Medical waste whole-process supervision method based on intelligent medical waste monitoring platform

Abstract

The invention provides a medical waste whole-process supervision method based on an intelligent medical waste monitoring platform, and the method comprises the steps: enabling collected smell data to be matched with pre-established medical waste smell component data, judging the type of medical waste to which a smell source belongs, and determining whether the smell concentration exceeds a preset threshold value or not; if the odor concentration exceeds the standard, microorganism information is obtained according to the relevance between the odor component information and microorganisms, and the microorganism breeding risk is evaluated in combination with temperature and humidity control parameters of the air conditioner; simulating airflow distribution of an air conditioning system, predicting diffusion paths and influence ranges of odor in different areas of a hospital by combining with position layout of an air outlet of the air conditioner, and generating an odor diffusion thermodynamic diagram; and according to the optimized disinfection scheme, the air conditioning system is controlled to enter a disinfection mode, the fresh air introduction proportion and the filtering efficiency grade are adjusted, a disinfectant is sprayed in the key area, and the disinfection effect is monitored in real time.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a full-process medical waste supervision method based on a smart medical waste monitoring platform. Background Art

[0002] During the intra-hospital transportation of medical waste, there is a complex relationship between the generation of odor and the spread of microorganisms. The odor components released by different types of medical waste on the transportation route are different and fluctuate with changes in temperature and humidity. These odors not only affect the environment, but may also indicate potential biological hazards. However, the existing regulatory system makes it difficult to track the source of odor in real time and predict its diffusion trend. At the same time, although the hospital air-conditioning system can be used to control odor, its airflow distribution often does not match the waste transportation route, making it difficult to accurately control the odor diffusion range. In addition, the preliminary disinfection treatment for different microorganisms needs to ensure the effect while avoiding chemical reactions with odor components to produce secondary pollution. However, there is currently a lack of intelligent regulatory systems that can comprehensively consider odor diffusion, microbial activity, air conditioning airflow, and disinfection reactions, making it difficult to achieve accurate control and risk warning of the entire process of medical waste transportation in a complex and changeable intra-hospital environment. Summary of the invention

[0003] The present invention provides a method for monitoring the entire process of medical waste based on a smart medical waste monitoring platform, which mainly includes:

[0004] According to the classification of medical waste, a distributed sensor network is used to sample the odor of waste transfer routes in different areas to obtain odor data, including odor concentration data and odor component information;

[0005] Match the collected odor data with the pre-established medical waste odor component data to determine the type of medical waste to which the odor source belongs and whether the odor concentration exceeds a preset threshold;

[0006] If the odor concentration exceeds the standard, the microbial information is obtained based on the correlation between the odor component information and the microorganisms, and the risk of microbial growth is evaluated in combination with the temperature and humidity control parameters of the air conditioner;

[0007] Simulate the air flow distribution of the air conditioning system, combine the location layout of the air conditioning outlets, predict the diffusion path and impact range of odors in different areas of the hospital, and generate an odor diffusion heat map;

[0008] Based on the odor diffusion heat map, combined with the frequency of air conditioning filter replacement and pipeline cleaning cycle factors, determine the areas that need to be disinfected. At the same time, based on the risk of microbial growth, select a disinfection plan to deal with such odors and microorganisms;

[0009] According to the selected disinfection scheme, the chemical components of the disinfectant used in the disinfection scheme are extracted, and the potential reaction of the chemical components with the known odor components in the air is evaluated through chemical reaction simulation. According to the evaluation results, if toxic and harmful substances are generated, the disinfection scheme is optimized to avoid secondary pollution;

[0010] According to the optimized disinfection plan, the air-conditioning system is controlled to enter the disinfection mode, the fresh air introduction ratio and filtration efficiency level are adjusted, disinfectant is sprayed in key areas, and the disinfection effect is monitored in real time.

[0011] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0012] The present invention discloses a method for supervising the entire process of medical waste based on a smart medical waste monitoring platform. The odor data of the medical waste transfer path is collected through a distributed sensor network, and the odor source and concentration are determined by matching with a pre-built database. When the odor concentration exceeds the standard, the microbial database is queried based on the odor component information, and the risk of microbial growth is evaluated in combination with the air-conditioning system parameters. At the same time, the odor diffusion path is simulated, and a thermal map is generated to determine the key disinfection areas. A suitable solution is selected from the disinfectant database, and the risk of potential harmful substances generated is evaluated and optimized through chemical reaction simulation to avoid secondary pollution. Finally, the air-conditioning system is controlled to enter the disinfection mode to monitor the effect in real time. The present invention realizes intelligent monitoring, risk assessment and precise disinfection of medical waste odor, effectively reduces the risk of nosocomial infection, and improves the safety of the medical environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The present invention is a flowchart of a method for supervising the entire process of medical waste based on a smart medical waste monitoring platform.

[0014] Figure 2 It is a schematic diagram of a full-process medical waste supervision method based on a smart medical waste monitoring platform of the present invention.

[0015] Figure 3 This is another schematic diagram of a full-process medical waste supervision method based on a smart medical waste monitoring platform according to the present invention. DETAILED DESCRIPTION

[0016] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0017] like Figure 1-3In this embodiment, a full-process medical waste supervision method based on a smart medical waste monitoring platform may specifically include:

[0018] Step S101, based on the classification of medical waste, a distributed sensor network is used to perform odor sampling on waste transfer routes in different areas to obtain odor data, including odor concentration data and odor component information.

[0019] Acquire the sampling area information divided according to the pre-established medical waste classification standards, set up multiple odor sampling points in the sampling area, and form a distributed sensor network covering the waste transfer path. Use a gas sensor array to detect the odor sampling points in real time to obtain the odor concentration and component data of each sampling point; fuse different types of sensor data according to the weighted average algorithm to determine the comprehensive odor data. Preprocess the comprehensive odor data and eliminate environmental noise interference through a filtering algorithm; reduce the dimensionality of the multi-dimensional odor feature data and extract the odor fingerprint feature vector containing the key parameters of gas component concentration ratio, odor intensity, and duration.

