Greening design method and system based on hospital infection characteristics

Abstract

The invention relates to the technical field of gardening greening, and discloses a greening design method and system based on hospital infection characteristics, and the method comprises the steps: monitoring hospital environment parameters in real time, storing and analyzing historical environment data, constructing a space-time decision engine to pre-judge an environment state, and preloading and dynamically adjusting a greening function according to the environment state. The plant root system environment is accurately controlled through the intelligent irrigation system, and environment purification is achieved through combination of specific plants and microorganisms. According to the method, by introducing time sequence analysis, the change trend of the hospital environment can be accurately pre-judged, and the greening function is actively adjusted before the risk appears, for example, a high-strength antibacterial mode is started in advance before personnel arrive or air quality deteriorates, so that the pre-digestion of the risk of the easily infected environment of the hospital is realized.

Description

Technical Field

[0001] The invention relates to a greening design method and system based on hospital infection characteristics, belonging to the technical field of gardening greening. Background Art

[0002] As a complex indoor environment, the air quality, microbial distribution and patient comfort of hospitals are directly related to medical effects and public health and safety. As an eco-friendly means of environmental improvement, greening has important application value in hospitals. It can not only improve the visual environment, but also regulate air composition and humidity through the physiological activities of plants. However, traditional hospital greening solutions have significant limitations in dealing with the complexity and dynamics of the hospital environment.

[0003] At present, hospital greening mainly relies on statically deployed plants, and its working principle is based on the passive absorption of atmospheric pollutants and the release of oxygen by plants. Typical applications include using potted plants to improve the air quality in wards, or increasing the green area through green walls to improve the overall environmental comfort. For example: 1. The hospital environment is a highly dynamic system, with parameters such as crowd density and air quality showing significant differences at different times and in different areas. Existing greening solutions lack effective perception and adaptation mechanisms for this temporal and spatial dynamics, making it difficult to predict pollution peaks in specific areas based on historical data and to initiate enhanced purification functions in advance.

[0004] 2. Existing technologies mostly utilize plant and microbial functions in a passive natural process, lacking active regulatory means, and are unable to activate or inhibit related biological functions in a targeted manner according to the specific needs of the hospital (such as the need for antibacterial treatment during a specific period of time). For example, methods that use water flow rate to regulate the metabolic state of rhizosphere microorganisms to achieve specific functional switching are rarely reported in existing technologies.

[0005] 3. There are some unique risks in the hospital environment, such as the spread of aerosols generated by irrigation in sterile areas and the potential interference of certain plant volatiles with medical equipment. Existing technologies often lack active prevention and suppression mechanisms for these specific risks.

[0006] To overcome the above shortcomings, the industry may try to introduce more complex environmental monitoring systems and automated control devices, such as intelligent greenhouse control systems based on artificial intelligence. However, these solutions often focus on precisely controlling physical environmental parameters, while ignoring the potential of plants and microorganisms as active purification units, and may face problems such as high costs and complex systems. Summary of the invention

[0007] The present invention provides a greening design method and system based on hospital infection characteristics, the main purpose of which is to solve the problem that the existing hospital greening system is unable to actively adapt and preload functions according to the spatiotemporal dynamic characteristics of the hospital environment, and lacks a prevention mechanism for hospital-specific risks, resulting in environmental safety and management efficiency that are difficult to meet modern medical needs.

[0008] To achieve the above object, the present invention provides a greening design method based on hospital infection characteristics, comprising the following steps: Step 1: Real-time monitoring of environmental parameters of each functional area of ​​the hospital, including crowd density, air quality, temperature and humidity, and light intensity; Step 2: The monitored environmental parameters are preliminarily processed through the edge computing node, and the key environmental data time series of the preset time period are stored in the ring buffer storage module in a sliding window manner to form a dynamically updated periodic database; Step 3, analyzing the historical environmental data in the periodic database to identify environmental characteristics and potential risk points in different time periods; Step 4: Based on the analysis results of the historical environmental data, a spatiotemporal decision engine is constructed, wherein the spatiotemporal decision engine stores the historical environmental data of the same period and the corresponding optimal greening parameter combination, and has a mode discriminator and a strategy executor; Step 5: Use the mode discriminator to compare the fluctuation characteristics of the real-time environmental parameters of the current period with the historical environmental data of the same period, and judge whether the current environmental state is steady, gradual or sudden. When the fluctuation percentage ΔP of the environmental parameters in the current period exceeds the preset mutation threshold When , it is determined to be a mutation state, and the calculation formula of the fluctuation percentage ΔP is: , in, Indicates the real-time environmental parameter value of the current period. It represents the average value of environmental parameters in the same period of history; Step 6, according to the environmental state, the strategy executor selects or generates a corresponding greening parameter combination, and controls the greening function execution layer to perform corresponding operations, wherein, before the arrival of personnel or the occurrence of risks, the parameters of the greening system are adjusted in advance according to the historical data prediction, so as to realize the preloading of the greening function; Step 7, the greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system can accurately control the amount of irrigation water and the water flow rate to regulate the plant root environment to affect the activity of the pre-implanted functional bacteria.

