Hospital health assessment system based on data stream

Abstract

The invention relates to the technical field of medical management, in particular to a hospital health assessment system based on data flow, and the system comprises a medical waste pollution diffusion recognition module which obtains medical waste circulation data, analyzes the retention time, calculates the pollution diffusion range in combination with the temperature and humidity and the airflow direction, screens out an area exceeding a contact threshold value, and carries out the data flow analysis; and generating a medical waste abnormal contact risk analysis result. According to the method, the pollution diffusion range can be accurately calculated by acquiring the medical waste circulation data and combining factors such as the temperature, the humidity and the airflow direction, the area exceeding the safety threshold value is screened, and the pollution risk identification is more accurate. The contact density is calculated in combination with the patient track of the ward, and the risk inpatient area boundary can be dynamically adjusted, so that the precise division of the pollution area range is realized, and the infection risk assessment is more flexible and reliable. Based on bacteria detection, air quality monitoring and violation disposal records, the trend change of pollution events can be effectively evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of medical management, and particularly to a hospital hygiene assessment system based on data streams. Background Art

[0002] The technical field of medical management includes the optimal allocation of medical resources, hospital operation management, patient health data management, improvement of medical service processes, etc. The purpose of this technical field is to improve the management efficiency of medical institutions by means of informatization, including aspects such as medical resource scheduling, patient information management, health supervision, and coordination of medical staff work. With the development of digitalization in the medical industry, medical management technology continuously combines computer systems, big data analysis, and intelligent tools to improve the operation efficiency of hospitals and the quality of medical services.

[0003] Among them, the hospital hygiene assessment system refers to an informatization system for monitoring, recording, and evaluating the internal hygiene conditions of a hospital. This system mainly collects and analyzes data on aspects such as the compliance of medical environment hygiene standards, the cleanliness of hospital equipment, and the hygiene operation specifications of medical staff. Its main methods include collecting environmental hygiene data through sensing devices, classifying and sorting hygiene indicators using data analysis methods, and identifying and warning abnormal situations through rule setting.

[0004] The existing technology mainly relies on sensing devices to collect environmental hygiene data and identifies and warns abnormalities by setting rules. However, in actual applications, there is a lack of accurate calculation of the pollution diffusion path and the scope of pollution impact, which easily leads to inaccurate division of risk areas and affects the pertinence of subsequent disinfection work. In addition, in terms of ward risk assessment, only static hygiene standards are relied on for judgment, and the dynamic changes in patient activity trajectories and pollutant transmission paths are not fully considered, resulting in some high-risk areas that may not be discovered in time. For the trend analysis of pollution events, the existing methods mainly conduct retrospective analysis based on historical data, making it difficult to accurately predict the pollution growth trend and affecting the hospital's ability to take preventive measures in advance. In the analysis of the execution of cleaning tasks, the existing technology only focuses on the completion of tasks and lacks in-depth analysis of the execution deviation of cleaning tasks, which may lead to insufficient cleaning frequency in some wards but without timely warning, affecting the overall environmental hygiene level. For the overall hygiene assessment of a hospital, the existing technology mainly relies on a single environmental data indicator and lacks comprehensive calculation of multiple factors such as cleaning tasks, pollution events, and patient contact density, resulting in one-sided assessment results and making it difficult to accurately reflect the dynamic change trend of the overall hygiene condition of the hospital, thereby affecting the accurate decision-making of hygiene management. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, an embodiment of the present invention provides a hospital hygiene assessment system based on data streams. The technical solution is as follows:

[0006] A hospital hygiene assessment system based on data flow, the system comprising:

[0007] The medical waste pollution diffusion identification module obtains medical waste transfer data, analyzes the residence duration, calculates the pollution diffusion range in combination with temperature, humidity and air flow direction, screens the areas exceeding the contact threshold, and generates the analysis result of the abnormal contact risk of medical waste;

[0008] The risk ward dynamic determination module, based on the analysis result of the abnormal contact risk of medical waste, calculates the contact density according to the patient trajectories in the wards, screens the risk wards, and generates the dynamic risk ward boundary;

[0009] The pollution event trend analysis module, based on the dynamic risk ward boundary, screens the wards with a growth rate exceeding the threshold according to bacterial detection, air quality and illegal disposal records, and generates the pollution event trend assessment result;

[0010] The cleaning task execution deviation analysis module, based on the pollution event trend assessment result, obtains the cleaning task execution data to calculate the execution deviation value, screens the wards with a cleaning frequency lower than the threshold, and obtains the deviation degree analysis result;

[0011] The hospital hygiene assessment module, based on the deviation degree analysis result, compares the ward cleaning compliance rate, calculates the environmental safety index in combination with the change in the frequency of pollution events, analyzes the hygiene change trend, and obtains the hospital ward hygiene assessment result.