[0020] Exemplarily, the sampling area is divided according to the pre-established medical waste classification standard, and multiple odor sampling points are set in each waste category area to form a distributed sensor network covering the waste transfer path. A high-sensitivity gas sensor array is used to detect the odor concentration and composition of each sampling point in real time. The sensor array includes metal oxide, electrochemical, and photoionization sensors. The weighted average algorithm is used to fuse the data of different types of sensors to obtain comprehensive odor data. The odor data collected at each sampling point is preprocessed, the environmental noise interference is eliminated by the Ka lman filter algorithm, and the singular value decomposition (SVD) algorithm is used to reduce the dimension of the multi-dimensional odor feature data to extract the odor fingerprint feature vector. The odor fingerprint feature vector includes key parameters such as gas component concentration ratio, odor intensity, and duration. An odor database is established, and the odor data is associated with the waste transfer path according to the geographical location information of the sampling point to form an odor distribution map. The preprocessed odor data is pattern recognized and classified using a convolutional neural network with a ResNet-50 architecture. The transfer learning method is used, and the pre-trained model is used as a feature extractor, and then fine-tuned on the medical waste odor dataset. The identification results are matched with the preset medical waste odor feature library to determine the waste category and concentration level at each sampling point. A waste distribution heat map is drawn to mark the main gathering areas and transfer channels of different types of waste. Based on the odor distribution heat map, the rationality of the current transfer route is evaluated, and the odor intensity and waste category distribution of each section are calculated. A medical waste transfer route optimization model is constructed, considering factors such as the hazard level of various types of waste and the timeliness requirements of treatment, combined with information such as the amount of waste generated and the location of treatment facilities. The Max-M in ant colony algorithm is used to dynamically optimize and adjust the existing transfer route, in which the odor intensity on the path is used as heuristic information and the hazard level of the waste category is used as a constraint condition for path selection. Through multiple iterative calculations, the optimal classification transfer route plan is generated to achieve efficient classification and transfer of medical waste in different regions. In the division of medical waste sampling areas, the areas are divided into five categories: infectious, damaging, pathological, chemical and pharmaceutical according to the pre-established classification standards. 20 odor sampling points are set in each area to form a distributed sensor network of 100 nodes. Each sampling point is equipped with three sensors: metal oxide sensors for detecting volatile organic compounds, electrochemical sensors for detecting ammonia and hydrogen sulfide, and photoionization sensors for detecting trace organic matter. The weighted average algorithm is used to fuse the data, with a weight ratio of 4:3:3. In the Ka lman filter algorithm, the measurement noise covariance R is set to 0.1 and the process noise covariance Q is set to 0.01 to balance sensitivity and stability. The SVD algorithm reduces the original 50-dimensional odor data to a 10-dimensional feature vector, retaining 95% of the information. The odor fingerprint feature vector contains the relative concentration ratios of 10 key gas components such as formaldehyde, ethanol, and acetone. The odor intensity is represented by a quantitative value of 0-100, and the duration is recorded in seconds.The odor distribution map uses color depth to represent concentration, and different patterns to represent waste categories. The ResNet-50 network uses pre-trained weights, and the last three layers are replaced by fully connected layers adapted to medical waste classification, with a layer number of 1024-512-5. Transfer learning uses 5,000 pre-labeled medical waste odor maps for fine-tuning, with a learning rate set to 0.001, a batch size of 64, and 50 rounds of training. The waste distribution heat map uses red, yellow, and green gradients to represent high and low concentrations, and uses icons of different shapes to mark five types of waste. When evaluating the rationality of the transfer route, the average odor intensity and the waste category distribution ratio on each route are calculated. In the improved Max-Min ant colony algorithm, the inverse of the odor intensity on the path is used as heuristic information, and the waste category hazard level is used as a constraint for path selection. The pheromone volatility coefficient is set to 0.5, the local update coefficient is 0.1, and the global update coefficient is 0.2. Through 100 iterative calculations, the most optimized classification and transfer route plan was generated, realizing the efficient classification and transfer of medical waste in different areas. The average route length was shortened by 15% compared with before optimization, and the exposure time of hazardous waste was reduced by 20%.

[0021] Step S102, matching the collected odor data with pre-established medical waste odor component data, determining the type of medical waste to which the odor source belongs, and determining whether the odor concentration exceeds a preset threshold.

[0022] Acquire odor data collected by a multi-channel gas sensor array, the odor data including the output of metal oxide, electrochemical and photoionization sensors; dynamically adjust the weight according to the accuracy of each sensor in the historical data, and fuse the odor data using the weighted average method; standardize the fused data to obtain a unified format of odor feature vector. Extract feature templates from a pre-established medical waste odor component database, the feature templates contain typical odor components and concentration ranges of different types of medical waste; perform dimensionality reduction processing on the odor feature vector, and select the first N principal components whose cumulative contribution rate reaches a preset value as key odor component information. Use a support vector machine classifier to classify the odor feature vector, the support vector machine classifier uses a radial basis function kernel; optimize the kernel parameters and penalty factors of the radial basis function kernel through cross-validation; if the output result of the support vector machine classifier matches the preset category, the type of medical waste from which the odor comes is determined. Establish a preset threshold database, the preset threshold database contains multi-level odor concentration thresholds; use a cubic spline interpolation algorithm to convert the sensor raw signal into a standardized odor concentration value; determine whether the standardized odor concentration value exceeds the corresponding threshold in the preset threshold database. If the standardized odor concentration value exceeds the preset threshold, an alarm of a corresponding level is triggered according to the degree of excess.

[0023] Exemplarily, a multi-channel gas sensor array is used to collect odor data, including metal oxide, electrochemical and photoionization sensors, and data fusion is performed by weighted average method, and the weight is dynamically adjusted according to the accuracy of each sensor in the historical data. The fused data is standardized, and the moving average filter is used to eliminate the interference of environmental temperature and humidity to obtain an odor feature vector in a unified format. The processed odor feature vector is passed to the subsequent steps. Feature templates are extracted from a pre-established medical waste odor component database, which contains typical odor components and concentration ranges of different types of medical waste. Singular value decomposition (SVD) is used to reduce the dimension of the odor feature vector, and the top N principal components with a cumulative contribution rate of 95% are selected as key odor component information. New odor samples are collected regularly, and the feature templates and concentration ranges in the database are updated. A support vector machine (SVM) classifier is used to classify the odor feature vector to determine the type of medical waste from which the odor comes. The SVM classifier uses a radial basis function (RBF) kernel, and the kernel parameters and penalty factors are optimized by cross-validation. In the training stage, a grid search method is used to determine the optimal parameter combination to improve the classification accuracy. According to historical data statistics, a preset threshold database is established and regularly updated. For each type of medical waste, multi-level odor concentration thresholds are set, including warning values ​​and dangerous values. The original sensor signal is converted into a standardized odor concentration value using the cubic spline interpolation algorithm, and the interpolation point selects the key inflection point of the sensor response curve. By comparing the calculated odor concentration with the preset threshold, it is determined whether the odor concentration exceeds the standard, and different levels of alarms are triggered according to the degree of exceeding the standard. In the multi-channel gas sensor array, metal oxide sensors detect volatile organic compounds, electrochemical sensors detect ammonia and hydrogen sulfide, and photoionization sensors detect trace organic matter. In the weighted average method, the initial weights are set to 0.4, 0.3, and 0.3, and the weights are automatically adjusted every 24 hours according to the accuracy of each sensor. The z-score method is used for standardization processing to convert the data into a distribution with a mean of 0 and a standard deviation of 1. The moving average filter window size is set to 60 seconds to eliminate the influence of environmental temperature and humidity fluctuations in real time. The medical waste odor component database contains typical odor characteristics of five major types of waste: infectious, damaging, pathological, chemical, and pharmaceutical. During the SVD dimension reduction process, the first five principal components were selected, and the cumulative contribution rate reached 96.8%. 100 new odor samples were automatically collected every week, and the feature templates and concentration ranges in the database were updated. The SVM classifier uses the RBF kernel, and the parameters are optimized through 5-fold cross-validation. The kernel parameter γ range is [0.001, 0.1], the penalty factor C range is [1, 100], and the grid search step is 0.1. The optimal parameter combination was finally determined to be γ = 0.01, C = 10, and the classification accuracy reached 94.5%. In the preset threshold database, three thresholds are set for each waste type as warning value, danger value and emergency value, corresponding to the 70%, 85% and 95% quantiles of odor concentration respectively.The cubic spline interpolation algorithm selects the 0%, 25%, 50%, 75% and 100% response points of the sensor response curve as key inflection points to construct a smooth concentration conversion curve. If the calculated odor concentration exceeds the preset threshold, an alarm of the corresponding level is triggered and a real-time warning message is pushed to the waste management personnel.

[0024] Step S103, if the odor concentration exceeds the standard, the microbial information is obtained according to the correlation between the odor component information and the microorganisms, and the risk of microbial growth is evaluated in combination with the temperature and humidity control parameters of the air conditioner.