[0009] In a preferred embodiment, in step 6, when the mode discriminator determines that the current environmental state is a gradual change, and the environmental data fluctuation of the current period is within the preset gradual change threshold range When the greening function is adjusted, the strategy executor generates a transitional parameter combination by using a linear interpolation method.

[0010] In a preferred embodiment, in step 1, the environmental parameters of the air quality monitoring include concentration, PM2.5 and total bacteria count.

[0011] In a preferred embodiment, in step 5, when the environmental parameter fluctuation percentage ΔP of the current period satisfies: When , it is determined to be a steady state, where is the preset steady-state threshold.

[0012] In a preferred embodiment, in step 6, when the mode discriminator determines that the current environmental state is a steady state, the strategy executor continues to use the optimal greening parameter combination in the same period of history.

[0013] In a preferred embodiment, in step 2, the preset time period is 168 hours.

[0014] In a preferred embodiment, in step 6, when the pattern discriminator determines that the current environmental state is a sudden change, the strategy executor switches to an emergency response mode dominated by real-time sensor data, starts the highest intensity purification function or adjusts the irrigation strategy to reduce the aerosol risk; and adjusts the oxygen content around the plant roots by precisely controlling the irrigation water flow rate to selectively activate or inhibit the pre-implanted functional bacteria.

[0015] A greening system based on hospital infection characteristics, the greening system comprising: The environmental perception layer is used to monitor the environmental parameters of each functional area of ​​the hospital in real time, including crowd density, air quality, temperature and humidity, and light intensity, and transmit the monitoring data to the data processing and storage layer; The data processing and storage layer includes an edge computing node and a ring buffer storage module arranged in each greening unit or area. The edge computing node is used to receive and preliminarily process the environmental parameter data from the environmental perception layer in real time, and store the processed key environmental data time series in the ring buffer storage module in a sliding window manner to form a dynamically updated periodic database; The decision control layer includes a spatiotemporal decision engine, which is configured with a memory unit, a mode discriminator and a strategy executor. The memory unit stores historical environmental data of the same period and the corresponding optimal greening parameter combination. The mode discriminator is used to compare the real-time environmental parameters of the current period with the fluctuation characteristics of the historical environmental data of the same period stored in the memory unit to determine whether the current environmental state is steady, gradual or sudden. The strategy executor selects or generates a corresponding greening parameter combination according to the judgment result of the mode discriminator. The greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system accurately controls the irrigation water volume and water flow rate according to the greening parameter combination output by the strategy executor to regulate the plant root environment, thereby affecting the activity of the pre-implanted functional bacteria and realizing dynamic switching of the greening function. It also uses a porous ceramic slow-release irrigation head combined with negative pressure adsorption technology to reduce the risk of aerosol diffusion. The specific plant and microorganism combination is selected and pre-implanted according to the needs of different areas of the hospital to achieve specific functions such as antibacterial, degradation of pollutants or release of sleep-inducing substances. Among them, the decision-making control layer adjusts the parameters of the greening function execution layer through the strategy executor in advance at a preset time based on the analysis of historical data before personnel arrive or risks occur, so as to realize the preloading of greening functions.

[0016] Compared with the problems described in the background technology, the beneficial effects of the present invention are: 1. By introducing time series analysis and studying the hospital environmental data of the past week (168 hours), we can more accurately predict the changing trends of environmental parameters in various regions in the future, such as peak traffic flow and air quality deterioration periods, and start corresponding greening functions at a preset time (for example, 1 hour) before the risk actually arrives, such as high-intensity antibacterial mode or increasing the release of specific plant volatiles. This can achieve risk pre-emptive elimination and avoid the passive response mode of traditional greening systems that rely on real-time perception, providing active safety for hospital environmental safety management and more conducive to controlling hospital infection risks.

[0017] 2. The system uses a circular buffer embedded in the edge computing node to continuously update key environmental data of the past 7 days in a sliding window manner to form a dynamic periodic database, avoiding the need for massive data storage. More importantly, it enables the system to automatically adjust and optimize greening strategies as factors such as seasons and holidays change. For example, it can adapt to humidity changes caused by winter heating and maintain optimal operating conditions without human intervention, with stronger environmental adaptability and lasting performance.

[0018] 3. By comparing the fluctuation characteristics of the current period with the data of the previous 7 days, three prediction modes are designed: steady-state, gradual and sudden change. In the steady-state mode with small fluctuations, the system uses the historical optimal parameter combination to avoid waste of resources; in the gradual change mode with fluctuations in the middle range, the system smoothly adjusts the parameters to ensure environmental comfort; and in the sudden change mode when the fluctuation exceeds the threshold, the system immediately initiates an emergency response based on real-time sensor data. This lightweight fluctuation analysis method and multi-mode intelligent switching mechanism realize the efficient utilization of hospital greening resources and precise control of the environment, especially in scenarios such as outpatient tides.

