Clean environment monitoring and early warning method and system based on Internet of Things

Abstract

The invention relates to the technical field of Internet of Things environment detection, in particular to a clean environment monitoring and early warning method and system based on the Internet of Things. The method comprises the following steps: acquiring a monitoring range, dividing the monitoring range into a plurality of sub-regions, deploying a multi-modal sensing node with an identifier in each sub-region, and collecting multi-dimensional environmental parameters of each sub-region; identifying a cross-region diffusion risk and a collaborative abnormal situation, and judging the cleanliness level of the current sub-region; a parameter multi-level threshold value is preset, multi-level early warning is divided in combination with a correlation analysis result, and corresponding sub-region equipment is linked to carry out differential regulation and control; the system comprises a sub-region multi-parameter acquisition module, a multi-sub-region association module and a cleanliness grading early warning module. By means of the mode, the multi-mode sensing nodes are dynamically deployed, a multi-level early warning and differentiation regulation and control mechanism is established, the accuracy and effectiveness of hospital environment infection control are improved, the medical quality and patient safety are guaranteed, the detection accuracy is improved, and the refined and real-time infection control requirement is met.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) environmental monitoring technology, and in particular to a clean environment monitoring and early warning method and system based on IoT. Background Technology

[0002] As special places with dense populations and concentrated pathogens, the stability and safety of clean environments (such as operating rooms, ICUs, and sterile pharmacies) in hospitals are directly related to medical quality and patient safety, and are a core aspect of hospital infection control. Currently, hospital environmental monitoring and control mainly rely on traditional methods, which have the following shortcomings: crude sub-area division and uneven monitoring coverage.

[0003] Existing methods often treat a single functional area of ​​a hospital (such as the entire operating room or an entire ICU floor) as a single monitoring unit, failing to divide it into refined sub-areas based on operational attributes and cleanliness levels. This results in monitoring standards being the same for core operational points (such as operating tables and sterile preparation stations) and non-core areas, making it impossible to accurately capture environmental anomalies in critical locations. Furthermore, sensor node deployment is often based on experience-based density settings, without scientific planning considering sub-area area and the distribution of environmentally sensitive points. This easily leads to monitoring blind spots or data redundancy, affecting detection accuracy and failing to meet the needs of refined, real-time infection control.

[0004] Therefore, a clean environment monitoring and early warning method and system with dynamic deployment of multimodal sensing nodes and establishment of multi-level early warning and differentiated control mechanism is proposed to improve the accuracy and effectiveness of hospital environmental infection control, ensure medical quality and patient safety, improve detection accuracy, and meet the needs of refined and real-time infection control. Summary of the Invention

[0005] The purpose of this invention is to provide a clean environment monitoring and early warning method and system based on the Internet of Things, which aims to solve the technical problems of poor detection accuracy in the prior art, making it difficult to meet the needs of refined and real-time infection control.

[0006] To achieve the above objectives, the present invention employs an Internet of Things-based clean environment monitoring and early warning method, comprising the following steps: The monitoring range is determined, divided into multiple sub-regions, and labeled multimodal sensor nodes are deployed in each sub-region to collect multi-dimensional environmental parameters of each sub-region. Based on the spatial, airflow, and functional characteristics of the sub-region, the parameter transfer coefficient and abnormal diffusion probability are calculated to identify cross-regional diffusion risks and collaborative abnormal situations, and to determine the cleanliness level of the current sub-region. Based on the preset parameters and thresholds of the cleanliness level of the sub-area, and combined with the results of correlation analysis, multiple levels of early warning are divided, and the corresponding sub-area equipment is linked to carry out differentiated control.

[0007] Among the steps, the monitoring range is determined by dividing the area into multiple sub-regions and deploying identifiable multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters for each sub-region: Obtain the total area of ​​clean environment monitoring and divide it into multiple sub-areas, assigning each sub-area a classification label and a geographical label; among which, the classification labels include core operation area, auxiliary function area, and passage connection area; Based on the area, cleanliness level, and distribution of environmentally sensitive points of the sub-area, plan the deployment density of IoT multimodal sensor nodes and install the sensor nodes.

