, and continuously monitoring it.

7. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 6, characterized in that: The second extraction subunit is used to extract the walking speed v of the jth person in the i-th area from the third data set. i,j , the number of times the jth person in the i-th area sneezes i,j and the mask wearing rate m of people in the i-th area i , the bacterial breeding coefficient B of the i-th area is obtained by calculation i .

8. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 7, characterized in that: The third evaluation subunit is used to preset a behavior-based bacteria breeding threshold W; The behavioral bacterial growth threshold W is combined with the behavioral bacterial growth coefficient B in the i-th region. i Perform a comparison and generate a third evaluation instruction, including: When B i When the value is greater than W, it indicates that the behavior of people in the i-th area is abnormal, resulting in the distance between people being between 0.3m and 0.7m. The fourth strategy is generated, including: improving the ventilation efficiency of the area by more than 30%, triggering a behavioral guidance mechanism based on pedestrian density, maintaining an average distance of more than 0.9m per person through broadcasting and station patrols, spraying disinfectant inside the station, increasing the disinfection frequency by 5%-7%, and having station staff distribute masks to passengers to increase the mask wearing rate to 80%-90%. When B i When ≤W, it means that the behavior of people in the i-th area is normal and the flow of people in the area is also within the controllable range of 50%-80%. Continue to execute and monitor according to the pre-planned plan.

9. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 8, characterized in that: The disinfection quality analysis module includes a correlation unit and an optimization unit; The associated unit is used to calculate the bacterial growth coefficient E of the i-th area environment. i and the bacterial breeding coefficient B of the i-th region i The comprehensive disinfection behavior coefficient D is obtained by calculation after dimensionless processing. total .

10. The integrated disinfection monitoring and management system based on quantitative risk assessment according to claim 9, characterized in that: The optimization unit is used to preset a comprehensive disinfection behavior threshold L; The comprehensive disinfection behavior threshold L includes L1 and L2, and satisfies L1>L2, and the comprehensive disinfection behavior threshold L is combined with the comprehensive disinfection behavior coefficient D total Perform a comparison and generate a fourth evaluation instruction, including: When D total When the level is higher than L1, it indicates that bacteria are growing abnormally in the station, generating the first abnormality level. Based on the first abnormality level, the first optimization strategy is generated, including: increasing the disinfection frequency in the station by 25%-40%, increasing the ventilation equipment in the station to increase the air circulation rate in the station by 50%-60%, and having the station staff maintain the flow of people in each area of ​​the station. If the flow of people in each area exceeds the original set number of people by 20%, the people will be evacuated to other areas and masks will be distributed to increase the mask wearing rate of people in the station to more than 90%; When L2≤D total When the value is ≤L1, it indicates that the bacterial growth in the station is abnormal, but lower than the first abnormality level, and a second abnormality level is generated. Based on the second abnormality level, a second optimization strategy is generated, including: increasing the disinfection frequency in the station by 10%-15%, and increasing the disinfection frequency of high-contact areas in the station, including public handrails and waiting seats, to 3-5 times every three hours; When D total When it is less than L2, it means that the hygiene inside the station is qualified, the original disinfection plan is maintained, and it is continuously monitored through the background.

Images