Medical environment air quality management method, system, equipment and medium

Abstract

The invention provides a medical environment air quality management method, system, equipment and medium, and relates to the technical field of environment air quality management.The medical environment air quality management method includes the steps that according to real-time data of a surrounding environment monitoring station outside a hospital and an air quality monitoring device in the hospital, a distribution map reflecting indoor and outdoor pollutant concentration is obtained through data fusion and calibration processing; performing pattern recognition on the distribution map by using a machine learning algorithm to obtain key features of medical environment air quality, and intelligently generating a customized air quality improvement scheme; processing through a near-end strategy optimization algorithm to obtain an equipment operation scheduling strategy; carrying out dynamic processing by utilizing a PID control algorithm to obtain dynamically adjusted equipment operation parameters; and the air quality of the medical environment is correspondingly managed through processing of an anomaly detection algorithm. According to the invention, a more intelligent and efficient air quality management scheme can be provided for hospitals.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental air quality management, and in particular to a medical environmental air quality management method, system, equipment and medium. Background Art

[0002] With the development of medical technology and the improvement of medical quality requirements, the air quality management of hospital environment has become more and more important. At present, hospital air quality management mainly relies on traditional air purification technology and manual monitoring methods, such as the use of high-efficiency air filters (HEPA), ultraviolet disinfection lamps and chemical disinfectants.

[0003] However, these methods have some problems, such as low efficiency, high cost, slow response, and inability to adapt to changes in air quality in real time. Existing technologies usually use regular maintenance and manual inspections to ensure air quality, but this method lacks flexibility and predictive ability, and it is difficult to meet the needs of modern hospitals for rapid response to air quality. Summary of the invention

[0004] The purpose of the present invention is to provide a medical environment air quality management method, system, equipment and medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows: In a first aspect, the present application provides a method for managing air quality in a medical environment, comprising: Based on the real-time data from the hospital's external environment monitoring station and the hospital's air quality monitoring device, after data fusion and calibration processing, a distribution map reflecting the indoor and outdoor pollutant concentrations is obtained. The external environment monitoring station includes the external air quality index and related real-time weather forecast data, and the hospital's air quality monitoring device includes the devices installed at designated locations in the hospital. Use machine learning algorithms to perform pattern recognition on distribution maps to obtain key features of medical environment air quality, combine the strategies that managers input into the system based on temporary or actual conditions to improve air quality, and intelligently generate customized air quality improvement plans; Based on the air quality improvement plan, the equipment operation scheduling strategy is obtained through processing by the proximal strategy optimization algorithm; According to the equipment operation scheduling strategy, the PID control algorithm is used for dynamic processing to obtain the dynamically adjusted equipment operation parameters; Based on the equipment operating parameters and the environmental feedback of the real-time monitoring equipment, the abnormal warning signal is obtained through the abnormal detection algorithm, and a response is made to the abnormal warning signal, so as to manage the air quality of the medical environment accordingly.

[0005] Preferably, the real-time data from the hospital's surrounding environment monitoring station and internal monitoring devices are fused and calibrated to obtain a distribution map reflecting the indoor and outdoor pollutant concentrations, including: Based on the real-time data from the hospital's surrounding environmental monitoring stations and internal monitoring devices, the data is preprocessed and processed using image recognition technology, including converting the numerical information in the chart into digital format to obtain the original time series data set; The time series data set is fused using the weighted average method, and the real-time data of the hospital's internal monitoring device is combined to obtain a fused data set. The weighted average method assigns different weights to the data at different monitoring points. wi To calculate the average value of pollutant concentration; Based on the fused data set, the principal components of the data are obtained through principal component analysis, and finally the calibrated PCA components are obtained, where PCA transforms the multidimensional data into a new coordinate system through singular value decomposition; The calibrated PCA components were visualized using a data visualization library, and the calibrated data were mapped to geographic coordinates to generate a distribution map reflecting indoor and outdoor pollutant concentrations.

[0006] Preferably, the visualizing the calibrated PCA components using a data visualization library comprises: Based on the calibrated pollutant concentration data, associate it with the geographic location in terms of latitude and longitude and select a data visualization library; Define a color mapping scheme that maps the range of pollutant concentration values ​​to a color gradient where blue represents low concentrations and red represents high concentrations, and create the color gradient in the visualization tool; Use color coding to plot pollutant concentration data on the map, ensure that the color of each area is selected from the color gradient based on its concentration value, add a legend that explains the relationship between color coding and pollutant concentration, and adjust the color gradient, legend, and other visual elements of the map as needed, where color coding is used to represent pollutant concentration levels in different areas.

[0007] Preferably, the distribution graph is subjected to pattern recognition using a machine learning algorithm to obtain key features of the medical environment air quality, including: Extracting original time series data from the distribution map, where the distribution map displays the change of pollutant concentration in the form of a chart, including data from multiple monitoring points; Cleaning the collected time series data, including processing missing values, outliers and duplicate values, to obtain cleaned data, integrating the data from different monitoring stations or monitoring devices with the cleaned data to obtain fused data, and calibrating the fused data to obtain preprocessed data; The preprocessed data is decomposed into several intrinsic mode functions using the VMD algorithm. The optimal solution of the variational mode is searched iteratively, each mode function and the center frequency are updated, and the intrinsic mode function after VMD decomposition is obtained. The bidirectional gated recurrent unit network is used to extract the features of the intrinsic mode function after VMD decomposition to obtain the key features reflecting the changes in air quality.

[0008] Preferably, the air quality improvement plan is processed by a proximal strategy optimization algorithm to obtain a device operation scheduling strategy, which includes: Based on the goals and constraints of the air quality improvement plan, a mixed integer linear programming model is constructed through mathematical modeling. The objective function of the mixed integer linear programming model includes minimizing energy consumption and maximizing air quality improvement effects, and the constraints include equipment operation restrictions and pollutant emission standards. The mixed integer linear programming model is processed by the branch and bound algorithm to solve the model and obtain the optimal solution. The branch and bound algorithm gradually narrows the range of feasible solutions by systematically searching the decision space until the optimal solution is found. According to the optimal solution, the performance of the strategy in the simulation environment is verified through simulation processing. The simulation constructs a virtual environment to simulate the air quality changes and energy consumption of the equipment when it runs according to the optimal solution, and then obtains the simulation results, including air quality indicators and energy consumption data; The simulation results are processed using a multi-index evaluation method to evaluate the effectiveness of the scheduling strategy, and the strategy is evaluated to obtain the final equipment operation scheduling strategy, in which the equipment operation scheduling strategy takes into account the air quality improvement effect and energy consumption. The multi-index evaluation method includes the dimensions of renewable energy absorption ratio, scheduling response time, load smoothness and economic benefits.