[0008] Among the steps, the deployment density of IoT multimodal sensor nodes is planned based on the sub-area area, cleanliness level, and distribution of environmentally sensitive points, and then the sensor nodes are installed: An IoT gateway is used to bind nodes to sub-area identifiers and connect them to the local IoT communication network.

[0009] After planning the deployment density of IoT multimodal sensor nodes based on the sub-area area, cleanliness level, and distribution of environmentally sensitive points, and then installing the sensor nodes: The sensor node acquisition frequency is dynamically adjusted according to the cleanliness level of the sub-region. After preliminary noise reduction by the nodes, the acquired data is uploaded to the sub-region edge computing node in real time via wireless communication.

[0010] Among them, the steps of calculating parameter transfer coefficients and abnormal diffusion probabilities based on the spatial, airflow, and functional correlation characteristics of sub-regions, identifying cross-regional diffusion risks and collaborative abnormal situations, and determining the current cleanliness level of the sub-region include: The environmental parameters of each sub-region are standardized, abnormal data caused by sensor failure are removed, and the parameter change trends and statistical characteristics are extracted. Based on the analysis of sub-region topology and IoT map data, the positional relationship and physical interval of adjacent sub-regions are determined to establish the intensity coefficient of mutual influence of parameters.

[0011] After analyzing the positional relationships and physical intervals of adjacent sub-regions based on the sub-region topology and IoT map data, and determining the intensity coefficient of the mutual influence of parameters: Based on the operational data of IoT devices in the air conditioning and ventilation system, calculate the probability of time and range of pollutant diffusion across sub-regions; For related sub-areas with personnel and material flow, the actual cleanliness level of each sub-area is determined by identifying the pattern of coordinated changes in parameters through flow frequency data recorded by IoT devices.

[0012] Among them, in the steps of setting multiple thresholds based on the cleanliness level of sub-areas, dividing multiple early warning levels based on correlation analysis results, and linking corresponding sub-area equipment for differentiated control: Three levels of thresholds—safe, early warning, and exceeding—are set for various environmental parameters in different sub-regions. Based on the correlation of multiple sub-regions to obtain the probability of abnormal spread and the scope of impact, the early warning is divided into four levels; Real-time parameter monitoring data is acquired, and when the parameters exceed the threshold, control commands are triggered for the air conditioning, fresh air, air purification, and differential pressure regulation equipment in the affected sub-area.

[0013] Among them, in the step of obtaining the probability of abnormal spread and the scope of impact based on the association of multiple sub-regions, and dividing the early warning into four levels: Divide the triggering conditions and response priorities corresponding to each level of early warning, and associate them with the IoT sound and light alarm devices in the corresponding sub-regions.

[0014] Among them, in the step of acquiring parameter monitoring data in real time and triggering control commands for the air conditioning, fresh air, air purification, and differential pressure regulation equipment in the affected sub-area when the parameters exceed the threshold: During the control process, the system receives real-time feedback on the operating status of the equipment and parameter monitoring data from the sensor nodes, and dynamically adjusts the control strategy until the environmental parameters of the sub-region return to the safe threshold.

[0015] This invention also provides a clean environment monitoring and early warning system based on the Internet of Things, including a sub-area multi-parameter acquisition module, a multi-sub-area association module, and a cleanliness classification early warning module; wherein: The sub-region multi-parameter acquisition module is used to acquire the monitoring range, divide it into multiple sub-regions, and deploy identifiable multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters of each sub-region. The multi-sub-region association module is used to calculate the parameter transmission coefficient and abnormal diffusion probability based on the spatial, airflow and functional association characteristics of the sub-region, identify cross-region diffusion risks and collaborative abnormal situations, and determine the cleanliness level of the current sub-region. The cleanliness classification and early warning module is used to divide the early warning into multiple levels based on preset parameters and thresholds of the cleanliness level of the sub-area, and to link the corresponding sub-area equipment for differentiated control.