[0012] As a further solution of the present invention, the analysis result of the abnormal contact risk of medical waste includes the abnormal contact rate of medical equipment, the number of abnormal contacts of medical staff, and the pollution diffusion coverage area; the dynamic risk ward boundary includes the polluted ward area, the patient contact density level, and the ward infection risk level; the pollution event trend assessment result includes the incidence rate of hospital pollution events, the growth rate of pollution events, and the spatial distribution range of pollution events; the deviation degree analysis result includes the cleaning task completion rate, the cleaning task delay duration, and the ward cleaning deviation level; the hospital ward hygiene assessment result includes the overall hospital hygiene index, the ward environmental safety score, and the ward area hygiene risk level.

[0013] As a further solution of the present invention, the medical waste pollution diffusion identification module includes:

[0014] The medical waste transfer analysis sub-module obtains the medical waste transfer data of the hospital's infectious disease departments, emergency rooms, and operating rooms, extracts the waste generation time, storage location, and treatment time, calculates the residence duration of medical waste, combines the waste storage environment temperature, humidity, and air flow direction, screens the medical waste with abnormal pollution diffusion conditions, calls the waste type classification parameters, judges the proportion of infectious waste, and generates the pollution characteristics of medical waste;

[0015] Based on the medical waste pollution characteristics, the pollution diffusion range calculation sub-module calls the ambient temperature, humidity, and air flow direction of the storage environment to calculate the pollution diffusion radius, extracts the pollution diffusion path data, filters the areas covering medical equipment and personnel activity areas, analyzes the pollution diffusion influence range, and combines the residence time of the medical waste to filter the areas where the pollution duration exceeds the preset storage time limit, and generates the medical waste pollution diffusion range.

[0016] Based on the medical waste pollution diffusion range, the abnormal contact risk identification sub-module calls the usage frequency of medical equipment, the equipment contact duration, and the personnel operation records to calculate the frequency of medical equipment contacting pollution, filters the pollution contact areas exceeding the equipment usage safety threshold, calculates the residence time of medical staff within the pollution diffusion range, judges the abnormal contact situation, filters the medical areas exceeding the contact duration threshold or contact frequency threshold, and generates the medical waste abnormal contact risk analysis result.

[0017] As a further solution of the present invention, the risk ward dynamic determination module includes:

[0018] Based on the medical waste abnormal contact risk analysis result, the patient activity data analysis sub-module obtains the patient activity trajectory data of the inpatient ward and the intensive care unit, extracts the patient residence time and the number of patient movements per unit time, filters the patients whose movement frequency between wards exceeds the preset movement frequency threshold, calls the ward type data, judges the change trend of the patient density, and generates the patient activity distribution characteristics.

[0019] Based on the patient activity distribution characteristics, the ward contact density calculation sub-module calls the patient residence time and the number of patients per unit area of the ward to calculate the ward contact density, compares it with the ward infection risk threshold, filters the wards exceeding the infection risk threshold, combines the medical waste abnormal contact risk analysis result, adjusts the ward infection risk level, and generates the ward contact risk index.

[0020] Based on the ward contact risk index, the dynamic risk ward boundary generation sub-module calls the medical waste pollution diffusion radius, filters the wards within the pollution diffusion range, calculates the intersection area of the ward contact risk index and the pollution influence range, adjusts the ward division boundary, filters the wards with abnormal changes in the risk level, and establishes the dynamic risk ward boundary.

[0021] As a further solution of the present invention, the pollution event trend analysis module includes:

[0022] The pollution event data extraction sub-module obtains the environmental pollution event data within the hospital based on the dynamic risk ward area boundary, extracts the bacterial test results, air quality monitoring data, medical waste illegal disposal records, and the number of pollution events occurring within a specified time period, screens the ward areas where the number of pollution events exceeds the pollution alarm threshold, and combines the ward contact density to adjust the pollution event statistical scope to generate pollution event distribution data;

[0023] The pollution event growth rate calculation sub-module obtains the pollution event data for adjacent time periods based on the pollution event distribution data, calculates the pollution event growth rate, screens the ward areas where the pollution event growth rate exceeds the growth threshold, and combines the dynamic risk ward area boundary to adjust the list of pollution event abnormal ward areas to generate pollution event growth trend information;

[0024] The pollution trend assessment sub-module, based on the pollution event growth trend information, calls the pollution event distribution data and the ward contact density, calculates the correlation between the pollution event growth rate and the ward contact risk, screens the ward areas where the pollution event growth rate and the contact density change rate increase synchronously, adjusts the list of risk pollution ward areas, and establishes the pollution event trend assessment result.

[0025] As a further solution of the present invention, for extracting the bacterial test results, air quality monitoring data, medical waste illegal disposal records, and the number of pollution events occurring within a specified time period, the formula is used:

[0026] N PEV =N BEX +N AQX +N MWV ;

[0027] Calculate the total number of pollution events N PEV ;

[0028] where N BEX represents the number of events with excessive bacterial culture results, N AQX represents the number of events with excessive air quality monitoring data, N MWV represents the number of events of illegal storage of medical waste.