[0009] In a second aspect, the present application also provides a medical environment air quality management system, comprising: The first processing module is used to obtain a distribution map reflecting the indoor and outdoor pollutant concentrations based on the real-time data from the hospital's surrounding environmental monitoring stations and internal monitoring devices through data fusion and calibration processing; Feature recognition module: used to use machine learning algorithms to perform pattern recognition on the distribution map, obtain key features of medical environment air quality, and intelligently generate customized air quality improvement plans based on the hospital's internal activity arrangements and patient condition data; The second processing module is used to obtain the equipment operation scheduling strategy based on the air quality improvement plan through the proximal strategy optimization algorithm; The third processing module is used to dynamically process the equipment operation parameters by using the PID control algorithm according to the equipment operation scheduling strategy; Management module: It is used to obtain abnormal warning signals based on the equipment operating parameters and real-time monitoring equipment environmental feedback, and respond to the abnormal warning signals after being processed by the abnormal detection algorithm, so as to manage the medical environment air quality accordingly.

[0010] In a third aspect, the present application also provides a medical environment air quality management device, comprising: Memory for storing computer programs; A processor is used to implement the steps of the medical environment air quality management method when executing the computer program.

[0011] In a fourth aspect, the present application also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned medical environment air quality management method are implemented.

[0012] The beneficial effects of the present invention are: The present invention uses advanced data processing technology and intelligent optimization algorithms to achieve real-time monitoring and optimization of air quality inside and outside the hospital. First, the mixed integer linear programming (MILP) model is used to transform the air quality improvement plan into an optimization problem, where the decision variables x represents the operating status of the equipment. The objective function aims to minimize energy consumption, and constraints are set to ensure that the equipment operates within a safe and effective range. Then, the proximal strategy optimization algorithm is used to adjust the equipment operating parameters through an iterative learning strategy to achieve air quality goals while optimizing energy consumption. Finally, the effectiveness of the strategy is verified through simulation, and its impact on air quality improvement and energy consumption is evaluated to generate the final equipment operation scheduling strategy. This method can provide a more intelligent and efficient air quality management solution for sensitive environments such as hospitals.

[0013] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 It is a schematic diagram of the process of the medical environment air quality management method described in an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of the medical environment air quality management system described in an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of the medical environment air quality management device described in an embodiment of the present invention.

[0016] In the figure: 701, first processing module; 702, identification feature module; 703, second processing module; 704, third processing module; 705, management module; 800, medical environment air quality management equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, 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 part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0018] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0019] Embodiment 1:

[0020] This embodiment provides a method for managing air quality in a medical environment.

[0021] See also Figure 1 , the figure shows that the method includes step S100, step S200, step S300, step S400 and step S500.

[0022] S100. Based on the real-time data from the hospital's off-site environmental monitoring station and the hospital's air quality monitoring device, after data fusion and calibration processing, a distribution map reflecting the concentration of indoor and outdoor pollutants is obtained, wherein the off-site environmental monitoring station includes the off-site air quality index and related real-time weather forecast data, and the hospital's air quality monitoring device includes devices installed at designated locations in the hospital.

[0023] In this step, air quality monitoring devices are distributed in various areas of the medical environment, such as wards, operating rooms, outpatient clinics, etc., and use advanced sensor technology based on quantum sensing, which can detect a variety of pollutants and gases with high precision and high sensitivity, including particulate matter concentration, harmful gas concentration, oxygen concentration, ozone concentration, volatile organic matter concentration, temperature, humidity, negative oxygen ion concentration, etc.; air quality improvement equipment includes air purifiers, air disinfectors, volatile organic matter removal equipment, harmful gas removal equipment, ozone removal equipment, negative oxygen ion generators, fresh air systems, oxygen distribution meters, temperature control equipment, humidity control equipment, etc., which are distributed in various areas of the hospital and work together according to the instructions of the central control system to improve air quality; the central control system is the core of the entire system, responsible for receiving and processing data from the air quality monitoring device, and using big data analysis and deep learning algorithms for in-depth mining and analysis. According to the preset algorithms and strategies, as well as the number of patients in the hospital, the distribution of diseases and other factors, the operation strategy of the air quality improvement equipment is intelligently adjusted. When the air quality is detected to be abnormal or about to be abnormal, it can automatically link related equipment for coordinated adjustment.

[0024] It can be understood that the step S100 includes S101, S102, S103 and S104, wherein: S101, based on the real-time data from the hospital's surrounding environment monitoring stations and internal monitoring devices, the data is processed by data preprocessing and image recognition technology, wherein the processing process includes converting the numerical information in the chart into a digital format to obtain an original time series data set; S102, using the weighted average method to fuse the time series data set, combined with the real-time data of the hospital's internal monitoring device, to obtain a fused data set, wherein the weighted average method assigns different weights to the data at different monitoring points. wi To calculate the average value of pollutant concentration, the calculation formula is as follows:

[0025] In the formula, Ci It is i The pollutant concentration at each monitoring point is wi is the corresponding weight, Cavg represents the weighted average of all monitoring points, and n is the total number of monitoring points; Among them, according to the real-time data of the hospital's surrounding environment monitoring station and the air quality monitoring device inside the hospital, after data fusion processing, a distribution map reflecting the indoor and outdoor pollutant concentration is obtained. In this step, the data provided by the monitoring station outside the hospital includes the air quality index (AQI) and related real-time weather forecast data, while the monitoring device inside the hospital includes sensor data installed at designated locations in the hospital. By fusing these data through the weighted average method, the redundancy between the data can be eliminated to obtain a comprehensive and accurate air quality data set.