[0016] Beneficial Effects: The present invention provides a clean environment monitoring and early warning method and system based on the Internet of Things, which employs a sub-region multi-parameter acquisition module, a multi-sub-region association module, and a cleanliness classification early warning module to perform the following steps: acquiring the monitoring range, dividing it into multiple sub-regions, and deploying identifiable multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters of each sub-region; calculating parameter transmission coefficients and abnormal diffusion probabilities based on the spatial, airflow, and functional correlation characteristics of the sub-regions, identifying cross-regional diffusion risks and collaborative abnormal situations, and determining the current cleanliness level of the sub-region; pre-setting multi-level thresholds for parameters based on the cleanliness level of the sub-regions, and dividing multi-level early warnings based on the correlation analysis results, and linking corresponding sub-region equipment for differentiated control; through the above methods, multimodal sensor nodes are dynamically deployed to establish a multi-level early warning and differentiated control mechanism, improving the accuracy and effectiveness of hospital environmental infection control, ensuring medical quality and patient safety, improving detection accuracy, and meeting the needs of refined and real-time infection control. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps of the clean environment monitoring and early warning method based on the Internet of Things of the present invention.

[0019] Figure 2 This is a flowchart of steps S100 of the present invention.

[0020] Figure 3 This is a flowchart of steps S200 of the present invention.

[0021] Figure 4 This is a flowchart of steps S300 of the present invention.

[0022] Figure 5 This is a schematic diagram of the structural principle of the Internet of Things-based clean environment monitoring and early warning system of the present invention.

[0023] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0024] 401 - Sub-region multi-parameter acquisition module, 402 - Multi-sub-region association module, 403 - Cleanliness classification early warning module. Detailed Implementation

[0025] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0026] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0027] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0028] Please see Figures 1-4 This invention provides a clean environment monitoring and early warning method based on the Internet of Things, comprising the following steps: S100: Obtain the monitoring range, divide it into multiple sub-regions, and deploy identifiable multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters of each sub-region.

[0029] In this embodiment, the monitoring range is obtained, divided into multiple sub-regions, and identifiable multimodal sensor nodes are deployed in each sub-region to collect multi-dimensional environmental parameters of each sub-region. The specific process is as follows: S101: Obtain the total area of ​​clean environment monitoring and divide it into multiple sub-areas, assigning a classification label and a geographical label to each sub-area; among which, the classification labels include core operation area, auxiliary function area, and passage connection area; S102: Based on the area, cleanliness level, and distribution of environmentally sensitive points of the sub-area, plan the deployment density of IoT multimodal sensor nodes, install the sensor nodes, use IoT gateways to bind the nodes to the sub-area identifiers, and connect them to the local IoT communication network. S103: The sensor node acquisition frequency is dynamically adjusted according to the cleanliness level of the sub-area. After the acquired data is initially denoised by the node, it is uploaded to the sub-area edge computing node in real time via wireless communication.

[0030] In the aforementioned process, the overall monitoring area was determined through hospital architectural design drawings and on-site surveys (covering the operating room, intensive care unit, intravenous medication preparation center, blood purification center, infectious disease wards, and medical corridors connecting these areas). Based on hospital infection control requirements, functional attributes, and patient and material flow paths, the overall area was divided into multiple independent sub-areas, each assigned a unique dual identifier: Category Identification: Core operating areas (such as operating rooms, sterile drug preparation rooms, and ICU bed units), auxiliary functional areas (such as medical equipment storage rooms, cleaning tool rooms, and drug storage areas), and connecting corridor areas (such as operating room corridors, ICU visitation corridors, and main medical corridors on each floor). Geographical identifiers (such as "Operating Department-01", "ICU-03 Bed Area", "Passage-West 2nd Floor") accurately locate the spatial position of sub-areas, facilitating subsequent risk tracing.