[0029] As a further solution of the present invention, for calculating the pollution event growth rate G PEV , the formula is used:

[0030]

[0031] where N CUR represents the total number of pollution events in the current time period, and N PREV represents the total number of pollution events in the previous time period.

[0032] As a further solution of the present invention, for calculating the correlation C between the growth rate of pollution events and the contact risk in the ward PEV_CD_MOD , the formula is adopted:

[0033]

[0034] where G PEV represents the growth rate of pollution events, represents the mean value of the growth rate of pollution events, R CD represents the change rate of the contact density in the ward, represents the mean value of the change rate of the contact density in the ward, E SRC represents the influence factor of the spread of pollution sources, T PEV_DEV represents the time series deviation parameter of pollution events.

[0035] As a further solution of the present invention, the cleaning task execution deviation analysis module includes:

[0036] The cleaning task data extraction sub-module obtains the cleaning task execution data of the infectious disease department, ward, and operating room based on the pollution event trend evaluation result, extracts the cleaning task completion time, task delay duration, number of unexecuted tasks, and cleaning area coverage rate, calculates the proportion of completed cleaning tasks within a specified time, screens the wards with abnormal cleaning task execution, and combines the dynamic risk ward boundary to establish the cleaning task execution status data;

[0037] The cleaning task deviation calculation sub-module calls the cleaning task completion time, task delay duration, and number of unexecuted tasks based on the cleaning task execution status data, calculates the cleaning task execution deviation value, screens the wards with the cleaning task execution deviation exceeding the task specification threshold, combines the cleaning area coverage rate, adjusts the cleaning task quality evaluation parameters, and generates the cleaning task deviation information;

[0038] The cleaning execution deviation level classification sub-module classifies the cleaning task execution deviation level according to the growth rate of pollution events and the cleaning task deviation based on the cleaning task deviation information, and establishes the deviation degree analysis result.

[0039] As a further solution of the present invention, the hospital hygiene assessment module includes:

[0040] The ward cleaning compliance rate calculation sub-module obtains the cleaning task execution data of each ward based on the deviation degree analysis result, extracts the cleaning task completion rate, cleaning coverage area, and cleaning task delay duration, calculates the ward cleaning compliance rate, screens the wards with the cleaning compliance rate lower than the cleaning benchmark threshold, and combines the cleaning task deviation level to generate the ward cleaning compliance rate data;

[0041] Based on the data of the ward cleaning compliance rate, the environmental safety index calculation sub-module calls the frequency change of pollution incidents, calculates the correlation coefficient between the growth rate of pollution incidents and the ward cleaning compliance rate, combines the dynamic risk ward boundary, adjusts the environmental safety evaluation standard, and generates the ward environmental safety index;

[0042] Based on the ward environmental safety index, the hospital overall hygiene assessment sub-module calls the cleaning task deviation level, calculates the change trend of ward hygiene risks, screens the wards with abnormal risk fluctuations, combines the overall hospital ward hygiene data, calculates the hospital overall hygiene assessment value, and establishes the hospital ward hygiene assessment result.

[0043] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0044] In the present invention, by obtaining the medical waste transfer data and combining factors such as temperature, humidity, and air flow direction, the pollution diffusion range can be accurately calculated, and the areas exceeding the safety threshold can be screened, making the identification of pollution risks more accurate. Combining the patient trajectories in the ward and calculating the contact density, the risk ward boundary can be dynamically adjusted, thereby achieving a precise division of the pollution area range and making the infection risk assessment more flexible and reliable. Based on bacterial detection, air quality monitoring, and violation disposal records, the trend changes of pollution incidents can be effectively evaluated, high-growth rate wards can be screened, and the areas that may have environmental safety hazards can be accurately locked, which helps the hospital take timely intervention measures to prevent pollution from expanding. Combining the cleaning task execution data, calculating the execution deviation value, screening the wards with low-frequency cleaning, and quantitatively evaluating the cleaning task execution quality make the hygiene management more refined and avoid the blindness and inefficiency of cleaning work. By comparing the ward cleaning compliance rate and combining the frequency change of pollution incidents, calculating the environmental safety index can intuitively reflect the dynamic change trend of the hospital hygiene status, facilitate the management personnel to quickly respond to hygiene problems, optimize the cleaning resource allocation, and improve the overall environmental safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0046] Figure 1 It is the system module diagram of the present invention;

[0047] Figure 2 It is the system framework diagram of the present invention;

[0048] Figure 3 It is the schematic diagram of the medical waste pollution diffusion identification module of the present invention;

[0049] Figure 4 It is a schematic diagram of the dynamic determination module for the risk ward area of the present invention;

[0050] Figure 5 It is a schematic diagram of the pollution event trend analysis module of the present invention;

[0051] Figure 6 It is a schematic diagram of the cleaning task execution deviation analysis module of the present invention;

[0052] Figure 7 It is a schematic diagram of the hospital hygiene assessment module of the present invention. Detailed implementation manners

[0053] Next, in combination with the accompanying drawings, the technical solutions in the present invention will be described.