[0026] It should be noted that, based on the real-time data from the hospital's surrounding environmental monitoring stations and internal monitoring devices, these data may exist in the form of charts, such as air quality distribution maps. After image recognition technology processing, the numerical information in the chart is converted into a digital format to obtain the original time series data set. In this step, OCR technology may be used to identify and convert the data in the image. The calculation process involved includes image binarization, edge detection, character segmentation and recognition, etc., which converts non-digital chart information into a digital format that can be used for further analysis, providing a basic data set for subsequent data fusion and calibration processing.

[0027] In step S102, the time series data set is fused using the weighted average method, combined with the real-time data from the hospital's internal monitoring devices. The weighted average method calculates the average value of pollutant concentration by assigning different weights to the data at different monitoring points. This method takes into account the reliability and accuracy of different monitoring points and improves the accuracy of air quality assessment. The technical effect of this step is to generate a more comprehensive and accurate air quality data set that integrates information from multiple monitoring points and reduces the impact of abnormal data from a single monitoring point on the overall assessment through the weighted average method.

[0028] S103, based on the fused data set, the main components of the data are obtained through principal component analysis, and finally the calibrated PCA components are obtained, wherein PCA transforms the multidimensional data into a new coordinate system through singular value decomposition, and its calculation formula is as follows:

[0029] In the formula, X is the original data matrix, P is from X The calculated eigenvector matrix, Y is the transformed data matrix; S104, using a data visualization library to visualize the calibrated PCA components, mapping the calibrated data to geographic coordinates, and generating a distribution map reflecting indoor and outdoor pollutant concentrations.

[0030] It should be noted that based on the fused data set, the main components of the data are obtained through principal component analysis (PCA). PCA transforms multidimensional data into a new coordinate system through singular value decomposition, where PCA aims to extract the most important features in the data, reduce the data dimension, and retain the most critical information. The technical effect of this step is to extract the key components reflecting air quality through dimensionality reduction technology, which helps to simplify the complexity of subsequent analysis and improve the efficiency of data processing. The calibrated PCA components are visualized using a data visualization library, and the calibrated data are mapped to geographic coordinates to generate a distribution map reflecting indoor and outdoor pollutant concentrations. This step may be implemented using GIS software or a data visualization library (such as Python's matplotlib or Plotly). The technical effect of this step is to generate an intuitive pollutant concentration distribution map, so that the distribution of air quality is clear at a glance, which is convenient for taking corresponding management measures.

[0031] In practical applications, these steps can provide hospitals with a real-time air quality monitoring and early warning system. Through continuous analysis and visualization of monitoring data, hospital managers can quickly identify air quality problem areas and take timely measures to improve air quality. In addition, this data can also be used to develop long-term air quality improvement plans and maintain continuous optimization of the hospital environment.

[0032] In this step, step S104 includes S1041, S1042 and S1043, wherein: S1041. According to the calibrated pollutant concentration data, associate it with the geographical location related to longitude and latitude, and select a data visualization library; it should be noted that according to the calibrated pollutant concentration data, these data may be collected by various monitoring devices and processed by principal component analysis (PCA). Associating these data with geographical location information usually involves matching longitude and latitude. This process may require geographic information system (GIS) software or data visualization libraries, such as Python's matplotlib or Plotly, to process and display geographical data. In this step, a comprehensive data set containing pollutant concentration and geographical location information is created, providing the necessary data basis for subsequent visualization. In certain specific cases, such as air quality monitoring in mountainous areas or high-rise buildings, altitude data may have a significant impact on the distribution of pollutant concentrations. In these cases, it is possible to consider incorporating altitude data into the association of geographical location to provide more precise analysis. For a building complex such as a hospital, air quality may vary depending on the floor. For example, high floors may be affected by different wind forces and air flow patterns. In this case, it is possible to consider location association by building and floor to analyze and adjust air quality management strategies in more detail. Therefore, in actual management, it can be decided whether to include altitude or floor data based on the specific needs of the hospital and the purpose of monitoring. For example, if the hospital needs to optimize the air purification system on a specific floor, it becomes more important to associate locations by floor. When choosing a data visualization library, consider whether it supports visualization of geographic coordinate data, including two-dimensional and three-dimensional data. Many modern data visualization libraries, such as Cesium, Plotly, Folium, and Kepler.gl, provide rich geospatial data visualization functions, including scatter plots, heat maps, flow maps, etc., which can meet the needs of different levels of geographic data display.

[0033] S1042. Define a color mapping scheme to map the numerical range of pollutant concentrations to a color gradient, where blue represents low concentrations and red represents high concentrations, and create the color gradient in a visualization tool; It is understood that a color mapping scheme is defined to map the numerical range of pollutant concentrations to a color gradient. This color gradient is usually a sequence of color changes from low concentration to high concentration, such as a gradient from blue (low concentration) to red (high concentration). Creating this color gradient in a visualization tool may involve the use of a color mapping table. The technical effect of this step is to convert complex numerical data into intuitive color differences through a color mapping scheme, allowing users to identify pollutant concentration levels in different areas at a glance.

[0034] S1043. Use color coding to plot pollutant concentration data on the map, ensuring that the color of each area is selected from the color gradient according to its concentration value, and add a legend to illustrate the relationship between color coding and pollutant concentration, and adjust the color gradient, legend and other visual elements of the map as needed, where the color coding is used to represent the pollutant concentration level in different areas, and the calculation formula is as follows:

[0035] In the formula, V ( x , y ) is the geographic coordinate( x , y ), C ( x , y ) is the pollutant concentration at that location, f is the color coding function.

[0036] It is understandable that in the above formula, in practical applications, such as hospital ambient air quality management, it may be necessary to decide whether to include altitude data based on the specific layout of the building. For example, if a hospital building has multiple floors and the air quality on different floors is significantly different, you can consider incorporating floor information (which can be regarded as a kind of altitude) into the geographic coordinate system. In this way, pollutant concentration data can be associated and analyzed through more detailed geographic coordinates (such as longitude and latitude plus floor number). Therefore, in certain cases, it is necessary to consider altitude or floor information for more accurate air quality monitoring and visualization.

[0037] In addition, the pollutant concentration data is plotted on the map using color coding, a process that involves mapping the data associated with the geographical location to the corresponding color according to its concentration value. The color of each area is selected from a color gradient according to its concentration value. A legend is added to illustrate the relationship between color coding and pollutant concentration to ensure that the visualization is clear and easy to understand. By generating an intuitive pollutant concentration distribution map, the air quality status of different areas is intuitively displayed through color changes, which is convenient for users to quickly understand and analyze. This method can be applied to hospital environmental management departments to monitor and improve the air quality in and around hospitals. With the distribution map updated in real time, the management department can quickly identify pollution hotspots and take corresponding measures. In addition, this visualization tool can also be used to convey air quality information to the public and raise public awareness of environmental issues.