[0019] 4. The irrigation water flow rate is used as a biological switch to regulate the oxygen content of plant roots, thereby selectively activating or inhibiting the pre-implanted functional bacteria, so that the greening unit has differentiated functions such as antibacterial, pollutant degradation or release of sleep-inducing volatiles at different times. Planting plants that can release terpenes and mosses that release low-concentration ozone in specific areas further neutralizes ozone through biochemical reactions between plants. This water flow rate regulation works synergistically with plant-microorganisms to build directional, efficient and environmentally friendly purification capabilities for different functional areas of the hospital, which is conducive to the use of special places in the hospital such as infection wards. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a functional structural diagram of the greening system based on hospital infection characteristics of the present invention.

[0021] Figure 2 It is a schematic diagram of the greening parameter combination generation and execution process of the present invention.

[0022] Figure 3 The control flow timing diagram is preloaded for the greening function of the present invention.

[0023] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0024] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0025] The present application embodiment provides a greening design method based on hospital infection characteristics, comprising the following steps: Step 1: Real-time monitoring of environmental parameters of each functional area of ​​the hospital, including crowd density, air quality, temperature and humidity, and light intensity; Step 2: The monitored environmental parameters are preliminarily processed through the edge computing node, and the key environmental data time series of the preset time period are stored in the ring buffer storage module in a sliding window manner to form a dynamically updated periodic database; Step 3, analyzing the historical environmental data in the periodic database to identify environmental characteristics and potential risk points in different time periods; Step 4: Based on the analysis results of the historical environmental data, a spatiotemporal decision engine is constructed, wherein the spatiotemporal decision engine stores the historical environmental data of the same period and the corresponding optimal greening parameter combination, and has a mode discriminator and a strategy executor; Step 5: Use the mode discriminator to compare the fluctuation characteristics of the real-time environmental parameters of the current period with the historical environmental data of the same period, and judge whether the current environmental state is steady, gradual or sudden. When the fluctuation percentage ΔP of the environmental parameters in the current period exceeds the preset mutation threshold When , it is determined to be a mutation state, and the calculation formula of the fluctuation percentage ΔP is: , in, Indicates the real-time environmental parameter value of the current period. It represents the average value of environmental parameters in the same period of history; Step 6, according to the environmental state, the strategy executor selects or generates a corresponding greening parameter combination, and controls the greening function execution layer to perform corresponding operations, wherein, before the arrival of personnel or the occurrence of risks, the parameters of the greening system are adjusted in advance according to the historical data prediction, so as to realize the preloading of the greening function; Step 7, the greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system can accurately control the irrigation water volume and water flow rate to regulate the plant root environment, thereby affecting the activity of the pre-implanted functional bacteria, realizing the dynamic switching of the greening function, and using a porous ceramic slow-release irrigation head combined with negative pressure adsorption technology to reduce the risk of aerosol diffusion; the specific plant and microorganism combination is selected and pre-implanted according to the needs of different areas of the hospital to achieve specific functions such as antibacterial, degradation of pollutants or release of sleep-inducing substances.

[0026] In a preferred embodiment, in step 6, when the mode discriminator determines that the current environmental state is a gradual change, and the environmental data fluctuation of the current period is within the preset gradual change threshold range When the greening function is adjusted, the strategy executor generates a transitional parameter combination by using a linear interpolation method.

[0027] In a preferred embodiment, in step 1, the environmental parameters of the air quality monitoring include concentration, PM2.5 and total bacteria count.

[0028] In a preferred embodiment, in step 5, when the environmental parameter fluctuation percentage ΔP of the current period satisfies: When , it is determined to be a steady state, where is the preset steady-state threshold.

[0029] In a preferred embodiment, in step 6, when the mode discriminator determines that the current environmental state is a steady state, the strategy executor continues to use the optimal greening parameter combination in the same period of history.

[0030] In a preferred embodiment, in step 2, the preset time period is 168 hours.

[0031] In a preferred embodiment, in step 6, when the pattern discriminator determines that the current environmental state is a sudden change, the strategy executor switches to an emergency response mode dominated by real-time sensor data, starts the highest intensity purification function or adjusts the irrigation strategy to reduce the aerosol risk; in step 7, by precisely controlling the irrigation water flow rate, the oxygen content around the plant roots is adjusted to selectively activate or inhibit the pre-implanted functional flora, increase the oxygen content when antibacterial treatment is required, and promote the growth of aerobic antibacterial bacteria.

[0032] In a preferred embodiment, in step 7, plants that can release terpenes are planted in a specific area, and mosses that release low concentrations of ozone are mixed to reduce the concentration of ozone through natural oxidation neutralization reaction. .

[0033] In a preferred embodiment, the following steps are also included: when a sensor in the environmental perception layer fails, the spatiotemporal decision engine automatically switches to a historical data driven mode to maintain the basic functional operation of the greening system.