[0025] Obtain the odor concentration detection result, and determine whether it exceeds a preset threshold based on the detection result. If the detection result exceeds the preset threshold, trigger a subsequent evaluation process; use the Aprili algorithm to analyze the correlation between the odor component information and the microorganism, the support threshold of the Aprili algorithm is a preset value, and the confidence threshold of the Aprili algorithm is a preset value; screen out the microorganism species that are highly correlated with the odor component based on the correlation analysis result, and obtain the growth conditions and reproduction rate information of the microorganism species; establish a microbial growth prediction model, and the prediction model calculates the potential growth rate of the microorganism based on the growth conditions, the reproduction rate information, temperature parameters and humidity parameters; determine whether the potential growth rate exceeds the preset risk level threshold. If the potential growth rate exceeds the preset risk level threshold, determine the microbial breeding risk level; the risk levels include low risk, medium risk and high risk.

[0026] Exemplarily, according to the odor concentration detection result, it is determined whether it exceeds the preset threshold, which is set based on the 95% quantile of historical data. If the threshold is exceeded, the subsequent evaluation process is triggered to extract the currently detected odor component information from the odor component database, including the concentration and proportion of various chemical substances. The odor component database adopts a key-value pair structure, with the key being the chemical name and the value being the concentration range, and is automatically updated once a week. The April algorithm is used to analyze the correlation between odor component information and microorganisms, with the support threshold set to 0.1 and the confidence threshold set to 0.7. Microbial species that are highly correlated with the current odor component are screened out from the microbial database, and key information such as the growth conditions and reproduction rate of these microorganisms is obtained. The screened microbial information is passed to the next prediction model in JSON format. The real-time temperature and humidity data of the air-conditioning system are collected, and a microbial growth prediction model based on the Gompertz equation is established in combination with the growth conditions of the microorganisms. The model considers multiple influencing factors such as temperature, humidity, and odor component concentration, and calculates the potential growth rate of microorganisms in the current environment. According to the prediction results, the temperature and humidity parameters of the air-conditioning system are automatically adjusted to make the environmental conditions unfavorable for microbial growth. According to the output results of the microbial growth prediction model, combined with the pre-set risk level standards, the risk of microbial growth is evaluated. The risk level is divided into three levels: low, medium and high. Low risk corresponds to a predicted growth rate of less than 0.1 / hour, medium risk corresponds to 0.1-0.5 / hour, and high risk corresponds to greater than 0.5 / hour. Generate a risk assessment report, including risk level, main risk microbial types, and recommended prevention and control measures. At the same time, a microbial growth trend chart and a risk heat map are generated to intuitively display the risk distribution. In the medical waste treatment area, the odor concentration detection system monitors the odor concentration in the environment in real time, using an electrochemical sensor to sample every 5 minutes. Based on the historical data of the past 30 days, the 95% quantile is calculated as the preset threshold, which is currently set to 50ppm. The odor concentration is detected to reach 52ppm, exceeding the preset threshold, triggering the evaluation process. The currently detected odor component information is extracted from the odor component database, including formaldehyde 0.8ppm, ethanol 15ppm, acetone 5ppm, etc. The April algorithm analyzes the correlation between odor components and microorganisms, with a support threshold of 0.1 and a confidence threshold of 0.7. It identifies three microorganisms that are highly correlated with the current odor: Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa. The growth conditions for these microorganisms include the optimal growth temperature of 25-37°C and a relative humidity of 60-80%. The real-time temperature and humidity data of the air-conditioning system show that the current ambient temperature is 28°C and the relative humidity is 75%. The growth prediction model based on the Gompertz equation calculates that the current potential growth rate of Escherichia coli is 0.3 / hour. The air-conditioning temperature is adjusted to 22°C and the relative humidity is reduced to 55% to inhibit microbial growth.The risk assessment results show a medium risk level, with a growth rate of 0.3 / hour, between 0.1-0.5 / hour. The generated risk heat map shows that the center of the treatment area has the highest risk, which is red. The microbial growth trend chart predicts that if no measures are taken, the concentration of E. coli will increase by 7 times after 24 hours. Send a risk alert to the manager's mobile terminal, suggesting strengthening regional disinfection and ventilation.

[0027] Based on the odor component information, a query is performed in the microbial database to determine the types of microorganisms associated with the odor components, and the suitable growth condition information of each identified microorganism is extracted. The current temperature and humidity control parameters of the air conditioner are obtained in real time, including temperature setting, humidity control level and fresh air introduction ratio. The comprehensive breeding risk index of each microorganism is calculated based on the suitable growth condition information of the microorganism and the current temperature and humidity control parameters of the air conditioner.

[0028] Acquire odor component information and calculate cosine similarity, wherein the cosine similarity is used to identify associated microorganisms whose matching degree exceeds a preset threshold; acquire a unique identifier of the associated microorganism, and use the unique identifier to query information on suitable conditions for microbial growth; the suitable growth condition information includes temperature range, relative humidity range, pH range and oxygen demand; acquire temperature and humidity control parameters, wherein the temperature and humidity control parameters include temperature setting value, humidity control level and fresh air introduction ratio; standardize the temperature and humidity control parameters into standardized values; use a multi-factor weighted scoring model to compare the suitable growth condition information with the standardized values; in the multi-factor weighted scoring model, the temperature factor, humidity factor, pH factor and oxygen demand factor are respectively assigned preset weight values; determine the degree of harm of the associated microorganism; if the degree of harm of the associated microorganism exceeds a preset threshold, calculate a comprehensive breeding risk index for the associated microorganism; the comprehensive breeding risk index is determined by the product of the output result of the multi-factor weighted scoring model and the degree of harm.

[0029] Exemplarily, according to the odor component information, a cosine similarity calculation method based on TF-IDF is used to conduct a comprehensive search in the microbial database. Microorganisms with a matching degree of more than 80% are identified as associated microorganisms, and a list of related microorganisms is generated, including the microbial name and the corresponding matching degree. The matching threshold is determined by historical data analysis and adjusted once a quarter. The generated list of related microorganisms is passed to the next step of processing in JSON format. For each identified microorganism, the B+ tree index structure is used to quickly extract its detailed growth suitable condition information from the microbial database, including the optimal growth temperature range, the optimal relative humidity range, the optimal pH range and the oxygen demand. In the B+ tree index structure, the microbial name is used as the key and the growth condition information is used as the value to achieve efficient query and data extraction. The temperature and humidity control parameters of the current air conditioning system are obtained in real time through the air conditioning control system interface, including the temperature setting value, the humidity control level and the fresh air introduction ratio, and these parameter values ​​are standardized to standardized values ​​between 0-1. The effect of the fresh air introduction ratio on microbial growth is quantified by introducing the air quality index to calculate the inhibitory effect of fresh air on microbial reproduction. Using a multi-factor weighted scoring model, the suitable conditions for microbial growth are compared with the temperature and humidity control parameters of the current air-conditioning system to calculate the suitability score of each microorganism in the current environment. The weight of the temperature factor in the model is 0.4, the weight of the humidity factor is 0.3, the weight of the pH factor is 0.2, and the weight of the oxygen demand factor is 0.1. Combined with the weight of the microbial hazard level, the comprehensive breeding risk index of each microorganism is finally obtained. The weight of the microbial hazard level is comprehensively evaluated according to its pathogenicity, transmission ability and drug resistance, and the weight value is determined by the hierarchical analysis method. In the medical waste treatment area, the odor sensor detected a formaldehyde concentration of 0.5ppm, an ammonia concentration of 2ppm, and a hydrogen sulfide concentration of 0.1ppm. The cosine similarity calculation method based on TF-IDF is used to search in the microbial database, taking the odor component as the query word and the microbial feature as the document. The calculation results show that the matching degree of Escherichia coli is 85%, Staphylococcus aureus is 82%, and Pseudomonas aeruginosa is 78%. Since the matching threshold is set to 80%, the system generates a list of related microorganisms including Escherichia coli and Staphylococcus aureus. The growth conditions of these two microorganisms are quickly extracted using the B+ tree index structure: the optimal growth temperature of Escherichia coli is 35-37°C, the relative humidity is 60-70%, and the pH value is 6.0-7.0; the optimal growth temperature of Staphylococcus aureus is 30-37°C, the relative humidity is 20-80%, and the pH value is 7.0-7.5. The air conditioning control system shows that the current temperature is 25°C, the relative humidity is 55%, and the fresh air introduction ratio is 30%. These parameters are standardized to obtain a temperature of 0.71, a humidity of 0.69, and a fresh air ratio of 0.3. In the multi-factor weighted scoring model, the temperature factor weight is 0.4, the humidity factor is 0.3, the pH value is 0.2, and the oxygen demand is 0.1.The calculated environmental suitability scores for E. coli are 0.68 and for Staphylococcus aureus are 0.72. Considering the weights of the microbial hazard levels, E. coli is 0.6 and Staphylococcus aureus is 0.8, and the final comprehensive breeding risk indexes are 0.41 and 0.58, respectively. A risk report can be generated, suggesting lowering the temperature and humidity and increasing the proportion of fresh air to reduce the breeding risk.