[0054] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0055] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same.

[0056] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in a non-subscript form such as W1. When their differences are not emphasized, the meanings they express are the same.

[0057] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail in combination with the accompanying drawings and specific embodiments.

[0058] Please refer to Figure 1 , the embodiments of the present invention provide a hospital hygiene assessment system based on data flow. The system includes:

[0059] The medical waste pollution diffusion identification module obtains medical waste transfer data, analyzes the residence time, calculates the pollution diffusion range in combination with temperature, humidity and air flow direction, screens the areas exceeding the contact threshold, and generates the analysis result of the abnormal contact risk of medical waste;

[0060] Based on the analysis results of the abnormal contact risk of medical waste, the dynamic determination module of risk wards calculates the contact density according to the patient trajectories in the wards, screens the risk wards, and generates the boundary of the dynamic risk ward area;

[0061] Based on the boundary of the dynamic risk ward area, the pollution event trend analysis module screens the wards with a growth rate exceeding the threshold according to bacterial detection, air quality, and illegal disposal records, and generates the evaluation results of the pollution event trend;

[0062] Based on the evaluation results of the pollution event trend, the cleaning task execution deviation analysis module obtains the cleaning task execution data to calculate the execution deviation value, screens the wards with a cleaning frequency lower than the threshold, and obtains the analysis results of the deviation degree;

[0063] Based on the analysis results of the deviation degree, the hospital hygiene assessment module compares the cleaning compliance rate of the wards, calculates the environmental safety index in combination with the change in the frequency of pollution events, analyzes the hygiene change trend, and obtains the hospital ward hygiene assessment results.

[0064] The analysis results of the abnormal contact risk of medical waste include the abnormal contact rate of medical equipment, the number of abnormal contacts of medical staff, and the pollution diffusion coverage area. The boundary of the dynamic risk ward area includes the polluted ward area, the patient contact density level, and the ward infection risk level. The evaluation results of the pollution event trend include the incidence rate of hospital pollution events, the growth rate of pollution events, and the spatial distribution range of pollution events. The analysis results of the deviation degree include the cleaning task completion rate, the cleaning task delay duration, and the ward cleaning deviation level. The hospital ward hygiene assessment results include the overall hospital hygiene index, the ward environmental safety score, and the ward area hygiene risk level.

[0065] Please refer to Figure 2 and Figure 3 , the medical waste pollution diffusion identification module includes:

[0066] The medical waste transfer analysis sub-module obtains the medical waste transfer data of the hospital's infectious disease departments, emergency rooms, and operating rooms, extracts the waste generation time, storage location, and treatment time, calculates the residence time of medical waste, combines the temperature, humidity, and air flow direction of the waste storage environment, screens the medical waste with abnormal pollution diffusion conditions, calls the waste type classification parameters, judges the proportion of infectious waste, and generates the pollution characteristics of medical waste;

[0067] The medical waste transfer analysis sub-module obtains the medical waste transfer data of the hospital's infectious disease departments, emergency rooms, and operating rooms, extracts the waste generation time, storage location, and treatment time. First, it is necessary to retrieve relevant log data in the hospital information management system (HIS) or the medical waste management system (MWMS), including the medical waste generation records of each department. The specific extraction method can obtain the daily data transfer situation through an automated script or an API interface. The record of the waste generation time usually comes from after medical activities are completed, such as the waste generated after a surgery or after a patient's treatment. The storage location can be obtained from the RFID-tagged storage areas within the hospital, and the treatment time is determined by the data provided by the medical waste collection or destruction unit. When calculating the residence time of medical waste, the formula T = T 处理 -T 生成 can be used, where T 处理 is the treatment time, and T 生成 is the waste generation time. Suppose the T 生成 of a certain medical waste is 10:30 on February 1, 2025, and T 处理 is 18:45 on February 1, 2025. Then the residence time T = 18:45 - 10:30 = 8 hours and 15 minutes. Combining the temperature, humidity, and air flow direction data of the waste storage environment, sensors need to be installed in the medical waste storage area to collect data regularly. The temperature T' can be obtained through a temperature sensor (unit: °C), the humidity H is obtained through a humidity sensor (unit: %RH), and the air flow direction A is obtained by an air quality monitoring device combined with a wind direction sensor (unit: °). When screening medical waste with abnormal pollution diffusion conditions, the abnormal temperature threshold T' 异常 ≥30 °C or T' 异常 ≤5 °C, the abnormal humidity threshold H 异常 ≥80, and the air flow direction angle deviation A 异常 ≥45° can be set. If the temperature at a certain storage point is 32 °C, the humidity is 85%RH, and the wind direction is 60°, then it meets the conditions of T' 异常 and H 异常 , and the medical waste in this area needs to be marked as having abnormal pollution diffusion conditions. When calling the waste type classification parameters, it is necessary to rely on the medical waste classification standards. For example, the infectious waste stipulated by the WHO includes blood contaminants, medical device contaminants, biological tissue residues, etc. It is determined whether a certain batch of medical waste contains infectious components through automatic classification or manual review of medical waste identification. Suppose the total amount of medical waste in a certain area of the hospital on a certain day is 100 kg, and the proportion of infectious waste is 60 kg. Then the proportion of infectious waste Finally, the pollution characteristics of medical waste are generated.