[0031] Based on the size of each sub-area, the preset cleanliness level (e.g., operating room is Class 100 clean, ICU is Class 1000 clean, general ward is Class 10,000 clean), and the distribution of environmentally sensitive points (e.g., above the operating table, sterile drug handling table, ICU patient bedside), the sensor node deployment density is planned as follows: every 3-5m in the core operating area. 2 Deploy one node to ensure no blind spots in monitoring critical operation points; auxiliary function areas are monitored every 8-12 meters. 2 Deploy 1 node; channel connection area every 12~15m 2 Deploy one node. The selected multimodal sensor node must support the collection of core monitoring parameters of the hospital environment, including airborne dust content (≥0.5μm particle count), bacterial colony count, temperature and humidity (operating room 22~25℃, ICU 23~26℃), pressure difference (positive pressure ≥5Pa relative to adjacent areas in the core area), concentration of harmful gases (such as formaldehyde, residual VOCs from disinfected instruments), and ventilation rate. During installation, fix the node in a location that avoids airflow dead corners, equipment obstructions, and frequent personnel contact (such as the four corners of the operating room ceiling, the ceiling above ICU beds, and the top of the corridor). Bind each sensor node to the classification and geographic identifier of the corresponding sub-area through an IoT gateway to ensure that the collected data corresponds one-to-one with the sub-area. Then connect all nodes to the hospital's local IoT communication network (preferably using low-power, interference-resistant LoRa or NB-IoT technology) to complete network connectivity and data transmission tests, ensuring that data transmission latency is ≤1 second and packet loss rate is <1%.

[0032] Based on the cleanliness level and infection control priority of each sub-area, the data acquisition frequency of the sensor nodes is dynamically adjusted: the acquisition frequency for core operating areas (operating rooms, sterile preparation rooms) is set to 1 time / 15 seconds to capture environmental changes during surgery and drug preparation in real time; the acquisition frequency for core nursing areas such as ICU and blood purification centers is set to 1 time / 30 seconds; the acquisition frequency for auxiliary function areas is set to 1 time / 2 minutes; and the acquisition frequency for passage connection areas is set to 1 time / 1 minute. After the sensor nodes acquire data, preliminary noise reduction is performed using a built-in moving average algorithm to remove pulse interference data caused by disinfectant sprays and momentary obstruction by personnel. Then, the processed multi-dimensional environmental parameters are uploaded in real time to the edge computing nodes of the corresponding sub-area via a wireless communication module. The edge computing nodes temporarily store the data and standardize its format to provide high-quality data support for subsequent analysis.

[0033] S200: Calculates parameter transfer coefficients and abnormal diffusion probabilities based on the spatial, airflow, and functional characteristics of sub-regions, identifies cross-regional diffusion risks and collaborative abnormal situations, and determines the cleanliness level of the current sub-region.

[0034] In this embodiment, parameter transfer coefficients and abnormal diffusion probabilities are calculated based on the spatial, airflow, and functional correlation characteristics of the sub-region to identify cross-regional diffusion risks and collaborative abnormal situations, and to determine the cleanliness level of the current sub-region. The specific process is as follows: S201: Standardize the environmental parameters of each sub-region, remove abnormal data caused by sensor failures, and extract parameter change trends and statistical characteristics; S202: Based on the sub-region topology and IoT map data analysis, determine the positional relationship and physical interval of adjacent sub-regions, and determine the intensity coefficient of the mutual influence of parameters; S203: Calculate the probability of time and range of pollutant diffusion across sub-regions based on the operation data of IoT devices in the air conditioning and ventilation system; S204: For related sub-areas with personnel and material flow, identify the pattern of coordinated changes in parameters by using flow frequency data recorded by IoT devices to determine the actual cleanliness level of each sub-area.

[0035] In the above process, multi-dimensional environmental parameters of each sub-region are obtained from edge computing nodes. First, standardization is performed (parameters of different dimensions are converted into data in the range of 0-1, such as bacterial colony count being converted according to "(actual value - minimum standard value) / (maximum standard value - minimum standard value)"). The 3σ criterion is used to remove outliers caused by sensor failures (such as extreme data where bacterial colony count exceeds the mean ± 3 times the standard deviation). Short-term missing data (such as temporary sensor offline time ≤ 3 minutes) are filled in using linear interpolation. Long-term missing data are marked as invalid and trigger equipment maintenance reminders. Then, the changing trends of each parameter (such as the rate of decrease in bacterial colony count after disinfection, and the rate of increase in dust content after personnel enter) and statistical characteristics (mean, standard deviation, peak value, duration of continuous anomalies) are extracted to form a structured dataset of "sub-region-parameter-feature".