[0030] Step S104, simulating the air flow distribution of the air conditioning system, combining the location layout of the air conditioning outlets, predicting the diffusion path and impact range of the odor in different areas of the hospital, and generating an odor diffusion heat map.

[0031] Acquire a hospital building information model, and construct a three-dimensional digital model based on the building information model; divide the three-dimensional digital model into grid units, and record the spatial coordinates, temperature, humidity and airflow information of the grid units; perform computational fluid dynamics simulation on the grid units to obtain airflow field distribution data; store the airflow field distribution data in the form of a three-dimensional matrix; receive the location and initial concentration information of the odor source; calculate the diffusion process of odor molecules using the Euler-Lagrange hybrid model based on the location, initial concentration information and airflow field distribution data of the odor source; obtain time-series concentration distribution data; analyze the relationship between the airflow field distribution data and the time-series concentration distribution data; optimize the position and angle of the air outlet of the air conditioner according to the relationship; generate a continuous concentration distribution field based on the optimized air outlet layout; map the continuous concentration distribution field to the color space to generate an odor diffusion heat map; overlay the odor diffusion heat map on the hospital floor plan to display the odor diffusion path and the scope of influence.

[0032] For example, according to the hospital building information model (BIM), the hospital floor plan and the air conditioning system design drawing are integrated to build an accurate three-dimensional digital model. The space is divided into grid units, and the size of each unit is set to 0.1 m × 0.1 m × 0.1 m to improve the simulation accuracy. The spatial coordinates, temperature, humidity, airflow velocity and direction of each grid point are recorded. The Navier-Stokes equation is used for computational fluid dynamics simulation to calculate the airflow velocity vector and pressure value of each grid point. Considering the temperature stratification effect, the space is divided into multiple temperature layers in the vertical direction, and each layer is set with a different initial temperature. The humidity distribution is represented by the relative humidity field function and coupled with the temperature field. The airflow field distribution data of the entire space is obtained, and the data is stored in the form of a three-dimensional matrix as the input of the odor diffusion simulation. Using the real-time data collected by the odor sensor, the odor source position and initial concentration are input into the airflow field model. The Euler-Lagrangian hybrid model is used, combined with the airflow field data, to simulate the movement and diffusion process of odor molecules under the action of airflow. The Euler method calculates the continuous concentration field, and the Lagrangian method tracks the trajectory of individual odor particles. The odor concentration values ​​of each grid unit at different time points were calculated to generate time series concentration distribution data. According to the location layout of the air-conditioning outlet, the relationship between air flow distribution and odor diffusion path was analyzed. The location and angle of the air outlet were optimized using a genetic algorithm to minimize the accumulation of odor in key areas. Based on the optimized layout, a continuous concentration distribution field was generated using the Kriging interpolation method. The heat map visualization technology was used to map different concentration values ​​to the color space to generate an odor diffusion heat map, which was superimposed on the hospital floor plan to intuitively display the odor diffusion path and impact range. In the operating area of ​​a three-story hospital, the building information model integrated the 1:100 scale floor plan and the air-conditioning system design drawing to construct an accurate 20m×30m×9m three-dimensional digital model. The space was divided into 200×300×90 grid units, each unit of 0.1m×0.1m×0.1m. In the Navier-Stokes equation simulation, the boundary conditions were set as no wall slip, an inlet velocity of 2m / s, and an outlet pressure of standard atmospheric pressure. The temperature field is initially set to three layers, with 22°C from the ground to 1.5 meters, 24°C from 1.5 meters to 4 meters, and 26°C above 4 meters. The initial value of the relative humidity field is set to 50%, which is coupled with the temperature field. The odor source is located in the center of the operating room with an initial concentration of 100 ppm. In the Euler-Lagrangian hybrid model, the Euler grid is consistent with the spatial grid, and the number of Lagrangian particles is set to 10,000. The simulation time step is 0.1 seconds and the total duration is 300 seconds. When the genetic algorithm optimizes the outlet position, the population size is set to 100, the number of iterations is 50, the crossover probability is 0.8, and the mutation probability is 0.1. The objective function is to minimize the critical area, the average odor concentration within 3 meters around the operating table. Kriging interpolation uses an exponential variation function with a search radius of 2 meters.In the heat map visualization, the concentration value 0-10ppm is mapped to blue, 10-50ppm is green, 50-100ppm is yellow, and above 100ppm is red. The final generated heat map shows that under the optimized outlet layout, the odor mainly diffuses along the ceiling to the exhaust outlet, and the concentration in the operating area is maintained below 20ppm, meeting the requirements of the medical environment.

[0033] Step S105, based on the odor diffusion heat map, combined with the air conditioning filter replacement frequency and pipeline cleaning cycle factors, determine the areas that need to be disinfected, and select a disinfection plan for dealing with such odors and microorganisms based on the risk of microbial growth.

[0034] Obtain odor diffusion heat map data, set odor concentration thresholds according to historical data quantiles, and divide odor pollution areas; correspond the heat map data to the actual spatial position through rasterization processing to obtain a list of key areas of concern. According to the filter replacement frequency and pipeline cleaning cycle data, establish a filter efficiency attenuation model and a pipeline pollution accumulation model; the pipeline pollution accumulation model uses a logarithmic growth function of P(t)=aln(t+1), P(t) is the pollution degree at time t, and a is the pollution rate coefficient. Calculate the current filter residual efficiency and pipeline pollution degree, and associate the results with the list of key areas of concern. Use a multi-factor weighted scoring method to score odor concentration, filter efficiency, pipeline pollution degree and microbial breeding risk; if the scoring result is in the previous preset percentage, it is determined to be a key disinfection area. According to the odor type and microbial species in the key disinfection area, select the applicable disinfection plan; construct a decision tree, the root node of the decision tree is the odor type, the second-level node is the main microbial species, and the third-level node is the environmental sensitivity. Select the optimal disinfection plan through the decision tree, and generate a disinfection guidance plan including the name of the disinfectant, the concentration used, and the application method.