[0038] S200 uses machine learning algorithms to perform pattern recognition on distribution maps to obtain key features of medical environment air quality, combined with strategies that affect improving air quality input by managers in the system based on temporary or actual conditions, and intelligently generates customized air quality improvement plans.

[0039] It can be understood that step S200 includes S201, S202, S203 and S204, wherein: S201, extracting original time series data from a distribution map, wherein the distribution map displays changes in pollutant concentrations in the form of a chart, and includes data from multiple monitoring points; In this step, the original time series data is extracted from the distribution maps, which usually show the changes in pollutant concentrations in the form of graphs and contain data from multiple monitoring points. The extraction process may involve image recognition technology, such as OCR technology, to convert the numerical information in the graph into a digital format for further analysis.

[0040] S202, cleaning the collected time series data, including processing missing values, outliers and duplicate values, to obtain cleaned data, integrating data from different monitoring stations or monitoring devices with the cleaned data to obtain fused data, and calibrating the fused data to obtain preprocessed data; In this step, the collected time series data is cleaned to handle missing values, outliers, and duplicate values. Data cleaning is a key step in data preprocessing. Missing values ​​can be handled by interpolation, deletion, or replacement; outliers can be identified and processed by methods such as box plots; and duplicate values ​​can be identified and deleted by data comparison and logical checks. The data from different monitoring stations or monitoring devices are integrated with the cleaned data to obtain fused data. This step may involve operations such as data alignment, format unification, and time synchronization. The fused data is calibrated to obtain preprocessed data. The calibration process may include using known standard substances or reference data to adjust the monitoring data to ensure the accuracy and consistency of the data, providing high-quality input for subsequent data analysis and pattern recognition.

[0041] S203, using the VMD algorithm to decompose the preprocessed data into a number of intrinsic mode functions, iteratively searching for the optimal solution of the variational mode, updating each mode function and the center frequency, and obtaining the intrinsic mode function after VMD decomposition; It should be noted that the preprocessed data is decomposed into several intrinsic mode functions (IMFs) using the variational mode decomposition (VMD) algorithm. VMD is an adaptive, non-recursive signal processing method that determines the center frequency and bandwidth of each decomposition component by iteratively searching for the optimal solution of the variational model, decomposing complex time series data into multiple relatively simple IMFs. Each IMF represents a specific frequency component in the data, which is helpful for subsequent feature extraction and analysis.

[0042] S204, using a bidirectional gated recurrent unit network to extract features of the intrinsic mode function after VMD decomposition to obtain key features reflecting changes in air quality.

[0043] It should be noted that the bidirectional gated recurrent unit network (BiGRU) is used to extract features from the intrinsic mode function after VMD decomposition. BiGRU is a variant of a recurrent neural network that can capture long-term and short-term dependencies in time series data and effectively handle the retention and transmission of information through its gating mechanism. The technical effect of this step is to extract key features that reflect changes in air quality, which can be used for subsequent air quality prediction, trend analysis, and decision support. In practical applications, these steps can provide a real-time air quality monitoring and early warning system for hospital environmental management departments. Through real-time updated distribution maps, management departments can quickly identify pollution hotspots and take corresponding measures.

[0044] S300: Based on the air quality improvement plan, the equipment operation scheduling strategy is obtained by processing through the proximal strategy optimization algorithm.

[0045] It can be understood that step S300 includes S301, S302, S303 and S304, wherein: S301. Based on the objectives and constraints of the air quality improvement plan, a mixed integer linear programming model is constructed through mathematical modeling, wherein the objective function of the mixed integer linear programming model includes minimizing energy consumption and maximizing air quality improvement effect, and the constraints include equipment operation restrictions and pollutant emission standards; According to the objectives and constraints of the air quality improvement plan, a mixed integer linear programming (MILP) model is constructed after mathematical modeling. The objective function of the model is designed to minimize energy consumption and maximize the air quality improvement effect, which usually involves a multi-objective optimization problem. Multiple objectives can be integrated into a single objective function through the weighted sum method. Constraints include equipment operation restrictions, such as the maximum opening time of the air purifier and the maximum power limit of the fan, as well as pollutant emission standards, such as the indoor carbon dioxide concentration must not exceed the set threshold.

[0046] S302. The mixed integer linear programming model is processed by a branch and bound algorithm to obtain an optimal solution for the model, wherein the branch and bound algorithm gradually narrows the range of feasible solutions by systematically searching the decision space until the optimal solution is found; the mixed integer linear programming model is processed by a branch and bound algorithm to obtain an optimal solution for the model. The branch and bound algorithm is a systematic enumeration method that narrows the search range by continuously decomposing the problem into smaller sub-problems (branches) and calculating the boundaries (bounds) of each sub-problem. During the solution process, if the boundary value of a sub-problem can no longer be better than the currently known optimal solution, the sub-problem will be pruned to reduce the amount of calculation.

[0047] S303, according to the optimal solution, verify the performance of the strategy in the simulation environment through simulation processing, wherein the simulation constructs a virtual environment to simulate the air quality changes and energy consumption of the equipment when it runs according to the optimal solution, and then obtains the simulation results, including air quality indicators and energy consumption data; S304. Process the simulation results using a multi-index evaluation method to evaluate the effectiveness of the scheduling strategy, and evaluate the strategy to obtain the final equipment operation scheduling strategy, where the equipment operation scheduling strategy takes into account the air quality improvement effect and energy consumption. The multi-index evaluation method includes the dimensions of renewable energy absorption ratio, scheduling response time, load smoothness, and economic benefits.

[0048] It should be noted that the optimal solution is processed through simulation to verify the performance of the strategy in the simulated environment. Simulation builds a virtual environment to simulate the changes in air quality and energy consumption when the equipment is running according to the optimal solution. This process may involve complex environmental models and equipment models, and it is necessary to accurately simulate the diffusion of pollutants, the operating characteristics of the equipment, and their impact on the environment. Through simulation, the performance of the equipment operation strategy in actual operation can be predicted, and its impact on air quality improvement and energy consumption can be evaluated, providing a basis for the final decision.