[0068] Based on the pollution characteristics of medical waste, the pollution diffusion range calculation sub-module calls the stored environmental temperature, humidity, and air flow direction, calculates the pollution diffusion radius, extracts pollution diffusion path data, filters the areas covering medical equipment and personnel activity areas, analyzes the pollution diffusion influence range, combines the residence time of medical waste, filters the areas where the pollution duration exceeds the preset storage time limit, and generates the medical waste pollution diffusion range.

[0069] Based on the pollution characteristics of medical waste, the pollution diffusion range calculation sub-module calls the stored environmental temperature, humidity, and air flow direction, calculates the pollution diffusion radius. First, it is necessary to combine the environmental data of the storage environment with the waste pollution characteristics, extract the air flow diffusion model around the pollution source, and use the Gaussian diffusion model to calculate the pollutant diffusion radius R. The calculation formula is where Q is the pollution source emission (mg / s), u is the air flow speed (m / s), and H' is the effective diffusion height (m) of the waste storage area. Assuming Q = 100 mg / s, u = 1.5 m / s, and H' = 2 m, then When extracting the pollution diffusion path data, an air quality monitoring device is used in combination with fluid simulation software to analyze the movement trajectory of pollution particles. When filtering the areas covering medical equipment and personnel activity areas, the hospital's electronic health record system (EHR) and hospital layout data are combined to mark the affected medical equipment and patient activity areas. Assuming that the pollution radius R of a certain area is 4.6 m, and this area contains equipment such as ventilators, monitors, and infusion pumps, it is necessary to mark that these equipment may be polluted. Combining the residence time of medical waste, the areas where the pollution duration exceeds the preset storage time limit are filtered. Assuming that the storage time limit T 限 = 6 hours for a certain hospital, and the storage time of medical waste in a certain area is 8 hours, then it exceeds the time limit by 2 hours, and finally the medical waste pollution diffusion range is generated.

[0070] Based on the medical waste pollution diffusion range, the abnormal contact risk identification sub-module calls the medical equipment usage frequency, equipment contact duration, and personnel operation records, calculates the frequency of medical equipment contact with pollution, filters the pollution contact areas that exceed the equipment usage safety threshold, calculates the residence time of medical staff within the pollution diffusion range, judges the abnormal contact situation, filters the medical areas that exceed the contact duration threshold or contact frequency threshold, and generates the analysis result of the abnormal contact risk of medical waste.

[0071] Based on the medical waste pollution diffusion range, the abnormal contact risk identification sub-module calls the medical equipment usage frequency, equipment contact duration, and personnel operation records, calculates the frequency of medical equipment contact with pollution. First, it is necessary to obtain the usage log of medical equipment, including equipment switch records, usage time, operator identity, etc., and calculate the pollution contact frequency: Assuming that the total number of times a ventilator is used in a certain hospital on a certain day is 100 times, and 40 times are used in the polluted area, then: When screening for contaminated contact areas that exceed the safety threshold for device use, it is necessary to set the safety threshold for use, P 安全 ≤ 30%, if P 接触 > P 安全 , then the device area needs to be further investigated. To calculate the residence time of medical staff within the range of contaminated spread, it is necessary to obtain personnel activity trajectory data, such as IC card swipe records and video surveillance data, and calculate the residence time: T 滞留 = T 离开 - T 进入 ; Suppose a nurse's T 进入 = 14:00, T 离开 = 16:30, then T 滞留 = 16:30 - 14:00 = 2 hours and 30 minutes. When judging abnormal contact situations, set the contact duration threshold T 阈 = 2 hours. If T 滞留 > T 阈 , then mark that the person has abnormal contact, screen medical areas that exceed the contact duration threshold or contact frequency threshold, and finally generate the analysis result of the risk of abnormal contact with medical waste.

[0072] Please refer to Figure 2 and Figure 4 , the risk ward dynamic determination module includes:

[0073] The patient activity data analysis sub-module, based on the analysis result of the risk of abnormal contact with medical waste, obtains the patient activity trajectory data of the inpatient wards and intensive care units, extracts the patient's stay time and the number of movements per unit time of the patient, screens patients whose movement frequency between wards exceeds the preset movement frequency threshold, calls the ward type data, and judges the changing trend of the patient density to generate the patient activity distribution characteristics;