[0036] Based on the hospital's sub-region topology (adjacency relationships, connectivity paths) and IoT map data, the positional relationships and physical intervals of adjacent sub-regions are analyzed to determine the intensity coefficient of mutual influence of parameters: the intensity coefficient for directly adjacent sub-regions without physical barriers (such as operating rooms and operating corridors, ICU wards and visitor access areas) is set at 0.8~0.9; the intensity coefficient for indirectly adjacent sub-regions or sub-regions with simple barriers (such as sterile pharmacies and drug storage areas) is set at 0.4~0.7; and the intensity coefficient for sub-regions with complete barriers such as physical walls and doors and independent airflow (such as general wards and infectious disease wards) is set at 0.1~0.3. The higher the coefficient, the more significant the mutual influence of environmental parameters (such as bacteria and particulate matter) between sub-regions, providing a basis for subsequent diffusion risk calculation.

[0037] Collect operational data from IoT devices in the hospital's air conditioning and ventilation system (HVAC), including supply air volume, air velocity, air pressure, return air ratio, HEPA filter operating status and purification efficiency, and disinfection equipment start / stop status for each sub-zone. Combine this data with the intensity coefficient determined in step S202 to calculate the probability of time and range for pollutants (bacteria, particulate matter, harmful gases) to diffuse across sub-zones. Diffusion time calculation: The transmission time of pollutants between sub-areas is calculated based on the length of the ventilation duct and the wind speed. Combined with the wind pressure difference and spatial volume within the sub-area, the uniform diffusion time of pollutants within the sub-area is calculated. The total diffusion time is obtained by summing the results (e.g., the probability of bacteria spreading from the operating room corridor to the adjacent operating room is "70% in 3-5 minutes"). Diffusion range probability calculation: Based on the air volume dilution effect, HEPA filter purification efficiency, and disinfection equipment action cycle, a concentration decay model is constructed. Combined with diffusion time, the concentration distribution of pollutants in the target sub-region is statistically analyzed to obtain the probability of diffusion range meeting or exceeding the standard (e.g., the probability of particulate matter diffusing from the passage area to the ICU exceeding the standard is 18%).

[0038] For interconnected sub-areas with personnel and material flow (such as operating rooms and ICUs, laboratories and inpatient wards, medical corridors and various functional areas), IoT devices such as access control systems (recording the entry and exit of medical staff and visitors), RFID tags (trajectories of medical devices and medications), and video counting sensors (real-time counting of personnel flow) are used to collect data on personnel entry and exit frequency (e.g., number of times medical staff enter and exit the operating room per hour, frequency of visitor flow in the ICU) and material transfer frequency (e.g., number of times sterile instruments are transferred, frequency of medical waste disposal). The flow frequency data is then correlated with the corresponding environmental parameters (bacterial colony count, dust content) of the sub-areas through time-series correlation analysis to identify patterns of coordinated change (e.g., when the frequency of visitor flow increases, the bacterial colony count in the corridors surrounding the ICU increases synchronously). Combined with the diffusion probability results from step S203, a comprehensive assessment of "parameter characteristics + diffusion risk + flow impact" is used to determine the actual cleanliness level (e.g., Class 100, Class 1000, Class 10,000, Class 100,000) of each sub-area. The core operating areas require particular attention to verifying whether both bacterial colony count and dust content meet the standards.

[0039] S300: Based on the preset parameters of the cleanliness level of the sub-area, multiple thresholds are set, and multiple early warnings are divided according to the correlation analysis results, and the corresponding sub-area equipment is linked to carry out differentiated control.

[0040] In this embodiment, multiple threshold values ​​are preset based on the cleanliness level of sub-regions, and multiple early warning levels are established based on correlation analysis results, triggering differentiated control of corresponding sub-region equipment. The specific process is as follows: S301: Set three levels of thresholds for various environmental parameters in different sub-regions: safety, early warning, and exceeding the standard. S302: Based on the association of multiple sub-regions, obtain the probability of abnormal spread and the scope of impact, divide the early warning into four levels, and divide the triggering conditions and response priorities corresponding to each level of early warning, and associate the IoT sound and light alarm devices in the corresponding sub-regions; S303: Real-time acquisition of parameter monitoring data; when parameters exceed the threshold, triggering control commands for the air conditioning, fresh air, air purification, and differential pressure regulation equipment in the affected sub-area. S304: During the control process, receive real-time feedback on the operating status of the equipment and parameter monitoring data from the sensor nodes, and dynamically adjust the control strategy until the environmental parameters of the sub-region return to the safe threshold.