[0049] Among them, the present invention can adopt a multivariate time series prediction model, such as an LSTM-AutoEncoder combined model, to make a more accurate prediction of air quality. This model can process multivariate data, such as PM2.5, PM10, SO2, NO2, etc., and combine them with meteorological data to improve the accuracy of the prediction. In addition, an intelligent air quality monitoring system can be used, which integrates an air quality data acquisition and quality control system, an intelligent information display screen, and a series of supporting hardware products. Through technological innovation and optimization, the system significantly improves data accuracy, realizes comprehensive control of the station's operating status, and provides strong support for the scientific, precise, and efficient air quality monitoring work.

[0050] In this step, the effectiveness of the scheduling strategy is evaluated based on the simulation results after being processed by a multi-index evaluation method. The multi-index evaluation method evaluates the strategy from multiple dimensions (such as renewable energy consumption ratio, scheduling response time, load smoothness, and economic benefits). This process may involve the assignment of weights to determine the importance of different indicators in the evaluation process. The technical effect of this step is to generate an equipment operation scheduling strategy that comprehensively considers multiple evaluation indicators. This strategy not only meets the requirements for air quality improvement, but also takes into account energy consumption, economic benefits, and the stability of equipment operation, providing a comprehensive and optimized air quality management solution for the hospital.

[0051] S400, according to the equipment operation scheduling strategy, a PID control algorithm is used for dynamic processing to obtain dynamically adjusted equipment operation parameters.

[0052] It can be understood that in this step, the PID control algorithm is a classic feedback control algorithm, which adjusts the control input according to the deviation of the control object (i.e., the difference between the expected value and the actual value) to achieve the purpose of regulating the control object. The output of the PID controller is the weighted sum of the proportion (P), integral (I) and differential (D) of the deviation. By adjusting these parameters, the PID controller can adapt to different control requirements and system dynamics. The technical effect of this step is to achieve dynamic adjustment of the equipment operating parameters to maintain the air quality within the set optimal range. In this step, the PID control algorithm can be applied to the air quality management system of the hospital. By real-time monitoring of air quality indicators (such as PM2.5, CO2 concentration, etc.), the operating parameters of equipment such as air purifiers and ventilation systems are dynamically adjusted to ensure that the air quality is always in an ideal state. In addition, the PID control algorithm can also be used in combination with other intelligent control algorithms (such as fuzzy control, adaptive control, etc.) to further improve the control accuracy and adaptability. With the development of Internet of Things technology, the PID control algorithm can be integrated into the intelligent building management system to achieve remote monitoring and automatic control, and improve the comfort and safety of the hospital environment.

[0053] Among them, in this embodiment, it is possible to consider combining the air quality monitoring device with the Internet of Things technology to realize real-time data collection and remote monitoring. Through the Internet of Things platform, the air quality monitoring devices inside and outside the hospital can be connected to realize centralized management and analysis of data. This method can improve the real-time and accuracy of the data, provide support for subsequent data processing and decision-making, and can also use deep learning technologies such as LSTM and GRU networks to predict air quality. These models can capture long-term dependencies in time series data, thereby improving the accuracy of predictions. By using these models, changes in air quality over a period of time in the future can be predicted, providing hospitals with early warnings and response measures.

[0054] S500, based on the equipment operation parameters and the environmental feedback of the real-time monitoring equipment, after being processed by the abnormal detection algorithm, an abnormal warning signal is obtained, and a response is made to the abnormal warning signal, so as to manage the medical environment air quality accordingly.

[0055] It is understandable that in this step, based on the equipment operating parameters and the environmental feedback of the real-time monitoring equipment, the abnormal warning signal is obtained after being processed by the anomaly detection algorithm. The anomaly detection algorithm may include statistical methods, machine learning models, or deep learning models that can identify data points that are significantly different from normal behavior. For example, a control chart-based method can be used to detect whether a data point is outside the control limit, indicating that an anomaly may exist. Respond to the abnormal warning signal, which may involve automatically adjusting the equipment operating parameters, notifying maintenance personnel to conduct inspections, or initiating emergency plans. The design of the response mechanism needs to take into account the safety and response speed of the system. The technical effect of this step is to be able to detect and respond to abnormal changes in air quality in a timely manner, so as to manage the air quality of the medical environment accordingly. This helps to prevent possible health risks and ensure the safety of patients and medical staff.

[0056] In practical applications, the anomaly detection system can be integrated into the hospital's intelligent building management system. By continuously monitoring air quality parameters, the system is able to identify abnormal patterns in real time, such as a sudden increase in pollutant concentrations. Once an anomaly is detected, the system can automatically adjust the air purification equipment, such as increasing the operating speed of the air purifier or starting an additional filtration system, to quickly improve air quality. At the same time, the system can also notify hospital managers so that they can take further measures, such as performing equipment maintenance or checking the source of pollution.

[0057] In addition, the anomaly detection system can also be integrated with other hospital management systems (such as patient management systems, ward management systems) to provide more comprehensive environmental and health monitoring. For example, if the air quality in a certain area is abnormal, the system can recommend temporarily transferring patients in that area to protect their health. Among them, in this embodiment, the installation location and method of the air quality monitoring device can ensure that all key areas of the hospital are covered and comprehensive monitoring is achieved. An air quality monitoring device is installed in the central position of the ceiling of each ordinary ward, which can monitor parameters such as particle concentration, harmful gas concentration, oxygen concentration, temperature, humidity and negative oxygen ion concentration in the ward. The installation method adopts a hanging type to ensure that the device does not affect the normal activities in the ward; for special wards (such as infectious disease wards, intensive care units, etc.), in addition to installing a monitoring device in the central position of the ceiling, a small monitoring device is installed in each of the four corners of the ward to more comprehensively monitor the changes in air quality at different locations in the ward. These small monitoring devices are wall-mounted for easy maintenance and replacement; an air quality monitoring device is installed in each of the four corners of the ceiling in the operating room, which can accurately monitor the air quality parameters in the operating room, including particle concentration, harmful gas concentration, bacterial concentration, etc. The installation method is embedded, so that the device is flush with the ceiling surface and does not affect the surgical operation and sterile environment. On the ceiling of the operating room corridor, a monitoring device is installed at a certain distance to monitor the air quality in the corridor to ensure that the environmental quality outside the operating room meets the requirements. The installation method is suspended. Multiple air quality monitoring devices are evenly distributed on the ceiling of the waiting area to monitor the density of people, particulate matter concentration, carbon dioxide concentration and other parameters in the waiting area. The installation method is suspended. A monitoring device is installed in the center of the ceiling of each treatment room to monitor the air quality in the treatment room and provide patients with a good treatment environment. The installation method is suspended, etc.