[0074] The patient activity data analysis sub-module, based on the analysis result of the risk of abnormal contact with medical waste, obtains the patient activity trajectory data of the inpatient wards and intensive care units. First, it is necessary to access the patient monitoring database within the hospital, which usually includes patient ICU dynamic monitoring, electronic medical records (EMR) and movement trajectory data. When extracting the patient's stay time, directly read the patient's admission time, discharge time, and each card swipe or electronic wristband record in the ward from the ward access record, calculate the stay time in each ward, and the number of movements per unit time of the patient can be obtained through RFID positioning or ward entrance and exit management records, calculate the ward switching frequency of the patient within a given time interval. When screening patients whose movement frequency between wards exceeds the preset movement frequency threshold, set the movement frequency threshold N 移动阈值 , this value is determined according to the hospital infection control standard. If the number of ward movements N 移动 of a patient within a unit time (such as 24 hours) exceeds N 移动阈值, then it is marked as a highly mobile patient, assuming N 移动阈值 = 5 times / 24 hours, and if a certain patient moves 8 times in a day, then this patient is screened as a highly mobile patient. When calling the ward type data and judging the change trend of patient density, combined with the ward area and the current number of inpatients, calculate the patient density D per square meter 病房 , assuming that the area of a certain ICU ward is 30㎡ and there are currently 6 patients, then D 病房 = 6 / 30 = 0.2 persons / ㎡. Compare the patient densities at different time periods. If ΔD 病房 = D 当前 - D 之前 is greater than the set threshold, it indicates that the patient density in the ward has increased, and finally generate the patient activity distribution characteristics.

[0075] The ward contact density calculation sub-module, based on the patient activity distribution characteristics, calls the patient stay time and the number of patients per unit area of the ward to calculate the ward contact density, compares it with the ward infection risk threshold, screens the wards exceeding the infection risk threshold, and combines the analysis results of the abnormal contact risk of medical waste to adjust the ward infection risk level and generate the ward contact risk index;

[0076] When the ward contact density calculation sub-module, based on the patient activity distribution characteristics, calls the patient stay time and the number of patients per unit area of the ward to calculate the ward contact density, the formula is used, where N 病房患者 represents the total number of patients in the ward, and A 病房面积 represents the ward area (㎡). Assuming that the area of a certain general ward is 50㎡ and there are 10 patients at the same time, then the contact density is When comparing with the ward infection risk threshold, set the infection risk threshold D 风险阈值 , if D 接触 > D 风险阈值 , then mark this ward as a high-risk area. Assuming D 风险阈值 = 0.15 persons / ㎡, then this ward is classified as a high-risk area because 0.2 > 0.15. After screening the wards exceeding the infection risk threshold, combine the analysis results of the abnormal contact risk of medical waste, extract the medical waste data in the polluted area. If high-risk infectious medical waste is found in a certain ward, further increase the risk level of this ward. When adjusting the ward infection risk level, set the grading criteria, such as low risk (D 接触 ≤0.1 persons / ㎡), medium risk (0.1 < D 接触 ≤0.2 persons / ㎡), high risk (D 接触 > 0.2 persons / ㎡). Assuming that the calculated D 接触 of a certain ward is 0.22 persons / ㎡, then it is classified as a high-risk ward, and finally generate the ward contact risk index.

[0077] The dynamic risk ward area boundary generation sub-module, based on the ward contact risk index, calls the medical waste pollution diffusion radius, screens the wards within the pollution diffusion range, calculates the intersection area between the ward contact risk index and the pollution influence range, adjusts the ward area division boundary, screens the wards with abnormal changes in risk levels, and establishes the dynamic risk ward area boundary.

[0078] The dynamic risk ward area boundary generation sub-module, based on the ward contact risk index, calls the medical waste pollution diffusion radius data, screens the wards within the pollution diffusion range, and when calculating the intersection area between the ward contact risk index and the pollution influence range, extracts the coordinate information of all high-risk wards, and calculates the Euclidean distance between the ward and the medical waste pollution diffusion center. Set the pollution source center coordinates as (x 污染源坐标 , y 污染源坐标 ), and the ward center coordinates as (x 病房坐标 , y 病房坐标 ), then the Euclidean distance between the ward and the pollution source is calculated as follows: If the distance d 病房-污染源 is less than or equal to the pollution diffusion radius R 污染扩散 , then the ward is within the pollution influence range. Assume that the pollution diffusion radius of a certain pollution source is R 污染扩散 = 5.0 meters, the center coordinates of a certain ward are (10, 15), and the pollution source coordinates are (12, 18), then the Euclidean distance from the ward to the pollution source is calculated as follows: meters. Since 3.61 < 5.0 meters, the ward is within the pollution influence range, and finally the dynamic risk ward area boundary is generated.