[0034] A greening system based on hospital infection characteristics, the greening system comprising: The environmental perception layer is used to monitor the environmental parameters of each functional area of ​​the hospital in real time, including crowd density, air quality, temperature and humidity, and light intensity, and transmit the monitoring data to the data processing and storage layer; The data processing and storage layer includes an edge computing node and a ring buffer storage module arranged in each greening unit or area. The edge computing node is used to receive and preliminarily process the environmental parameter data from the environmental perception layer in real time, and store the processed key environmental data time series in the ring buffer storage module in a sliding window manner to form a dynamically updated periodic database; The decision control layer includes a spatiotemporal decision engine, which is configured with a memory unit, a mode discriminator and a strategy executor. The memory unit stores historical environmental data of the same period and the corresponding optimal greening parameter combination. The mode discriminator is used to compare the real-time environmental parameters of the current period with the fluctuation characteristics of the historical environmental data of the same period stored in the memory unit to determine whether the current environmental state is steady, gradual or sudden. The strategy executor selects or generates a corresponding greening parameter combination according to the judgment result of the mode discriminator. The greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system accurately controls the irrigation water volume and water flow rate according to the greening parameter combination output by the strategy executor to regulate the plant root environment, thereby affecting the activity of the pre-implanted functional bacteria and realizing dynamic switching of the greening function. It also uses a porous ceramic slow-release irrigation head combined with negative pressure adsorption technology to reduce the risk of aerosol diffusion. The specific plant and microorganism combination is selected and pre-implanted according to the needs of different areas of the hospital to achieve specific functions such as antibacterial, degradation of pollutants or release of sleep-inducing substances. Among them, the decision-making control layer adjusts the parameters of the greening function execution layer through the strategy executor in advance at a preset time based on the analysis of historical data before personnel arrive or risks occur, so as to realize the preloading of greening functions.

[0035] Example 1: In the process of status determination of real-time environmental parameters, the system uses the hourly average of historical data in the past 7 days as the benchmark value of P historical period. The historical period here is defined as a set of continuous hourly data with the same time index as the current period. For example, if the current time is Wednesday at 14:00, the historical period data consists of the parameter values ​​at 14:00 every Wednesday in the past 7 days. The average value is calculated as Historical period input formula. The value of the sensor raw data collected by the current edge computing node after being standardized, which is used to eliminate the risk of deviation caused by differences in device models or calibration. Fluctuation percentage Used to determine the degree of change in the current environmental status. Its value is determined by the following formula: , In the above formula: : The environmental parameter value collected in real time during the current period. The unit is determined by the parameter type, such as ppm (VOCs concentration), (PM2.5), etc. : The historical average value for the same period is the weighted average of the corresponding period in the historical data set. The weight can be adjusted according to the stability of the time series. :Current parameter volatility percentage, used for status classification. According to the fluctuation range The value of and , the environmental state is divided into three types: steady state, gradual change and sudden change. To avoid deviations introduced by artificial settings, and It can be automatically generated based on the distribution of the standard deviation of historical data. For example, when the system runs for one week at the initial deployment, the fluctuation range of each parameter time series is fitted by Gaussian distribution, and the standard deviation is set. Within 1.0 times the standard deviation, The specific value is determined by the risk management level of the hospital where the deployment is located. In terms of the parameter combination selection mechanism, the system adopts different strategies according to different states: when it is determined to be a steady state, that is, The system directly reuses the greening parameter combination that has been verified as the best in the same period of history. This parameter combination is derived from the optimal solution of the ratio of environmental quality improvement to greening response cost in the previous operation records, covering plant species, water flow settings, irrigation cycles and root zone aeration parameters.

[0036] When it is judged to be a gradual state, that is, , the system uses linear interpolation to continuously transition between two adjacent historical parameter combinations. The interpolation strategy is based on volatility. The relative position in the threshold interval is used as a factor to dynamically adjust parameters such as water volume and irrigation frequency to form a smooth transition and avoid system shock or resource waste caused by response delay or sudden switching. , the strategy executor immediately switches to the emergency response mode, which does not rely on historical combinations, but is dominated by real-time parameters. The antibacterial plant release channel is activated first, and the irrigation water flow rate is increased to the upper limit allowed by the system (controlled within the range of 20~30 mL / min) to increase the root oxygen diffusion rate. In this process, the dissolved oxygen level in the rhizosphere is monitored in real time, and the water rate is adjusted through closed-loop feedback to ensure the metabolic activity of the target flora (such as aerobic antibacterial bacteria) and inhibit the over-growth of potential anaerobic flora; in the intelligent irrigation device, the porous ceramic slow-release head is combined with the negative pressure adsorption mechanism to form an irrigation module to ensure that water vapor is still transported stably under sudden changes in the environment, avoiding aerosol leakage caused by pressure fluctuations during the irrigation process. The ceramic pore size range is set to 2~5μm, combined with the slow-release dynamics formed by the siphon negative pressure, to form a micro-water flow-micro-adsorption synergistic mechanism, effectively reducing the risk of escape of bacterial aerosols and improving the level of hospital infection control, which are all extended implementation methods known to ordinary technicians in this field.

[0037] While executing the greening parameters, the system has a built-in biological function group control mechanism to selectively activate the microbial community based on the oxygen concentration in the root zone. For example, an increase in oxygen concentration can promote the growth of aerobic antibacterial flora represented by Gram-positive Bacillus, thereby enhancing the antibacterial function of plants; conversely, when the environment is degrading When it is the main goal, the ventilation rate is appropriately lowered to activate the anaerobic bacteria to complete the enzymatic oxidation degradation and achieve the purpose of pollutant treatment. This embodiment also introduces redundant fault-tolerant logic. When some sensors in the perception layer fail, data is missing, or the error rate exceeds the set threshold (such as 5%), the system automatically switches to the historical data driven mode. This mode is based on high-confidence sample data within the past 7 days. Compensation parameters are generated through trend prediction and similar day fitting to ensure the continuous operation of the greening function and avoid the risk of interruption to hospital environmental management.