[0035] Exemplarily, according to the odor diffusion heat map, the 90%, 95%, and 99% quantiles of historical data are used to set the low, medium, and high thresholds of odor concentration to divide the odor pollution area. Combined with the spatial coordinate information, the heat map data is matched with the actual spatial position through rasterization processing to generate a list of key areas of concern, including area number, location description, and odor concentration value. The filter replacement frequency and pipeline cleaning cycle data are extracted from the air conditioning maintenance record database, and the filter efficiency attenuation model is established using an exponential decay function as E(t) = E0e^(-kt), where E(t) is the efficiency at time t, E0 is the initial efficiency, and k is the attenuation coefficient. The pipeline pollution accumulation model uses a logarithmic growth function of P(t) = aln(t+1), P(t) is the pollution degree at time t, and a is the pollution rate coefficient. Calculate the current filter residual efficiency and pipeline pollution degree, associate the results with the list of key areas of concern, and pass them to the next step. A multi-factor weighted scoring algorithm is used to comprehensively consider the odor concentration weight of 0.4, the filter efficiency weight of 0.2, the pipeline contamination weight of 0.2, and the microbial growth risk weight of 0.2. The microbial growth risk data is obtained from the aforementioned microbial assessment module and standardized to 0-100 points. The disinfection priority score for each area is calculated as follows:

[0036] Score = 0.4O + 0.2F + 0.2P + 0.2M, where O, F, P, and M are the standardized odor concentration, filter efficiency, pipeline contamination degree, and microbial risk score, respectively. The top 20% of the areas with the highest scores are identified as key disinfection areas. According to the odor type and microbial species in the key disinfection areas, the applicable disinfection schemes are screened out from the disinfectant database. The decision tree algorithm is used to select the optimal disinfection scheme. The decision tree construction includes: setting the root node as the odor type, the second-level node as the main microbial species, the third-level node as the environmental sensitivity, and the leaf node as the recommended disinfectant. The optimal split feature is selected based on the information gain ratio, and the pruning algorithm is used to avoid overfitting. Finally, a disinfection guidance plan containing the name of the disinfectant, the concentration used, and the method of application is generated. In the operating room area of ​​a hospital, the odor diffusion heat map shows the distribution of formaldehyde concentration. Based on historical data analysis, the low, medium, and high thresholds are set to 0.05ppm, 0.08ppm, and 0.1ppm, respectively. Through rasterization, the 20m×30m area is divided into 400 0.5m×0.5m cells, each corresponding to a concentration value. 15 key focus areas were identified, of which the concentration in area 3 (coordinates 5,7) reached 0.09ppm. The air conditioning maintenance record shows that the filter was last replaced 30 days ago and the pipeline was cleaned 90 days ago. The filter efficiency decay model E(t)=100e^(-0.02t) is applied to calculate the current filter efficiency of 54.8%. The pipeline pollution accumulation model P(t)=10l n(t+1) calculates the pollution level to be 45.2. The microbial assessment report shows that the E. coli risk index of this area is 75, with a full score of 100. The multi-factor weighted scoring algorithm calculates that the score of area 3 is 0.490+0.254.8+0.2*(100-45.2)+0.2*75=73.92, ranking second and being identified as a key disinfection area. The decision tree algorithm selects the disinfection scheme based on the odor type of formaldehyde, the microorganism type of Escherichia coli, and the environmental sensitivity of the operating room, high. The first layer of the tree node "odor type" selects the "aldehyde" branch, the second layer "microorganism type" selects the "bacteria" branch, and the third layer "environmental sensitivity" selects the "high" branch. Finally, it is recommended to use 0.5% peracetic acid solution, spray by atomization, and the action time is 30 minutes.

[0037] Step S106, extract the chemical components of the disinfectant used in the disinfection scheme according to the selected disinfection scheme. Through chemical reaction simulation, evaluate the potential reaction of the chemical components with known odor components in the air. According to the evaluation results, if toxic and harmful substances are generated, optimize the disinfection scheme to avoid secondary pollution.

[0038] The method comprises the following steps: obtaining information of a selected disinfection scheme in a disinfection scheme database, wherein the information includes the name, chemical composition, concentration and usage of the disinfectant; constructing a three-dimensional molecular model, wherein the three-dimensional molecular model includes the chemical composition and odor composition of the disinfectant; running a chemical reaction simulation according to the three-dimensional molecular model to obtain reaction product information; matching the reaction product information with a toxic and hazardous substance database to determine whether there are potential toxic and hazardous substances; if there are potential toxic and hazardous substances, calculating their generated concentration and comparing them with a preset safety threshold; obtaining a hazard level assessment result according to the comparison result, wherein the hazard level assessment result includes the name of the substance, the predicted concentration and the excess multiple; if the hazard level assessment result determines that toxic and hazardous substances exceeding the safety threshold will be generated, starting a disinfection scheme optimization program based on a genetic algorithm; and generating a new alternative disinfection scheme by adjusting the type, concentration or usage of the disinfectant.

[0039] Exemplarily, detailed information of the selected disinfection scheme is extracted from the disinfection scheme database, including the name, chemical composition, concentration and use of the disinfectant. For complex disinfectant mixtures, high performance liquid chromatography-mass spectrometry is used for component decomposition and quantitative analysis. At the same time, the odor component information in the known air is obtained from the odor component database to generate a list of chemical components to be evaluated. Using GROMACS molecular dynamics simulation software, a three-dimensional molecular model containing the chemical composition and odor component of the disinfectant is constructed. The simulation environment parameters are set, including temperature 25°C, relative humidity 60% and standard atmospheric pressure. The chemical reaction simulation program is run, and the ReaxFF reaction force field is used to calculate the reaction probability between each component and the possible reaction products. The simulation duration is set to 100 nanoseconds and the time step is 0.1 femtoseconds. The simulated reaction product information is matched with the toxic and hazardous substance database to determine whether there are potential toxic and hazardous substances. If so, its generated concentration is calculated and compared with the preset safety threshold. The safety threshold refers to the World Health Organization's indoor air quality guidelines and national occupational health standards, and a more stringent standard value is selected. The hazard level assessment results are obtained, including the name of the substance, the predicted concentration and the excess multiple. The evaluation results are passed to the next step in JSON format. According to the results of the hazard assessment, if it is judged that toxic and hazardous substances exceeding the safety threshold will be generated, the disinfection scheme optimization program based on genetic algorithm is started. New alternative disinfection schemes are generated by adjusting the type, concentration or usage of disinfectants. The optimization objective function considers three factors: disinfection effect, risk of hazardous substance generation and economic cost. The population size is set to 100, the number of iterations is 50, the crossover probability is 0.8, and the mutation probability is 0.1. The optimal scheme of each iteration is returned for evaluation until the optimal disinfection scheme that does not produce hazardous substances is found. In the evaluation of the disinfection scheme of a hospital operating room, the selected 0.5% peracetic acid solution disinfection scheme was extracted. High performance liquid chromatography-mass spectrometry analysis showed that the main components of the solution were 0.5% peracetic acid, 0.3% acetic acid and 0.2% hydrogen peroxide. The odor component database shows that there are 0.05ppm formaldehyde and 0.01ppm benzene in the air. The GROMACS software constructed a three-dimensional molecular model containing these components and performed a 100 nanosecond simulation at 25°C, 60% relative humidity and 1 standard atmosphere. ReaxFF force field calculations show that the probability of peracetic acid reacting with formaldehyde is 0.15, and formic acid and acetic acid may be produced. The simulation predicts that the formic acid concentration can reach 0.02ppm. Compared with the World Health Organization's indoor air quality guidelines, the safety threshold of formic acid is 0.01ppm. The evaluation results are transmitted in JSON format as {"substance":"formic acid

[0040] ","concentration":0.02,"threshold":0.01,"exceed_rate":2}. The genetic algorithm optimization program was started with a population size of 100 and 50 iterations. The objective function was set to f = 0.5 disinfection effect - 0.3 hazardous substance risk - 0.2*cost. The optimal solution found in the 27th iteration was 0.3% peracetic acid solution combined with ultraviolet irradiation. This solution was simulated again by GROMACS, predicting that the formic acid concentration dropped to 0.008ppm, which is below the safety threshold, while maintaining 95% disinfection effect. A new disinfection guidance scheme was generated, including solution preparation and ultraviolet irradiation parameters.