[0058] Among them, the system sets different air quality priorities and response strategies for different wards. In the operating room, the system always pays close attention to air quality, and takes immediate measures to adjust it once any abnormality is found. In ordinary wards, the system flexibly adjusts the air quality requirements according to the patient's condition and physical condition. For example, for wards for patients with respiratory diseases, the system will focus on the concentration of particulate matter and harmful gases in the air, and appropriately increase the concentration of negative oxygen ions and oxygen to improve the patient's breathing environment; when the hospital receives infectious patients, the system will automatically switch to the corresponding prevention and control mode. It will strengthen the monitoring and removal of harmful gases and microorganisms, and adjust the operation mode of the ventilation system to ensure that the air circulation inside the hospital meets the prevention and control requirements. In the later stage, the air quality monitoring device and air quality improvement equipment will be regularly maintained and maintained to ensure their normal operation. At the same time, the system is regularly upgraded, and the algorithm model and equipment parameters are updated to improve the performance and accuracy of the system.

[0059] In summary, the present invention extracts original time series data from the distribution map by using image recognition technology. The present invention can convert non-digital chart information into a digital format that can be used for further analysis, thereby improving the accuracy and availability of air quality monitoring data; the weighted average method is used to fuse the time series data from different monitoring points. The present invention can perform reasonable data fusion according to the importance and accuracy of the monitoring points, thereby improving the accuracy and reliability of air quality assessment; using a mixed integer linear programming model and a PID control algorithm, the present invention can construct an optimization model and solve the optimal solution according to the objectives and constraints of the air quality improvement plan, thereby optimizing the equipment operation strategy, minimizing energy consumption and maximizing the air quality improvement effect.

[0060] The present invention also uses an anomaly detection algorithm. The present invention can monitor air quality in real time and quickly issue a warning signal when an anomaly is detected, so that the management department can take timely measures to improve the real-time and effectiveness of medical environment air quality management; through principal component analysis (PCA) and data visualization technology, the present invention can convert complex air quality data into an intuitive distribution map, providing decision makers with a clear air quality distribution, thereby improving the efficiency and accuracy of air quality management decisions; through the optimization algorithm to dynamically adjust the equipment operating parameters, the present invention can ensure that while meeting air quality requirements, resources are reasonably used to avoid unnecessary energy waste; by real-time monitoring and optimization of air quality, the present invention can provide hospitals with a more comfortable and safe indoor environment, which is conducive to the rehabilitation of patients and the health of medical staff.

[0061] Embodiment 2:

[0062] like Figure 2As shown, this embodiment provides a medical environment air quality management system, see Figure 2 The system comprises: The first processing module 701 is used to obtain a distribution map reflecting indoor and outdoor pollutant concentrations based on real-time data from the hospital's surrounding environment monitoring station and internal monitoring devices through data fusion and calibration processing; Identification feature module 702: used to use machine learning algorithms to perform pattern recognition on the distribution map, obtain key features of medical environment air quality, and intelligently generate customized air quality improvement plans based on hospital internal activity arrangements and patient condition data; The second processing module 703 is used to obtain a device operation scheduling strategy based on the air quality improvement plan through a proximal strategy optimization algorithm; The third processing module 704 is used to dynamically process the equipment operation parameters by using the PID control algorithm according to the equipment operation scheduling strategy; Management module 705: used to obtain abnormal warning signals based on equipment operating parameters and real-time monitoring equipment environmental feedback after being processed by an abnormal detection algorithm, and respond to the abnormal warning signals, thereby managing the medical environment air quality accordingly.

[0063] Specifically, the first processing module 701 includes: The first processing unit is used to process the real-time data from the hospital's surrounding environment monitoring stations and internal monitoring devices through data preprocessing and image recognition technology, wherein the processing process includes converting the numerical information in the chart into a digital format to obtain the original time series data set; The second processing unit is used to fuse the time series data set using the weighted average method, and combine the real-time data of the hospital's internal monitoring device to obtain a fused data set. The weighted average method gives different weights to the data at different monitoring points. wi To calculate the average value of pollutant concentration, the calculation formula is as follows:

[0064] In the formula, Ci It is i The pollutant concentration at each monitoring point is wi is the corresponding weight, Cavg represents the weighted average of all monitoring points, and n is the total number of monitoring points; Calculation unit: used to obtain the main components of the data through principal component analysis based on the fused data set, and finally obtain the calibrated PCA components. PCA converts multidimensional data to a new coordinate system through singular value decomposition. The calculation formula is as follows:

[0065] In the formula, X is the original data matrix, P is from X The calculated eigenvector matrix, Y is the transformed data matrix; The third processing unit is used to visualize the calibrated PCA components using a data visualization library, map the calibrated data to geographic coordinates, and generate a distribution map reflecting indoor and outdoor pollutant concentrations.

[0066] Specifically, the identification feature module 702 includes: A first extraction unit: used to extract original time series data from a distribution map, wherein the distribution map displays changes in pollutant concentrations in the form of a chart, and includes data from multiple monitoring points; Integration unit: used to clean the collected time series data, including processing missing values, outliers and duplicate values ​​to obtain cleaned data, integrate the data from different monitoring stations or monitoring devices with the cleaned data to obtain fused data, calibrate the fused data to obtain preprocessed data; Decomposition unit: used to decompose the preprocessed data using the VMD algorithm, decompose it into several intrinsic mode functions, iteratively search for the optimal solution of the variational mode, update each mode function and center frequency, and obtain the intrinsic mode function after VMD decomposition; The second extraction unit is used to extract features of the intrinsic mode function after VMD decomposition using a bidirectional gated recurrent unit network to obtain key features reflecting changes in air quality.