[0038] Example 2: To further illustrate the system structure and operation logic of the present invention, Figures 1 to 3 The different structures and flow charts shown further illustrate the present application, wherein: Figure 1 The figure shows a functional structure diagram of a greening system based on hospital infection characteristics. The system is divided into four functional levels: environmental perception layer, data processing and storage layer, decision control layer, and greening function execution layer. Among them, the environmental perception layer is used to monitor the environmental parameters of each functional area of ​​the hospital in real time and transmit the monitoring data to the data processing and storage layer. The data processing and storage layer includes edge computing nodes and a ring buffer storage module. The edge computing node is responsible for the preliminary processing of the original data uploaded by the environmental perception layer, and then writes the key time series data into the ring buffer storage module in a sliding window manner for dynamic construction of a periodic database. The processed data is transmitted to the decision control layer for analysis. The layer integrates a spatiotemporal decision engine, which is composed of a memory unit, a pattern discriminator, and a strategy executor. The memory unit stores historical environmental data of the same period and its corresponding optimal greening parameter combination; the pattern discriminator is used to compare the real-time environmental parameters of the current period with the historical fluctuation characteristics to determine whether the current environmental state is steady, gradual or sudden; the strategy executor selects or generates the corresponding greening parameter combination based on the judgment result, and sends the control instruction to the greening function execution layer. The greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system can accurately control the amount of irrigation water and the speed of water flow, thereby regulating the plant root zone environment and affecting the activity of the pre-implanted functional bacteria. The specific plant and microorganism combination is selected and configured according to the infectious characteristics of different areas of the hospital to achieve greening function goals such as antibacterial, purification or sleep assistance.

[0039] Figure 2 The figure shows the flow chart of greening parameter combination generation and execution, which is used to explain how the system selects different parameter control strategies according to the current environmental fluctuation state. After the system is started, the fluctuation characteristics of the real-time environmental parameters in the current period are compared with the historical data of the same period. If the steady-state threshold is less than the fluctuation percentage, the system will be judged as a steady-state state and the optimal greening parameter combination of the same period in history will be used; if the steady-state threshold is less than or equal to the fluctuation percentage If the fluctuation percentage is less than the mutation threshold, it is judged as a gradual change state. At this time, the system uses linear interpolation to generate a transitional parameter combination to achieve a flexible transition of parameters. If the value is greater than or equal to the mutation threshold, the system determines it as a mutation state and immediately switches to an emergency response mode based on real-time sensor data to quickly respond to high-risk mutation scenarios. Regardless of the above state judgment results, the system will eventually output a combination of greening parameters and control the greening function execution layer to perform operations. The intelligent irrigation system and a combination of specific plants and microorganisms will jointly complete environmental intervention and regulation, and the process will enter the end node. This process realizes the adaptive adjustment of greening parameters based on environmental fluctuation identification, enhancing the responsiveness and accuracy of the greening system to dynamic environments.

[0040] Figure 3 The figure shows the timing diagram of the greening function preloading control process, which reflects the process of the spatiotemporal decision engine to achieve pre-control based on the prediction mechanism. In this process, the decision control layer first analyzes the historical environmental data, and then the spatiotemporal decision engine queries the historical data of the same period, and predicts the environmental change trend based on the data model, such as the potential occurrence time of risk events such as personnel arrival. The system sets the advance preset time according to the model judgment result, and actively adjusts the greening system parameters at the specified time point before the risk appears to achieve pre-load control. The pre-load here includes the pre-activation of greening strategies that match the current trend, such as increasing the irrigation water flow rate, activating specific root zone flora, or releasing biovolatiles. The parameter adjustment instruction is sent from the spatiotemporal decision engine to the greening function execution layer, and the greening function execution layer then starts the corresponding greening function to ensure that the environmental state intervention is completed before the risk officially occurs, and the pre-suppression ability of hospital infection risks is improved. The timing logic shows the whole process from historical data analysis, trend judgment, strategy preset to instruction execution, reflecting the closed-loop design idea of ​​the system in information flow, instruction flow and execution flow.

[0041] Example 3: In a hospital comprehensive ward scenario, the system uses the following method to calculate the environmental state fluctuation rate: , in, : An environmental parameter value (such as PM2.5 concentration) collected and standardized in real time by the edge computing node, in units of ; : The weighted average of the data set in the historical data that has the same time index as the current period (such as Wednesday 14:00). The weight is determined by the inverse proportion of the variance of each historical sample to enhance the reference value of the stable sample; : The calculated volatility percentage is used for environmental status classification and parameter scheduling basis; in order to improve the objectivity and universality of threshold setting, the system runs continuously for 7 days at the initial deployment, and performs normal distribution fitting based on the time series fluctuation amplitude of each type of environmental parameter, and automatically derives the parameter standard deviation . Hence: Steady-state threshold Set to ; Mutation threshold Set to ; This mechanism ensures that the threshold is portable across different deployment environments and avoids human experience bias.