[0041] Analyze the selected disinfection scheme, extract the active chemical components in all disinfectants, and based on the odor component information, obtain a list of chemical substances of all odor components known to exist in the air, predict all chemical reactions that may occur between disinfectant components and odor components, and analyze and identify potential toxic and harmful substances.

[0042] The chemical composition information of the disinfectant is obtained, and the information of the odor components known to exist in the air is obtained; a comprehensive chemical substance list is generated based on the chemical composition information and the odor component information. According to the molecular structure and reactivity of each component in the comprehensive chemical substance list, the chemical reaction that can occur between the disinfectant component and the odor component is determined, and a potential reaction product list including reactants, products, and reaction conditions is generated. A toxicity assessment is performed for each compound in the potential reaction product list using a quantitative structure-activity relationship model; the potential reaction products are classified into hazard levels according to the toxicity assessment results to obtain a list of potential toxic and harmful substances. Based on a computational fluid dynamics model, the generated concentration of potential toxic and harmful substances is quantitatively predicted in combination with the disinfectant dosage, odor component concentration, and environmental parameters; the diffusion process of toxic and harmful substances in the air is simulated, and the equilibrium concentration of toxic and harmful substances at each point in space is calculated. The equilibrium concentration is compared with a preset toxicological threshold; if the equilibrium concentration exceeds the toxicological threshold, it is determined to be a high-risk toxic and harmful substance; uncertainty analysis and sensitivity analysis are performed on the high-risk toxic and harmful substances.

[0043] Exemplarily, according to the selected disinfection scheme, the chemical composition information of the disinfectant is extracted from the disinfectant database, and the complex disinfectant mixture is analyzed by high performance liquid chromatography-mass spectrometry to identify and extract the active chemical components. At the same time, the information of all odor components known to exist in the air is obtained to generate a comprehensive chemical list containing active ingredients and odor components of the disinfectant. Density functional theory calculations are used to predict all chemical reactions that may occur between disinfectant components and odor components based on the molecular structure and reactivity of each component in the comprehensive chemical list. Considering reaction kinetics and thermodynamic factors, a list of potential reaction products is generated, including reactants, products, reaction conditions, reaction probability and Gibbs free energy change. The list of potential reaction products is passed to the next step in JSON format. Using the quantitative structure-activity relationship model, the toxicity of each compound in the list of potential reaction products is evaluated, including acute toxicity, carcinogenicity, teratogenicity and mutagenicity. The reaction products are classified into hazard levels according to the predicted results to generate a list of potential toxic and hazardous substances. The random forest algorithm is used to verify and optimize the prediction results to improve the prediction accuracy. Based on the computational fluid dynamics model, the generation concentration of potential toxic and harmful substances is quantitatively predicted by combining the amount of disinfectant, the concentration of odor components in the air and environmental parameters. The diffusion process of toxic and harmful substances in the air is simulated to calculate their equilibrium concentrations at various points in space. The predicted concentrations are compared with the relevant toxicological thresholds, and uncertainty analysis and sensitivity analysis are performed to finally determine the high-risk toxic and harmful substances that need to be focused on. In the evaluation of the disinfection program of a hospital operating room, a 0.5% peracetic acid solution disinfectant was analyzed. High-performance liquid chromatography-mass spectrometry analysis showed that the main components of the solution were 0.5% peracetic acid, 0.3% acetic acid and 0.2% hydrogen peroxide. The odor component database showed that there were 0.05ppm formaldehyde and 0.01ppm benzene in the air. Density functional theory calculations using the B3LYP / 6-31G(d) basis set predicted that the Gibbs free energy change of the reaction between peracetic acid and formaldehyde was -15.3kJ / mol, and the reaction probability was 0.78. The main reaction product was formic acid, with a predicted concentration of 0.03 ppm. Quantitative structure-activity relationship model evaluation showed that the acute toxicity LD50 of formic acid was 1100 mg / kg, which was lower than the high-risk threshold of 50 mg / kg. The random forest algorithm, with 500 trees and a maximum depth of 10, verified the prediction results with an accuracy of 95%. The computational fluid dynamics model used the k-ε turbulence model to simulate the operating room space of 20m×15m×3m. The results showed that under ventilation conditions with an air change rate of 6 times / hour, the maximum concentration of formic acid appeared within 1.5m of the disinfection point, which was 0.02ppm, lower than the occupational exposure limit of 5ppm. Sensitivity analysis showed that ventilation conditions had the greatest impact on concentration distribution, and increasing the air change rate to 8 times / hour could reduce the maximum concentration to 0.015ppm.It was ultimately determined that formic acid was a medium-risk substance, and it was recommended to increase ventilation during the disinfection process.

[0044] Step S107, according to the optimized disinfection scheme, control the air conditioning system to enter the disinfection mode, adjust the fresh air introduction ratio and filtration efficiency level, spray disinfectant in key areas, and monitor the disinfection effect in real time.

[0045] Switch the air conditioning system to disinfection mode, which includes the fresh air introduction ratio and the filter efficiency level; wherein the fresh air introduction ratio is obtained by comparing the indoor and outdoor air quality indexes, and the filter efficiency level is adjusted to a preset level. Receive spraying instructions for key areas, and spray disinfectants according to the spraying instructions at preset time intervals and dosages; obtain environmental parameter data, which are collected by a sensor network distributed in various areas; wherein the sensor network includes temperature and humidity sensors, VOC sensors, particulate matter sensors, and special disinfectant concentration sensors. Calculate the disinfection effect index, which is based on real-time environmental parameter data and a pre-established disinfection effect evaluation model. Determine whether the disinfection effect index meets the preset conditions; if the disinfection effect index does not meet the preset conditions, adjust the air conditioning parameters and the disinfectant spraying strategy; wherein the air conditioning parameters include the fresh air introduction ratio and the filter efficiency level, and the disinfectant spraying strategy includes the spraying time interval and dosage.

[0046] Exemplarily, according to the optimized disinfection scheme, a command is sent to the air conditioning control system to switch the air conditioning system to disinfection mode. Based on the comparison of indoor and outdoor air quality indexes, the proportion of fresh air introduction is calculated. When the outdoor air quality index is lower than that of the indoor air, the proportion of fresh air is increased to 80%, otherwise it is reduced to 20%. At the same time, the filter efficiency level is increased to MERV13 to achieve an 85% filtration rate for 0.3-1.0 micron particles, balancing air purification and disinfectant diffusion. Through remote control, the automatic spraying device in key areas is activated, and the spraying is sprayed every 30 minutes at a preset time interval and a dosage of 5ml / m 2, accurately spray disinfectants. Spraying information is transmitted to the central control unit in real time for subsequent environmental parameter analysis and disinfection effect evaluation. Using the sensor network distributed in various areas, environmental parameter data is collected in real time. The sensors include temperature and humidity sensors, VOC sensors, particulate matter sensors and special disinfectant concentration sensors, with one set installed every 100 square meters. The collected data include temperature, humidity, air flow velocity, VOC concentration, PM2.5 concentration and disinfectant concentration. The data is collected every 5 seconds and transmitted to the central processing unit. The long short-term memory network (LSTM) algorithm is used to dynamically calculate the disinfection effect index by combining real-time environmental parameter data and a pre-established disinfection effect evaluation model. The disinfection effect evaluation model is trained based on historical data and considers the relationship between environmental parameters and microbial survival rate. At the same time, air microbial samples are collected every hour through an automatic sampling device, and the microbial content is detected using rapid PCR technology to directly evaluate the disinfection effect. According to the calculation results, the air conditioning parameters and disinfectant spraying strategy are automatically adjusted to achieve closed-loop control of the disinfection process. During the disinfection process of an operating room in a hospital, the air conditioning control system receives the optimized disinfection scheme instruction and switches to disinfection mode. Real-time monitoring shows that the outdoor air quality index is 75 and the indoor air quality index is 120. The fresh air introduction ratio is adjusted to 80%. At the same time, the filter efficiency is upgraded to MERV13, and the filtration rate of 0.3-1.0 micron particles reaches 85%. Then the automatic spraying device in the key areas is activated, spraying 0.5% peracetic acid solution every 30 minutes, with a dosage of 5ml / m 2 . Five sets of sensors distributed in the 100-square-meter operating room collected data in real time, showing a temperature of 22°C, a relative humidity of 60%, and a VOC concentration of 0.3 mg / m 3 , PM2.5 concentration 15μg / m 3 , disinfectant concentration 0.2mg / m 3 . These data are transmitted to the central processing unit every 5 seconds. Based on these parameters and the pre-trained model, the LSTM algorithm calculates the current disinfection effect index to be 0.85, with a full score of 1.0. At the same time, the automatic sampling device collects air samples, and the rapid PCR test results show that the total number of bacteria is 50 CFU / m 3 , lower than 500CFU / m before disinfection 3 Based on these results, the air conditioning temperature was automatically lowered by 1°C and the relative humidity was increased by 5% to optimize the disinfectant effect; the final disinfection effect index stabilized at 0.92 and the total bacterial count dropped to 20 CFU / m 3 , meeting the disinfection standards of operating rooms.