[0067] Specifically, the third processing unit includes: Association unit: used to associate the calibrated pollutant concentration data with the latitude and longitude geographic location and select a data visualization library; Create unit: used to define a color mapping scheme, map the numerical range of pollutant concentrations to a color gradient, where blue represents low concentrations and red represents high concentrations, and create the color gradient in the visualization tool; Representation unit; used to plot pollutant concentration data on a map using color coding, ensuring that the color of each area is selected from the color gradient according to its concentration value, and adding a legend to illustrate the relationship between color coding and pollutant concentration, and adjusting the color gradient, legend, and other visual elements of the map as needed, where color coding is used to represent the pollutant concentration levels in different areas, and the calculation formula is as follows:

[0068] In the formula, V (x , y ) is the geographic coordinate( x , y ), C ( x , y ) is the pollutant concentration at that location, f is the color coding function.

[0069] Specifically, the second processing module 703 includes: Modeling processing unit: used to construct a mixed integer linear programming model based on the objectives and constraints of the air quality improvement plan through mathematical modeling, where the objective function of the mixed integer linear programming model includes minimizing energy consumption and maximizing air quality improvement effects, and the constraints include equipment operation restrictions and pollutant emission standards; Solving unit: used to process the mixed integer linear programming model through the branch and bound algorithm to solve the model to obtain the optimal solution, wherein the branch and bound algorithm systematically searches the decision space and gradually narrows the range of feasible solutions until the optimal solution is found; Processing simulation unit: used to verify the performance of the strategy in a simulated environment based on the optimal solution through simulation processing. The simulation constructs a virtual environment to simulate the air quality changes and energy consumption of the equipment when it runs according to the optimal solution, and then obtains the simulation results, including air quality indicators and energy consumption data; Scheduling unit: It is used to process the simulation results using a multi-index evaluation method, evaluate the effectiveness of the scheduling strategy, and evaluate the strategy to obtain the final equipment operation scheduling strategy, in which the equipment operation scheduling strategy takes into account the air quality improvement effect and energy consumption. The multi-index evaluation method includes the dimensions of renewable energy absorption ratio, scheduling response time, load smoothness, and economic benefits.

[0070] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0071] Embodiment 3:

[0072] Corresponding to the above method embodiment, a medical environment air quality management device is also provided in this embodiment. The medical environment air quality management device described below and the medical environment air quality management method described above can refer to each other.

[0073] Figure 3 FIG. 8 is a block diagram of a medical environment air quality management device 800 according to an exemplary embodiment. Figure 3As shown, the medical environment air quality management device 800 includes: a processor 801 and a memory 802. The medical environment air quality management device 800 also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0074] The processor 801 is used to control the overall operation of the medical environment air quality management device 800 to complete all or part of the steps in the above-mentioned medical environment air quality management method. The memory 802 is used to store various types of data to support the operation of the medical environment air quality management device 800, and these data may include, for example, instructions for any application or method operating on the medical environment air quality management device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse or a button, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the medical environment air quality management device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: a Wi-Fi module, a Bluetooth module or an NFC module.

[0075] In an exemplary embodiment, the medical environment air quality management device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned medical environment air quality management method.

[0076] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned medical environment air quality management method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the medical environment air quality management device 800 to complete the above-mentioned medical environment air quality management method.

[0077] Embodiment 4:

[0078] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the medical environment air quality management method described above can refer to each other.

[0079] A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, the steps of the medical environment air quality management method of the above method embodiment are implemented.

[0080] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0082] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for managing air quality in a medical environment, characterized in that: include: Based on the real-time data from the hospital's external environment monitoring station and the hospital's air quality monitoring device, after data fusion and calibration processing, a distribution map reflecting the indoor and outdoor pollutant concentrations is obtained. The external environment monitoring station includes the external air quality index and related real-time weather forecast data, and the hospital's air quality monitoring device includes the devices installed at designated locations in the hospital. Use machine learning algorithms to perform pattern recognition on distribution maps to obtain key features of medical environment air quality, combine the strategies that managers input into the system based on temporary or actual conditions to improve air quality, and intelligently generate customized air quality improvement plans; Based on the air quality improvement plan, the equipment operation scheduling strategy is obtained through processing by the proximal strategy optimization algorithm; According to the equipment operation scheduling strategy, the PID control algorithm is used for dynamic processing to obtain the dynamically adjusted equipment operation parameters; Based on the equipment operating parameters and the environmental feedback of the real-time monitoring equipment, the abnormal warning signal is obtained through the abnormal detection algorithm, and a response is made to the abnormal warning signal, so as to manage the air quality of the medical environment accordingly.

2. The medical environment air quality management method according to claim 1, characterized in that: According to the real-time data from the hospital's surrounding environmental monitoring stations and internal monitoring devices, after data fusion and calibration processing, a distribution map reflecting the indoor and outdoor pollutant concentrations is obtained, including: Based on the real-time data from the hospital's surrounding environmental monitoring stations and internal monitoring devices, the data is preprocessed and processed using image recognition technology, including converting the numerical information in the chart into digital format to obtain the original time series data set; The time series data set is fused using the weighted average method, and the real-time data of the hospital's internal monitoring device is combined to obtain a fused data set. The weighted average method assigns different weights to the data at different monitoring points. wi To calculate the average value of pollutant concentration, the calculation formula is as follows: In the formula, Ci It is i The pollutant concentration at each monitoring point is wi is the corresponding weight, Cavg represents the weighted average of all monitoring points, and n is the total number of monitoring points; Based on the fused data set, the principal components of the data are obtained through principal component analysis, and finally the calibrated PCA components are obtained. PCA transforms multidimensional data into a new coordinate system through singular value decomposition. The calculation formula is as follows: In the formula, X is the original data matrix, P is from X The calculated eigenvector matrix, Y is the transformed data matrix; The calibrated PCA components were visualized using a data visualization library, and the calibrated data were mapped to geographic coordinates to generate a distribution map reflecting indoor and outdoor pollutant concentrations.