[0042] When the result is steady state, the system calls the optimal parameter combination that has been verified in the same period of history. This parameter combination includes the following dimensions, such as: plant combination type (such as basil and lemongrass that release terpenes); irrigation water flow rate (unit: mL / min); irrigation cycle frequency (times / hour); root zone aeration intensity (control signal magnitude, used to adjust the on-off time of the oxygen diffusion device); target bacterial community type (aerobic antibacterial bacteria / facultative anerobic degrading bacteria, etc.); the basis for judging the optimality is: under the same time index, compare the environmental improvement effect in the historical operation records (such as The ratio of the reduction rate of irrigation water and resource consumption (irrigation water, electricity, etc.) is taken as the target optimal group.

[0043] When the state is gradual, the system calls the parameter groups in the above two adjacent states and constructs the transition parameter group using linear interpolation. The interpolation coefficient is given by The relative position within the threshold interval is determined. For example: In and midpoint, the two historical parameter groups are combined with a 50% weight; if When the system enters the emergency response process under the sudden change state, it not only increases the irrigation water flow rate (such as to 30 mL / min), but also focuses on starting the closed-loop control mechanism of the oxygen content in the root zone. Specifically, a micro dissolved oxygen sensor is placed in the soil of the root zone and samples are taken every 5 minutes. The system will record the real-time oxygen content. With target setting value If the deviation exceeds ±10%, feedback regulation is triggered; the regulation method is to control the water supply frequency of the porous ceramic irrigation head and the opening and closing time of the negative pressure siphon valve to indirectly affect the water flow rate and adjust the root zone humidity and oxygen diffusion rate; the system maintains this cycle until the oxygen concentration stabilizes in the target range to ensure that the required microbial community is in the most active state. At the same time, in order to achieve volatile organic compounds ( ) purification, the system deploys a combination of plants that release terpenes (such as rosemary) and mosses that emit low concentrations of ozone.

[0044] When the system detects that some sensors have invalid data for two consecutive rounds (10 minutes) or the error rate exceeds 5%, it automatically switches to the historical data driven mode, which includes: building a trend model (such as exponential smoothing method) based on high-confidence data in the same period within the past 7 days; generating alternative inputs for current status evaluation; if multiple parameters are missing, the system limits the intensity of greening operations and only maintains basic operations (such as moisturizing and low-frequency irrigation); at the same time, it starts redundant detection logic and reminds manual intervention, which are all extended implementation methods known to ordinary technicians in this field.

[0045] Example 4: In the actual deployment of the hospital greening control system, the system can adopt a time index mechanism based on hours when constructing a historical environmental data sequence. Specifically, the current time is matched one-to-one with the environmental parameters at the same time point in the past seven days, and a historical data set of length 7 is constructed, and the statistical average of the set is used as the historical reference value for the same period. In order to improve the stability and representativeness of the data, the system sets a weighting mechanism based on the fluctuation range of the time series of each historical sample. The specific method is: first evaluate the parameter variance of each sample on its own day, and then normalize the inverse of its variance as a weight factor, so that the sample data with small fluctuation range and high stability has a higher weight. This mechanism ensures that the reference to historical parameters is fully representative and effectively avoids the interference of short-term burst data on system decision-making.

[0046] In the face of multiple environmental parameters (such as In scenarios where the air quality (such as concentration, PM2.5, and total bacteria count) fluctuates simultaneously, in order to avoid the failure of the control strategy due to parameter priority conflicts, an environmental parameter priority table is set in the system. The table is graded according to the hospital infection risk level, the degree of impact of the parameter on indoor air quality, and the relevance to medical safety. For example, in the core area of ​​the ward, the total bacteria count is set as the highest priority, followed by PM2.5, and then concentration. When multiple parameters enter the mutation state at the same time, the system will take the one with the highest priority as the dominant factor and trigger the corresponding greening response strategy. If multiple parameters have the same priority, the system will select the parameter with the largest fluctuation amplitude as the dominant factor to improve the pertinence and effectiveness of the response. The system adjusts the microenvironment of the plant root zone through refined irrigation control to activate or inhibit the activity of the preset functional flora. To ensure the controllability of the oxygen level in the root zone, the system is equipped with a micro dissolved oxygen sensor and sets the target range of oxygen concentration. During operation, the system samples the dissolved oxygen value in the root zone every 5 minutes and compares it with the set target in real time. If the deviation exceeds the adjustment tolerance of ±10%, the control logic is triggered to indirectly adjust the water flow rate by adjusting the water supply frequency of the ceramic irrigation head and the opening and closing cycle of the negative pressure siphon valve, thereby affecting the oxygen diffusion rate in the root zone. This closed-loop feedback mechanism not only ensures that the flora activity operates within the optimal range, but also effectively inhibits the abnormal proliferation of anaerobic flora, enhancing the antibacterial and purification capabilities of the greening system.