[0079] Please refer to Figure 2 and Figure 5 , the pollution event trend analysis module includes:

[0080] The pollution event data extraction sub-module, based on the dynamic risk ward area boundary, obtains the hospital environmental pollution event data, extracts the bacterial test results, air quality monitoring data, medical waste illegal disposal records, and the number of pollution events occurring within a specified time, screens the wards where the number of pollution events exceeds the pollution alarm threshold, combines the ward contact density, adjusts the pollution event statistical range, and generates the pollution event distribution data;

[0081] The pollution event data extraction sub-module obtains the environmental pollution event data within the hospital based on the dynamic risk ward boundary. First, it is necessary to access the hospital environmental monitoring software (such as LabWare LIMS, AirVisual, WasteLog), which integrates functions such as a bacteria detection database, an air quality monitoring system, and a medical waste management system. Users can extract the required data by querying the air quality reports of the wards, the bacterial culture test records, and the medical waste management logs. When extracting the bacterial test results, first retrieve the microbial laboratory database, extract the ward air bacterial test data for a specified past time period, filter out the data points with excessive bacterial content, and count the number of excessive events. The bacterial content at each test point is recorded in colony-forming units (CFU / m3). When extracting the air quality monitoring data, call the historical records of the air quality monitoring equipment, analyze the excessive situations of pollutant concentrations such as PM2.5, PM10, and carbon dioxide within a specified past time period, and count the number of excessive times. The medical waste violation disposal records are obtained from the medical waste management system, which records the storage location, storage time, waste type, and violation situations of medical waste, such as violations such as exceeding the storage time, not storing in the specified area, and not classifying and storing hazardous waste. After extracting the bacterial excessive events, air quality excessive events, and medical waste illegal storage events, calculate the total number of pollution events. The formula for calculating the number of pollution events is as follows: N PEV = N BEX + N AQX + N MWV . N PEV represents the total number of pollution events, which is obtained by counting the sum of the numbers of bacterial culture excessive events, air quality excessive events, and medical waste violation events. N BEX represents the number of events with excessive bacterial culture results, which is obtained from the laboratory microbial culture test data. N AQX represents the number of events with excessive air quality monitoring data, which is obtained by analyzing the data collected by the air quality monitoring system. N MWV represents the number of events with illegal storage of medical waste, which is obtained by counting the violation records of the medical waste management system. Suppose the pollution event data monitored by a certain hospital are as follows: The number of events with excessive bacterial culture results N BEX = 7 times / week; The number of events with excessive air quality monitoring data N AQX = 5 times / week; The number of events with illegal storage of medical waste N MWV = 4 times / week; Substitute into the formula to calculate: N PEV = 7 + 5 + 4 = 16 times / week. Suppose the pollution alarm threshold is set as N ALERT = 10 times / week, then since N PEV= 16 > 10, this ward area is classified as an area with excessive pollution. When adjusting the statistical scope of pollution events in combination with the contact density in the ward, the ward contact density data is called. If the ward contact density D CD = 0.22 persons per square meter, and the infection risk threshold D CD_THRESH = 0.15 persons per square meter, then since 0.22 > 0.15, the pollution statistical scope is expanded, and adjacent wards are included in the statistics of pollution events, and finally the pollution event distribution data is generated.

[0082] The pollution event growth rate calculation sub-module, based on the pollution event distribution data, obtains the pollution event data for adjacent time periods, calculates the pollution event growth rate, screens out the ward areas where the pollution event growth rate exceeds the growth threshold, and combines with the dynamic risk ward area boundary to adjust the list of abnormal pollution event ward areas to generate pollution event growth trend information;

[0083] The pollution event growth rate calculation sub-module, based on the pollution event distribution data, obtains the pollution event data for adjacent time periods, extracts the pollution event records for different time periods from environmental monitoring software (such as SPSS, MATLAB, Tableau), and respectively counts the number of pollution events N CUR and N PREV in the current time period and the previous time period. When calculating the pollution event growth rate, the formula is used: G PEV represents the pollution event growth rate, obtained by calculating the change rate of pollution events in adjacent time periods, N CUR represents the total number of pollution events in the current time period, obtained by counting the pollution event data, N PREV represents the total number of pollution events in the previous time period, obtained by counting the pollution event data in the previous time period. Suppose the number of pollution events N PREV = 10 times monitored in a certain ward area in the previous week, and the number of pollution events N CUR = 18 times monitored this week. Substitute into the formula for calculation:

[0084] The pollution trend assessment sub-module, based on the pollution event growth trend information, calls the pollution event distribution data and the ward contact density, calculates the correlation between the pollution event growth rate and the ward contact risk, screens out the ward areas where the pollution event growth rate and the change rate of contact density increase synchronously, adjusts the list of risk pollution ward areas, and establishes the pollution event trend assessment result.

[0085] The pollution trend assessment sub-module, based on the pollution event growth trend information, calls the pollution event distribution data and the ward contact density data, calculates the correlation between the pollution event growth rate and the change rate of the ward contact density, and uses the formula: C PEV_CD_MODRepresents the correlation between the growth rate of pollution events and the change rate of ward contact density, calculated from the growth rate of pollution events and the change rate of ward contact density, G PEV Represents the growth rate of pollution events, calculated from the number of pollution events Represents the average value of the growth rate of pollution events, calculated from historical data, R CD Represents the change rate of ward contact density, calculated from the change rate of ward contact density at different time periods Represents the average value of the change rate of ward contact density, calculated from historical data, E SRC Represents the pollution source diffusion influence factor, calculated from environmental parameters such as the pollution source diffusion range and pollution settlement rate, T PEV_DEV Represents the pollution event time series deviation parameter, obtained through the analysis of the distribution characteristics of pollution events at different time periods. Suppose the calculated value is C PEV_CD_MOD = 1.756, while the standard range is set as C PEV_CD_MOD_THRESH = 1.5. Since 1.756 > 1.5, it indicates a relatively high correlation between the growth rate of pollution events and the change rate of ward contact density. The pollution risk in this ward area needs to be raised to a higher level. Adjust the list of abnormal ward areas for pollution events, and finally establish the pollution event trend assessment result