[0041] In the above process, for sub-areas with different cleanliness levels, three-level thresholds are set for each core environmental parameter to adapt to hospital infection control requirements: Safety threshold (e.g., dust content in the air of a Class 100 operating room ≤ 350 particles / m³) 3 Bacterial colony count ≤10 CFU / m³ 3 ); Warning threshold (approaching the upper limit of the standard, such as 350-500 particles / m³ in the air of a Class 100 operating room). 3 Bacterial colony count 10-20 CFU / m³ 3 ); Exceeding the threshold (exceeding standard requirements, such as dust content in a Class 100 operating room > 500 particles / m³) 3 Bacterial colony count > 20 CFU / m³ 3 In particular, the bacterial colony count and harmful gas concentration thresholds in special areas such as infectious disease wards and ICUs need to be further tightened to ensure the safety of infection control.

[0042] Based on the results of multi-sub-region correlation analysis (probability of abnormal spread, scope of impact), the early warning is divided into four levels, and the triggering conditions and response priorities for each level are clearly defined (adapted to hospital emergency response procedures): Level 1 Warning (Low Risk): A parameter in a single sub-region triggers the warning threshold, with no risk of cross-regional spread (spread probability ≤ 10%), and the response priority is low (local notification only). Level 2 Warning (Medium Risk): A parameter in a single sub-area exceeds the standard, with a spread probability of ≤20%, affecting only the sub-area itself, and the response priority is medium (activate local audible and visual alarms + on-duty nurse reminder). Level 3 warning (high risk): Multiple parameters in a single sub-area exceed the standard or parameters are seriously exceeded (exceeding the threshold by 50%), with a spread probability of 20%-50%, affecting 1-2 adjacent core sub-areas (e.g., exceeding the standard in the operating room affects adjacent operating rooms), and has a high response priority (activating the area's audible and visual alarm + head nurse + infection control department real-time notification). Level 4 Alert (Extremely High Risk): Multiple sub-areas exceed parameters, with a spread probability >50%, affecting 3 or more sub-areas or involving critical areas such as infectious disease wards and ICUs. This level has the highest response priority (activation of hospital-wide infection control alert + emergency notification from the infection control department + hospital leadership). Each alert level is linked to the corresponding IoT-based audible and visual alarm devices in the sub-areas (such as alarm lights at operating room entrances and alarm terminals at nurse stations) to ensure rapid location of at-risk areas when an alert is triggered.

[0043] The system receives parameter monitoring data from sensor nodes in each sub-area in real time and compares it with preset thresholds. If a parameter reaches a warning threshold, the corresponding sub-area's audible and visual alarm device is activated, and a risk warning is simultaneously displayed on the nurse station terminal. If a parameter exceeds the threshold, based on the diffusion range of step S203, control commands are sent to IoT devices in the affected sub-area. Air conditioning and fresh air systems: Increase fresh air volume (e.g., from 60m³ / h in operating rooms). 3 / h・human height increased to 80m 3 / h・person), increase the number of air exchanges; Air purification equipment: Switch to high-efficiency operation mode (HEPA filter fan speed increased by 20%), and start the mobile disinfection robot for targeted disinfection; Differential pressure regulating equipment: Adjusts the differential pressure in sub-regions (increasing the positive pressure in the core area relative to adjacent areas to 8~10Pa), blocking the diffusion path of pollutants; Disinfection equipment: Activate ultraviolet disinfection lamps (in unoccupied environments) or atomization disinfection equipment (in occupied environments) to specifically reduce the number of bacterial colonies.

[0044] After the control system is activated, it receives real-time feedback on the operating status of air conditioners, air purifiers, disinfection equipment, etc. (such as actual fresh air volume and disinfection equipment operating power) and parameter monitoring data from sensor nodes, and analyzes the trend of parameter changes. If the parameter decrease rate is ≥10% / minute (e.g., bacterial colony count decreases by more than 10% within 10 minutes), maintain the current control strategy; If the rate of decrease is less than 5% / minute, further optimize the control parameters (such as increasing the fresh air volume by another 15% and increasing the operating time of the disinfection equipment). If the parameters rebound, trace the spread path to see if there are any omissions (such as failure to close a passageway door in a certain area), supplement and adjust the equipment in the related sub-area, and notify medical staff to take manual intervention measures (such as temporarily restricting the movement of people).