[0047] When executing the selection of greening parameter combinations, the system no longer relies on empirical values ​​to determine the historical optimal parameter combination, but uses the ratio of environmental improvement to resource consumption recorded in the operation history as an evaluation indicator. Each set of parameter combinations must include factors such as plant species, irrigation water flow rate, irrigation cycle, root zone aeration intensity and target bacterial type. The system automatically selects the one with the largest ratio as the target combination. In the gradual state, the system regards the two adjacent historical optimal parameter combinations as the interpolation start and end points, and uses weighted average to generate transition parameter combinations based on the relative position of the current fluctuation level in the threshold interval. The interpolation ratio is completely determined by the linear relationship between the fluctuation percentage and the upper and lower limits of the threshold, ensuring the continuity and stability of the regulation process and avoiding system fluctuations or resource waste caused by sudden changes. At the same time, considering that occasional sensor failures are inevitable in hospital environments, the system has built-in redundant detection and adaptive switching mechanisms. When a sensor collects invalid data for two consecutive sampling cycles (i.e., 10 minutes) or the error rate exceeds 5%, the system will automatically enable the historical data driven mode. In this mode, the system builds a trend prediction model based on complete data samples in the same time period within the past seven days, and generates alternative input data through similar day fitting methods to support environmental status judgment and parameter control. In addition, the system will automatically limit the intensity of the greening strategy, retaining only basic irrigation and ventilation functions to ensure that the most basic greening purification capabilities can be maintained during data anomalies. At the same time, the system will automatically issue maintenance reminders and require operation and maintenance personnel to check the status of sensors, which are all extended implementation methods known to ordinary technicians in this field.

[0048] Example 5: In the actual deployment process, the system realizes the purification function of the hospital environment through a combination of specific plants and microorganisms. Among them, the selection of microbial flora is configured according to the specific needs of different functional areas of the hospital, mainly including aerobic antibacterial flora and facultative anaerobic degradation flora. Aerobic antibacterial flora is preferably Gram-positive Bacillus, Bacillus subtilis, etc., whose metabolites have antibacterial and antibacterial properties; facultative anaerobic degradation flora can be selected from Pseudomonas or Saccharomyces, which can degrade During the deployment phase, the system completes the screening and root zone implantation of strains based on the regional characteristics of the hospital to ensure the directional functionality of the microbial combination.

[0049] During operation, the system uses multi-parameter priority judgment rules for real-time monitoring results of multi-dimensional environmental parameters such as air quality and population density. When multiple parameters fluctuate at the same time and enter the risk threshold range, the system determines the dominant factor according to the pre-set priority table. The priority table is set based on the hospital risk level, environmental safety impact, and medical safety relevance. The specific order is: total bacteria count>PM2.5 concentration> Concentration > Crowd density > Temperature and humidity > Light intensity. For example, when the total number of bacteria and PM2.5 concentration reach the mutation threshold at the same time, the system prioritizes the total number of bacteria as the dominant factor, triggers the corresponding greening parameter scheduling strategy, and ensures the environmental parameter fluctuation percentage that minimizes the risk of infection. The calculation formula is: , In this embodiment, the parameters It represents the environmental parameter value collected in real time by the sensors of the environmental perception layer and standardized by the edge computing node. The unit is set according to the specific parameter type, such as the total number of bacteria in PM2.5 concentration is Parameters It indicates the weighted average value of the data set with the same time index as the current period in the past 7 days in the ring buffer storage module. The weighting factor is determined inversely according to the standard deviation of each historical sample in the intraday time series, and the sample data with small fluctuation and high stability are given priority to ensure the representativeness and accuracy of the historical benchmark value. The indicators are used to determine the current environment status in real time and provide a basis for parameter scheduling of subsequent strategy executors.

[0050] In order to further enhance the system's ability to operate continuously under extreme environmental fluctuations or equipment abnormalities, a historical data-driven fault-tolerant mechanism is introduced in this embodiment. When a sensor in the environmental perception layer has invalid data or an error rate of more than 5% for two consecutive sampling periods (i.e., 10 minutes), the system starts the fault-tolerant logic and automatically switches to the historical data-driven mode. In this mode, the system no longer relies on real-time sensor data, but uses high-confidence historical data samples in the same period within the past 7 days to generate alternative inputs for current environmental parameters through an exponentially weighted moving average method. Specifically, the system uses the stability weight of each sample in the historical data set as an exponential factor, smoothes and weights the parameter value, calculates the estimated value of the current period, and uses this to identify the environmental state and schedule greening parameters.

[0051] In addition, in order to avoid abnormal greening functions due to abnormal parameters or missing data, the upper limit of the execution intensity of the greening strategy in the fault-tolerant mode is clearly set in this embodiment. Specifically, in the historical data-driven mode, the greening function execution layer only maintains basic operations, including maintaining the minimum irrigation water flow rate (such as 10 mL / min) and low-frequency ventilation control, and temporarily not activating the emergency response mode or high-intensity antibacterial function. At the same time, the system automatically issues maintenance prompts to remind the operation and maintenance personnel to check the sensor status, which are all extended implementation methods known to ordinary technicians in this field.