3. The medical environment air quality management method according to claim 2, characterized in that: The calibrated PCA components were visualized using the data visualization library, which includes: Based on the calibrated pollutant concentration data, associate it with the geographic location in terms of latitude and longitude and select a data visualization library; Define a color mapping scheme that maps the range of pollutant concentration values ​​to a color gradient where blue represents low concentrations and red represents high concentrations, and create the color gradient in the visualization tool; Use color coding to plot the pollutant concentration data on the map, ensure that the color of each area is selected from the color gradient according to its concentration value, and add a legend to illustrate the relationship between color coding and pollutant concentration, and adjust the color gradient, legend, and other visual elements of the map as needed, where color coding is used to represent the pollutant concentration levels in different areas, and the calculation formula is as follows: In the formula, V ( x , y ) is the geographic coordinate( x , y ), C ( x , y ) is the pollutant concentration at that location, f is the color coding function.

4. The medical environment air quality management method according to claim 1, characterized in that: The machine learning algorithm is used to perform pattern recognition on the distribution map to obtain key features of the medical environment air quality, including: Extracting original time series data from the distribution map, where the distribution map displays the change of pollutant concentration in the form of a chart, including data from multiple monitoring points; Cleaning the collected time series data, including processing missing values, outliers and duplicate values, to obtain cleaned data, integrating the data from different monitoring stations or monitoring devices with the cleaned data to obtain fused data, and calibrating the fused data to obtain preprocessed data; The preprocessed data is decomposed into several intrinsic mode functions using the VMD algorithm. The optimal solution of the variational mode is searched iteratively, each mode function and the center frequency are updated, and the intrinsic mode function after VMD decomposition is obtained. The bidirectional gated recurrent unit network is used to extract the features of the intrinsic mode function after VMD decomposition to obtain the key features reflecting the changes in air quality.

5. The medical environment air quality management method according to claim 1, characterized in that: The air quality improvement plan is processed by the proximal strategy optimization algorithm to obtain the equipment operation scheduling strategy, which includes: Based on the goals and constraints of the air quality improvement plan, a mixed integer linear programming model is constructed through mathematical modeling. The objective function of the mixed integer linear programming model includes minimizing energy consumption and maximizing air quality improvement effects, and the constraints include equipment operation restrictions and pollutant emission standards. The mixed integer linear programming model is processed by the branch and bound algorithm to solve the model and obtain the optimal solution. The branch and bound algorithm gradually narrows the range of feasible solutions by systematically searching the decision space until the optimal solution is found. According to the optimal solution, the performance of the strategy in the simulation environment is verified through simulation processing. The simulation constructs a virtual environment to simulate the air quality changes and energy consumption of the equipment when it runs according to the optimal solution, and then obtains the simulation results, including air quality indicators and energy consumption data; The simulation results are processed using a multi-index evaluation method to evaluate the effectiveness of the scheduling strategy, and the strategy is evaluated to obtain the final equipment operation scheduling strategy, in which the equipment operation scheduling strategy takes into account the air quality improvement effect and energy consumption. The multi-index evaluation method includes the dimensions of renewable energy absorption ratio, scheduling response time, load smoothness and economic benefits.

6. A medical environment air quality management system, based on the medical environment air quality management method according to claim 1, characterized in that: include: The first processing module is used to obtain a distribution map reflecting the indoor and outdoor pollutant concentrations based on the real-time data from the hospital's surrounding environmental monitoring stations and internal monitoring devices through data fusion and calibration processing; Feature recognition module: used to use machine learning algorithms to perform pattern recognition on the distribution map, obtain key features of medical environment air quality, and intelligently generate customized air quality improvement plans based on the hospital's internal activity arrangements and patient condition data; The second processing module is used to obtain the equipment operation scheduling strategy based on the air quality improvement plan through the proximal strategy optimization algorithm; The third processing module is used to dynamically process the equipment operation parameters by using the PID control algorithm according to the equipment operation scheduling strategy; Management module: It is used to obtain abnormal warning signals based on the equipment operating parameters and real-time monitoring equipment environmental feedback, and respond to the abnormal warning signals after being processed by the abnormal detection algorithm, so as to manage the medical environment air quality accordingly.

7. The medical environment air quality management system according to claim 6, characterized in that: The first processing module includes: The first processing unit is used to process the real-time data from the hospital's surrounding environment monitoring station and internal monitoring devices through data preprocessing and image recognition technology, wherein the processing process includes converting the numerical information in the chart into a digital format to obtain the original time series data set; The second processing unit is used to fuse the time series data set using the weighted average method, and combine the real-time data of the hospital's internal monitoring device to obtain a fused data set. The weighted average method gives different weights to the data at different monitoring points. wi To calculate the average value of pollutant concentration, the calculation formula is as follows: In the formula, Ci It is i The pollutant concentration at each monitoring point is wi is the corresponding weight, Cavg represents the weighted average of all monitoring points, and n is the total number of monitoring points; Calculation unit: used to obtain the main components of the data through principal component analysis based on the fused data set, and finally obtain the calibrated PCA components. PCA transforms multidimensional data into a new coordinate system through singular value decomposition. The calculation formula is as follows: In the formula, X is the original data matrix, P is from X The calculated eigenvector matrix, Y is the transformed data matrix; The third processing unit is used to visualize the calibrated PCA components using a data visualization library, map the calibrated data to geographic coordinates, and generate a distribution map reflecting indoor and outdoor pollutant concentrations.

8. The medical environment air quality management system according to claim 6, characterized in that: The identification feature module includes: A first extraction unit: used to extract original time series data from a distribution map, wherein the distribution map displays changes in pollutant concentrations in the form of a chart, and includes data from multiple monitoring points; Integration unit: used to clean the collected time series data, including processing missing values, outliers and duplicate values ​​to obtain cleaned data, integrate the data from different monitoring stations or monitoring devices with the cleaned data to obtain fused data, calibrate the fused data to obtain preprocessed data; Decomposition unit: used to decompose the preprocessed data using the VMD algorithm, decompose it into several intrinsic mode functions, iteratively search for the optimal solution of the variational mode, update each mode function and center frequency, and obtain the intrinsic mode function after VMD decomposition; The second extraction unit is used to extract features of the intrinsic mode function after VMD decomposition using a bidirectional gated recurrent unit network to obtain key features reflecting changes in air quality.

9. A medical environment air quality management device, characterized in that: include: Memory for storing computer programs; A processor, used to implement the medical environment air quality management method as described in any one of claims 1 to 5 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the medical environment air quality management method according to any one of claims 1 to 5 is implemented.

Images