[0045] The environmental parameters of all affected sub-regions will be continuously and dynamically adjusted until they return to safe thresholds. At this point, the early warning and enhanced control measures will be stopped, and normal operation will be restored. The entire process of this early warning and control will be recorded for subsequent infection control analysis.

[0046] Corresponding to the aforementioned embodiments of the IoT-based clean environment monitoring and early warning method, this application also provides embodiments of an IoT-based clean environment monitoring and early warning system.

[0047] Figure 5 This is a block diagram illustrating an IoT-based clean environment monitoring and early warning system according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a sub-region multi-parameter acquisition module 401, a multi-sub-region association module 402, and a cleanliness classification early warning module 403; wherein: The sub-region multi-parameter acquisition module 401 is used to acquire the monitoring range, divide it into multiple sub-regions, and deploy identifiable multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters of each sub-region. The multi-sub-region association module 402 is used to calculate the parameter transmission coefficient and abnormal diffusion probability based on the spatial, airflow and functional association characteristics of the sub-region, identify cross-region diffusion risks and collaborative abnormal situations, and determine the cleanliness level of the current sub-region. The cleanliness classification early warning module 403 is used to divide the early warning into multiple levels based on the preset parameters of the cleanliness level of the sub-area and the results of correlation analysis, and to link the corresponding sub-area equipment for differentiated control.

[0048] In this embodiment, the sub-region multi-parameter acquisition module 401 acquires the monitoring range, divides it into multiple sub-regions, and deploys tagged multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters of each sub-region; the multi-sub-region association module 402 calculates the parameter transmission coefficient and abnormal diffusion probability based on the spatial, airflow, and functional association characteristics of the sub-regions, identifies cross-regional diffusion risks and collaborative abnormal situations, and determines the current cleanliness level of the sub-region; the cleanliness classification early warning module 403 divides the early warning into multiple levels based on the preset parameters of the cleanliness level of the sub-regions and combines the association analysis results, and links the corresponding sub-region equipment for differentiated control; through the above methods, multimodal sensor nodes are dynamically deployed, a multi-level early warning and differentiated control mechanism is established, the accuracy and effectiveness of hospital environmental infection control are improved, medical quality and patient safety are ensured, detection accuracy is improved, and the needs of refined and real-time infection control are met.

[0049] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0050] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0051] Accordingly, this application also provides an electronic device, including: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the IoT-based clean environment monitoring and early warning method described above. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities within a clean environment monitoring and early warning system based on the Internet of Things provided in an embodiment of the present invention, except... Figure 6In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0052] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned IoT-based clean environment monitoring and early warning method. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0053] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0054] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A clean environment monitoring and early warning method based on the Internet of Things, characterized in that, Includes the following steps: The monitoring range is determined, divided into multiple sub-regions, and labeled multimodal sensor nodes are deployed in each sub-region to collect multi-dimensional environmental parameters of each sub-region. Based on the spatial, airflow, and functional characteristics of the sub-region, the parameter transfer coefficient and abnormal diffusion probability are calculated to identify cross-regional diffusion risks and collaborative abnormal situations, and to determine the cleanliness level of the current sub-region. Based on the preset parameters and thresholds of the cleanliness level of the sub-area, and combined with the results of correlation analysis, multiple levels of early warning are divided, and the corresponding sub-area equipment is linked to carry out differentiated control.

2. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 1, characterized in that, In the steps of acquiring the monitoring range, dividing it into multiple sub-regions, deploying identifiable multimodal sensor nodes in each sub-region, and collecting multi-dimensional environmental parameters of each sub-region: Obtain the total area of ​​clean environment monitoring and divide it into multiple sub-areas, assigning each sub-area a classification label and a geographical label; among which, the classification labels include core operation area, auxiliary function area, and passage connection area; Based on the area, cleanliness level, and distribution of environmentally sensitive points of the sub-area, plan the deployment density of IoT multimodal sensor nodes and install the sensor nodes.

3. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 2, characterized in that, In the steps of planning the deployment density of IoT multimodal sensor nodes based on the sub-area area, cleanliness level, and distribution of environmentally sensitive points, and then installing the sensor nodes: An IoT gateway is used to bind nodes to sub-area identifiers and connect them to the local IoT communication network.

4. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 3, characterized in that, After planning the deployment density of IoT multimodal sensor nodes based on the sub-area area, cleanliness level, and distribution of environmentally sensitive points, and then installing the sensor nodes: The sensor node acquisition frequency is dynamically adjusted according to the cleanliness level of the sub-region. After preliminary noise reduction by the nodes, the acquired data is uploaded to the sub-region edge computing node in real time via wireless communication.

5. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 1, characterized in that, In the steps of calculating parameter transfer coefficients and abnormal diffusion probabilities based on the spatial, airflow, and functional correlation characteristics of sub-regions, identifying cross-regional diffusion risks and collaborative abnormal situations, and determining the current cleanliness level of the sub-region: The environmental parameters of each sub-region are standardized, abnormal data caused by sensor failure are removed, and the parameter change trends and statistical characteristics are extracted. Based on the analysis of sub-region topology and IoT map data, the positional relationship and physical interval of adjacent sub-regions are determined to establish the intensity coefficient of mutual influence of parameters.

6. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 5, characterized in that, After analyzing the locational relationships and physical intervals of adjacent sub-regions based on sub-region topology and IoT map data, and determining the intensity coefficients of parameter interactions: Based on the operational data of IoT devices in the air conditioning and ventilation system, calculate the probability of time and range of pollutant diffusion across sub-regions; For related sub-areas with personnel and material flow, the actual cleanliness level of each sub-area is determined by identifying the pattern of coordinated changes in parameters through flow frequency data recorded by IoT devices.

7. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 1, characterized in that, In the process of setting multiple thresholds based on pre-defined parameters for the cleanliness level of sub-areas, and dividing multiple early warning levels based on correlation analysis results, and then linking the corresponding sub-area equipment for differentiated control: Three levels of thresholds—safe, early warning, and exceeding—are set for various environmental parameters in different sub-regions. Based on the correlation of multiple sub-regions to obtain the probability of abnormal spread and the scope of impact, the early warning is divided into four levels; Real-time parameter monitoring data is acquired, and when the parameters exceed the threshold, control commands are triggered for the air conditioning, fresh air, air purification, and differential pressure regulation equipment in the affected sub-area.

8. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 7, characterized in that, In the step of obtaining the probability of abnormal spread and the scope of impact based on the correlation of multiple sub-regions, and classifying the early warning into four levels: Divide the triggering conditions and response priorities corresponding to each level of early warning, and associate them with the IoT sound and light alarm devices in the corresponding sub-regions.

9. The clean environment monitoring and early warning method based on the Internet of Things as described in claim 8, characterized in that, In the step of acquiring parameter monitoring data in real time and triggering control commands for the air conditioning, fresh air, air purification, and differential pressure regulation equipment in the affected sub-area when the parameters exceed the threshold: During the control process, the system receives real-time feedback on the operating status of the equipment and parameter monitoring data from the sensor nodes, and dynamically adjusts the control strategy until the environmental parameters of the sub-region return to the safe threshold.

10. A clean environment monitoring and early warning system based on the Internet of Things (IoT), employing the clean environment monitoring and early warning method based on the IoT as described in claim 1, characterized in that, This includes a sub-region multi-parameter acquisition module, a multi-sub-region association module, and a cleanliness classification early warning module; among which: The sub-region multi-parameter acquisition module is used to acquire the monitoring range, divide it into multiple sub-regions, and deploy identifiable multimodal sensor nodes in each sub-region to collect multi-dimensional environmental parameters of each sub-region. The multi-sub-region association module is used to calculate the parameter transmission coefficient and abnormal diffusion probability based on the spatial, airflow and functional association characteristics of the sub-region, identify cross-region diffusion risks and collaborative abnormal situations, and determine the cleanliness level of the current sub-region. The cleanliness classification and early warning module is used to divide the early warning into multiple levels based on preset parameters and thresholds of the cleanliness level of the sub-area, and to link the corresponding sub-area equipment for differentiated control.

Images