[0047] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring the entire process of medical waste based on a smart medical waste monitoring platform, characterized in that: The method comprises: According to the classification of medical waste, a distributed sensor network is used to sample the odor of waste transfer routes in different areas to obtain odor data, including odor concentration data and odor component information; Match the collected odor data with the pre-established medical waste odor component data to determine the type of medical waste to which the odor source belongs and whether the odor concentration exceeds a preset threshold; If the odor concentration exceeds the standard, the microbial information is obtained based on the correlation between the odor component information and the microorganisms, and the risk of microbial growth is evaluated in combination with the temperature and humidity control parameters of the air conditioner; Simulate the air flow distribution of the air conditioning system, combine the location layout of the air conditioning outlets, predict the diffusion path and impact range of odors in different areas of the hospital, and generate an odor diffusion heat map; Based on the odor diffusion heat map, combined with the frequency of air conditioning filter replacement and pipeline cleaning cycle factors, determine the areas that need to be disinfected. At the same time, based on the risk of microbial growth, select a disinfection plan to deal with such odors and microorganisms; According to the selected disinfection scheme, the chemical components of the disinfectant used in the disinfection scheme are extracted, and the potential reaction of the chemical components with the known odor components in the air is evaluated through chemical reaction simulation. According to the evaluation results, if toxic and harmful substances are generated, the disinfection scheme is optimized to avoid secondary pollution; According to the optimized disinfection plan, the air-conditioning system is controlled to enter the disinfection mode, the fresh air introduction ratio and filtration efficiency level are adjusted, disinfectant is sprayed in key areas, and the disinfection effect is monitored in real time.

2. The method according to claim 1, wherein: According to the classification of medical waste types, a distributed sensor network is used to sample the odor of waste transfer routes in different areas to obtain odor data, including odor concentration data and odor component information, including: Obtaining information on sampling areas divided according to pre-established medical waste classification standards, setting up multiple odor sampling points in the sampling areas to form a distributed sensor network covering the waste transfer path; Using a gas sensor array to perform real-time detection on the odor sampling points to obtain odor concentration and component data of each sampling point; The data of different types of sensors are fused according to the weighted average algorithm to determine the comprehensive odor data; Preprocessing the comprehensive odor data to eliminate environmental noise interference through a filtering algorithm; The multi-dimensional odor feature data is reduced in dimension to extract the odor fingerprint feature vector containing the key parameters of gas component concentration ratio, odor intensity and duration.

3. The method according to claim 1, wherein: The method of matching the collected odor data with pre-established medical waste odor component data, determining the type of medical waste to which the odor source belongs, and determining whether the odor concentration exceeds a preset threshold value includes: Acquiring odor data collected by a multi-channel gas sensor array, the odor data including outputs of metal oxide, electrochemical, and photoionization sensors; Dynamically adjust the weight according to the accuracy of each sensor in the historical data, and fuse the odor data using a weighted average method; The fused data is standardized to obtain the odor feature vector in a unified format; Extracting a feature template from a pre-established database of medical waste odor components, wherein the feature template includes typical odor components and concentration ranges of different types of medical waste; Performing dimensionality reduction processing on the odor feature vector, and selecting the first N principal components whose cumulative contribution rates reach a preset value as key odor component information; Using a support vector machine classifier to classify the odor feature vector, the support vector machine classifier uses a radial basis function kernel; Optimizing the kernel parameters and penalty factors of the radial basis function kernel by cross validation; If the output result of the support vector machine classifier matches the preset category, the type of medical waste from which the odor originates is determined; Establishing a preset threshold database, wherein the preset threshold database includes multiple levels of odor concentration thresholds; The cubic spline interpolation algorithm is used to convert the raw sensor signal into a standardized odor concentration value; Determining whether the standardized odor concentration value exceeds a corresponding threshold in the preset threshold database; If the standardized odor concentration value exceeds the preset threshold, an alarm of a corresponding level is triggered according to the degree of excess.

4. The method according to claim 1, wherein: If the odor concentration exceeds the standard, the microbial information is obtained based on the correlation between the odor component information and the microorganisms, and the risk of microbial growth is evaluated in combination with the temperature and humidity control parameters of the air conditioner, including: Obtaining the odor concentration detection result, and judging whether it exceeds a preset threshold value according to the detection result, and triggering a subsequent evaluation process if the detection result exceeds the preset threshold value; The Apriori algorithm is used to analyze the correlation between the odor component information and the microorganisms, the support threshold of the Apriori algorithm is a preset value, and the confidence threshold of the Apriori algorithm is a preset value; According to the correlation analysis results, microbial species highly correlated with odor components are screened out to obtain growth conditions and reproduction rate information of the microbial species; Establishing a microbial growth prediction model, wherein the prediction model calculates the potential growth rate of the microorganism based on the growth conditions, the reproduction rate information, the temperature parameter, and the humidity parameter; Determining whether the potential growth rate exceeds a preset risk level threshold, and if the potential growth rate exceeds the preset risk level threshold, determining a microbial growth risk level; The risk levels include low risk, medium risk and high risk; It also includes: querying the microbial database based on the odor component information to determine the type of microorganisms associated with the odor component, extracting the suitable growth condition information for each identified microorganism, obtaining the current temperature and humidity control parameters of the air conditioner in real time, including temperature setting, humidity control level and fresh air introduction ratio, and calculating the comprehensive breeding risk index of each microorganism based on the suitable growth condition information of the microorganism and the current temperature and humidity control parameters of the air conditioner.

5. The method according to claim 4, wherein: According to the odor component information, a query is performed in the microbial database to determine the type of microorganism associated with the odor component, and the suitable growth condition information of each identified microorganism is extracted, and the temperature and humidity control parameters of the current air conditioner are obtained in real time, including the temperature setting, the humidity control level and the fresh air introduction ratio. According to the suitable growth condition information of the microorganism and the temperature and humidity control parameters of the current air conditioner, the comprehensive breeding risk index of each microorganism is calculated, including: Obtaining odor component information and calculating cosine similarity, wherein the cosine similarity is used to identify associated microorganisms whose matching degree exceeds a preset threshold; Obtaining a unique identifier of the associated microorganism, and using the unique identifier to query information on suitable conditions for microbial growth; The suitable growth condition information includes temperature range, relative humidity range, pH value range and oxygen demand; Acquire temperature and humidity control parameters, wherein the temperature and humidity control parameters include a temperature setting value, a humidity control level, and a fresh air introduction ratio; Standardizing the temperature and humidity control parameters into standardized values; Using a multi-factor weighted scoring model to compare the growth suitable condition information with the standardized value; In the multi-factor weighted scoring model, the temperature factor, humidity factor, pH factor and oxygen demand factor are respectively assigned preset weight values; Determine the degree of hazard of the associated microorganisms; If the hazard level of the associated microorganism exceeds a preset threshold, a comprehensive breeding risk index is calculated for the associated microorganism; The comprehensive breeding risk index is determined by the product of the output result of the multi-factor weighted scoring model and the degree of hazard.