[0052] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A greening design method based on hospital infection characteristics, characterized in that: The following steps are involved: Step 1: Real-time monitoring of environmental parameters of each functional area of ​​the hospital, including crowd density, air quality, temperature and humidity, and light intensity; Step 2: The monitored environmental parameters are preliminarily processed through the edge computing node, and the key environmental data time series of the preset time period are stored in the ring buffer storage module in a sliding window manner to form a dynamically updated periodic database; Step 3, analyzing the historical environmental data in the periodic database to identify environmental characteristics and potential risk points in different time periods; Step 4: Based on the analysis results of the historical environmental data, a spatiotemporal decision engine is constructed, wherein the spatiotemporal decision engine stores the historical environmental data of the same period and the corresponding optimal greening parameter combination, and has a mode discriminator and a strategy executor; Step 5: Use the mode discriminator to compare the fluctuation characteristics of the real-time environmental parameters of the current period with the historical environmental data of the same period, and judge whether the current environmental state is steady, gradual or sudden. When the fluctuation percentage ΔP of the environmental parameters in the current period exceeds the preset mutation threshold When , it is determined to be a mutation state, and the calculation formula of the fluctuation percentage ΔP is: ， in, Indicates the real-time environmental parameter value of the current period. It represents the average value of environmental parameters in the same period of history; Step 6, according to the environmental state, the strategy executor selects or generates a corresponding greening parameter combination, and controls the greening function execution layer to perform corresponding operations, wherein, before the arrival of personnel or the occurrence of risks, the parameters of the greening system are adjusted in advance according to the historical data prediction, so as to realize the preloading of the greening function; Step 7, the greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system can accurately control the amount of irrigation water and the water flow rate to regulate the plant root environment to affect the activity of the pre-implanted functional bacteria.

2. The greening design method based on hospital infection characteristics according to claim 1 is characterized in that: In step 6, when the mode discriminator determines that the current environmental state is gradual, and the environmental data fluctuation of the current period is within the preset gradual threshold range, When the greening function is adjusted, the strategy executor generates a transitional parameter combination by using a linear interpolation method.

3. The greening design method based on hospital infection characteristics according to claim 1 is characterized in that: In step 1, the environmental parameters of the air quality monitoring include concentration, PM2.5 and total bacteria count.

4. The greening design method based on hospital infection characteristics according to claim 1 is characterized in that: In step 5, when the environmental parameter fluctuation percentage ΔP of the current period satisfies: When , it is determined to be a steady state, where is the preset steady-state threshold.

5. The greening design method based on hospital infection characteristics according to claim 4 is characterized in that: In step 6, when the mode discriminator determines that the current environmental state is a steady state, the strategy executor continues to use the optimal greening parameter combination in the same period of history.

6. The greening design method based on hospital infection characteristics according to claim 1 is characterized in that: In step 2, the preset time period is 168 hours.

7. The greening design method based on hospital infection characteristics according to claim 1 is characterized in that: In step 6, when the pattern discriminator determines that the current environmental state is a sudden change, the strategy executor switches to an emergency response mode dominated by real-time sensor data, starts the highest intensity purification function or adjusts the irrigation strategy to reduce the aerosol risk; and adjusts the oxygen content around the plant roots by precisely controlling the irrigation water flow rate to selectively activate or inhibit the pre-implanted functional bacteria.

8. A greening system based on hospital infection characteristics, characterized by: The greening system includes: The environmental perception layer is used to monitor the environmental parameters of each functional area of ​​the hospital in real time, including crowd density, air quality, temperature and humidity, and light intensity, and transmit the monitoring data to the data processing and storage layer; The data processing and storage layer includes an edge computing node and a ring buffer storage module arranged in each greening unit or area. The edge computing node is used to receive and preliminarily process the environmental parameter data from the environmental perception layer in real time, and store the processed key environmental data time series in the ring buffer storage module in a sliding window manner to form a dynamically updated periodic database; The decision control layer includes a spatiotemporal decision engine, which is configured with a memory unit, a mode discriminator and a strategy executor. The memory unit stores historical environmental data of the same period and the corresponding optimal greening parameter combination. The mode discriminator is used to compare the real-time environmental parameters of the current period with the fluctuation characteristics of the historical environmental data of the same period stored in the memory unit to determine whether the current environmental state is steady, gradual or sudden. The strategy executor selects or generates a corresponding greening parameter combination according to the judgment result of the mode discriminator. The greening function execution layer includes an intelligent irrigation system and a combination of specific plants and microorganisms. The intelligent irrigation system accurately controls the irrigation water volume and water flow rate according to the greening parameter combination output by the strategy executor to regulate the plant root environment, thereby affecting the activity of the pre-implanted functional bacteria and realizing the dynamic switching of the greening function. A porous ceramic slow-release irrigation head combined with negative pressure adsorption technology is used to reduce the risk of aerosol diffusion. The specific plant and microorganism combination is selected and pre-implanted according to the needs of different areas of the hospital to achieve specific functions of antibacterial, degradation of pollutants or release of sleep-inducing substances. Among them, the decision-making control layer adjusts the parameters of the greening function execution layer through the strategy executor in advance according to the analysis of historical data before the arrival of personnel or the occurrence of risks to realize the preloading of greening functions.

Images