6. The method according to claim 1, wherein: The air flow distribution of the air conditioning system is simulated, and the air outlet position layout is combined to predict the diffusion path and impact range of odor in different areas of the hospital, and generate an odor diffusion heat map, including: Acquire a hospital building information model, and construct a three-dimensional digital model based on the building information model; Dividing the three-dimensional digital model into grid units, and recording the spatial coordinates, temperature, humidity and airflow information of the grid units; Performing computational fluid dynamics simulation on the grid unit to obtain airflow field distribution data; Storing the airflow field distribution data in a three-dimensional matrix form; Receive odor source location and initial concentration information; According to the odor source location and initial concentration information and airflow field distribution data, the Euler-Lagrangian mixed model is used to calculate the odor molecule diffusion process; Obtaining time series concentration distribution data; Analyzing the relationship between the airflow field distribution data and the time series concentration distribution data; Optimizing the position and angle of the air outlet of the air conditioner according to the relationship; generating a continuous concentration distribution field based on the optimized air outlet layout; Mapping the continuous concentration distribution field to a color space to generate an odor diffusion heat map; The odor diffusion heat map is superimposed on the hospital floor plan to display the odor diffusion path and impact range.

7. The method according to claim 1, wherein: The areas that need to be disinfected are determined based on the odor diffusion heat map, combined with the frequency of air conditioning filter replacement and the pipeline cleaning cycle factors, and the disinfection plan for treating such odors and microorganisms is selected based on the risk of microbial growth, including: Obtain odor diffusion heat map data, set odor concentration thresholds based on historical data quantiles, and divide odor pollution areas; The heat map data is matched with the actual spatial position through rasterization processing to obtain a list of key focus areas; According to the filter replacement frequency and pipeline cleaning cycle data, the filter efficiency attenuation model and pipeline pollution accumulation model are established; The pipeline pollution accumulation model uses a logarithmic growth function of P(t)=aln(t+1), where P(t) is the pollution degree at time t and a is the pollution rate coefficient; Calculate the current filter remaining efficiency and pipeline contamination level, and correlate the results with a list of key areas of concern; A multi-factor weighted scoring method was used to score odor concentration, filter efficiency, pipe contamination level, and microbial growth risk; If the score result is within the preset percentage, it will be determined as a key disinfection area; Screen out the appropriate disinfection plan based on the odor type and microbial species in the key disinfection area; Construct a decision tree, where the root node is the odor type, the second-level nodes are the main microbial species, and the third-level nodes are the environmental sensitivity; The optimal disinfection plan is selected through a decision tree, and a disinfection guidance plan is generated including the disinfectant name, usage concentration and application method.

8. The method according to claim 1, wherein: According to the selected disinfection scheme, the chemical components of the disinfectant used in the disinfection scheme are extracted, and the potential reaction of the chemical components with the known odor components in the air is evaluated through chemical reaction simulation. According to the evaluation results, if toxic and harmful substances are generated, the disinfection scheme is optimized to avoid secondary pollution, including: Obtain information of a selected disinfection scheme in a disinfection scheme database, the information including the name, chemical composition, concentration and usage of the disinfectant; constructing a three-dimensional molecular model, wherein the three-dimensional molecular model includes a disinfectant chemical component and an odor component; Running a chemical reaction simulation according to the three-dimensional molecular model to obtain reaction product information; Matching the reaction product information with the toxic and hazardous substance database to determine whether there are potential toxic and hazardous substances; If there are potentially toxic and hazardous substances, calculate their generated concentration and compare it with the preset safety threshold; Deriving a hazard level assessment result based on the comparison result, the hazard level assessment result includes the substance name, predicted concentration and excess multiple; If the hazard level assessment results indicate that toxic and hazardous substances exceeding the safety threshold will be produced, the disinfection program optimization program based on genetic algorithms will be initiated; The disinfection scheme optimization program generates new alternative disinfection schemes by adjusting the type and concentration of disinfectants or the method of use; It also includes: analyzing the selected disinfection scheme, extracting the active chemical components in all disinfectants, obtaining a list of chemical substances of all odor components known to exist in the air based on the odor component information, predicting all chemical reactions that may occur between disinfectant components and odor components, and analyzing and identifying potential toxic and harmful substances.

9. The method according to claim 8, wherein: The analysis of the selected disinfection scheme extracts the active chemical components in all disinfectants, obtains a list of chemical substances of all odor components known to exist in the air based on the odor component information, predicts all chemical reactions that may occur between disinfectant components and odor components, and analyzes and identifies potential toxic and harmful substances, including: Obtain information about the chemical composition of disinfectants and obtain information about known odor components in the air; generating a comprehensive chemical substance list based on the chemical composition information and the odor component information; Determine the chemical reactions that can occur between the disinfectant component and the odor component based on the molecular structure and reactivity of each component in the comprehensive chemical substance list, and generate a potential reaction product list including reactants, products, and reaction conditions; Quantitative structure-activity relationship modeling was used to evaluate the toxicity of each compound in the list of potential reaction products; According to the toxicity assessment results, potential reaction products are classified into hazard levels to obtain a list of potential toxic and hazardous substances; Based on the computational fluid dynamics model, the generation concentration of potential toxic and harmful substances is quantitatively predicted by combining the disinfectant dosage, odor component concentration and environmental parameters; Simulate the diffusion process of toxic and hazardous substances in the air and calculate the equilibrium concentration of toxic and hazardous substances at various points in space; comparing the equilibrium concentration with a preset toxicological threshold; If the equilibrium concentration exceeds the toxicological threshold, it is determined to be a high-risk toxic and hazardous substance; Conduct uncertainty analysis and sensitivity analysis on the high-risk toxic and hazardous substances.

10. The method according to claim 1, wherein: According to the optimized disinfection scheme, the air conditioning system is controlled to enter the disinfection mode, the fresh air introduction ratio and the filtration efficiency level are adjusted, and disinfectants are sprayed in key areas to monitor the disinfection effect in real time, including: Switching the air conditioning system to a disinfection mode, wherein the disinfection mode includes a fresh air introduction ratio and a filter efficiency level; Wherein, the fresh air introduction ratio is obtained based on the comparison of indoor and outdoor air quality indexes, and the filter efficiency level is adjusted to a preset level; Receive a spraying instruction for a key area, and spray the disinfectant according to a preset time interval and dosage according to the spraying instruction; Acquiring environmental parameter data, wherein the environmental parameter data is collected by a sensor network distributed in various areas; Wherein, the sensor network includes temperature and humidity sensors, VOC sensors, particulate matter sensors and special disinfectant concentration sensors; Calculating a disinfection effect index, the disinfection effect index being based on real-time environmental parameter data and a pre-established disinfection effect evaluation model; Determine whether the disinfection effect index meets the preset conditions; If the disinfection effect index does not meet the preset conditions, the air conditioning parameters and the disinfectant spraying strategy are adjusted; Among them, the air conditioning parameters include the fresh air introduction ratio and the filter efficiency level, and the disinfectant spraying strategy includes the spraying time interval and dosage.

Images