[0086] Please refer to Figure 2 and Figure 6 , the cleaning task execution deviation analysis module includes:

[0087] Based on the pollution event trend assessment result, the cleaning task data extraction sub-module obtains the cleaning task execution data of infectious disease departments, wards, and operating rooms, extracts the cleaning task completion time, task delay duration, number of unexecuted tasks, and cleaning area coverage rate, calculates the proportion of cleaning tasks completed within a specified time, screens the wards with abnormal cleaning task execution, and combines with the dynamic risk ward area boundary to establish the cleaning task execution status data

[0088] Based on the pollution event trend assessment result, the cleaning task data extraction sub-module extracts the cleaning task execution data of infectious disease departments, wards, and operating rooms. First, it extracts the cleaning task records from the hospital cleaning task management system and verifies the task completion situation in combination with real-time monitoring data. The cleaning task completion time calculates the actual execution duration of each cleaning task through the cleaning task log. The task delay duration is calculated as the difference between the actual start time and the planned start time of the task. The number of unexecuted tasks is obtained by counting the difference between the total number of planned tasks and the total number of executed tasks. The cleaning area coverage rate is calculated by detecting the change in the microbial concentration in the cleaned area through sensors and comparing it with the cleaned area that should be covered. When calculating the proportion of cleaning tasks completed within a specified time, the number of completed cleaning tasks N COMP and the number of planned cleaning tasks N PLAN, the calculation formula is as follows: P CLN represents the completion ratio of the cleaning task, which is obtained by calculating the ratio of the number of completed cleaning tasks to the number of planned cleaning tasks. N COMP represents the number of completed cleaning tasks, which is obtained by counting the cleaning task log. N PLAN represents the number of planned cleaning tasks, which is obtained through the cleaning task scheduling system. P THRESH represents the threshold of the cleaning task completion ratio, which is set based on historical data. If P CLN is lower than this value, then this ward is marked as an area with abnormal cleaning task execution. Suppose a ward plans to execute 50 cleaning tasks in a week and actually completes 40 tasks, then: When screening wards with abnormal cleaning task execution, set the threshold P of the cleaning task completion ratio THRESH , and this threshold is set according to the hospital's historical data. For example, set P THRESH = 90%. If P CLN < 90%, then mark this ward as an area with abnormal cleaning task execution, combine the dynamic risk ward boundary, update the list of wards with abnormal cleaning task execution, and finally establish the cleaning task execution status data.

[0089] Based on the cleaning task execution status data, the cleaning task deviation calculation sub-module calls the cleaning task completion time, task delay duration, and number of unexecuted tasks, calculates the cleaning task execution deviation value, screens the wards where the cleaning task execution deviation exceeds the task specification threshold, combines the cleaning area coverage rate, adjusts the cleaning task quality evaluation parameters, and generates the cleaning task deviation information;

[0090] Based on the cleaning task execution status data, the cleaning task deviation calculation sub-module extracts the cleaning task completion time, task delay duration, and number of unexecuted tasks, and calculates the cleaning task execution deviation value. The cleaning task execution deviation value uses the standard deviation S of the task completion time TIME , the standardized value S of the task delay duration DELAY and the proportion R of unexecuted tasks MISS for calculation. The calculation formula is as follows: D CLN = S TIME + S DELAY + R MISS , where S TIME The calculation method is: The standardized value of the task delay duration is calculated using the maximum-minimum normalization method: Suppose the cleaning task completion times of a ward are: 10min, 12min, 15min, 18min, 20min, calculate the mean value: Calculate the standard deviation: Assume the mean value M of the task delay duration DELAY = 8 min, the maximum delay duration M DELAY_MAX = 15 min, the minimum delay duration M DELAY_MIN = 2 min, then: Assume the proportion R of unexecuted tasks MISS = 10%, substitute into the formula: D CLN = 3.22 + 0.46 + 10 = 13.68, D CLN represents the cleaning task execution deviation value, which is calculated from the standard deviation of the cleaning task completion time, the standardized value of the task delay duration, and the proportion of unexecuted tasks. S TIME represents the standard deviation of the cleaning task completion time, which is obtained by calculating the data fluctuation of the cleaning task completion time. S DELAY represents the standardized value of the task delay duration, which is calculated by maximum-minimum normalization. T COMP represents the completion time of a single cleaning task, which is obtained from the cleaning task execution record represents the mean value of the cleaning task completion time, which is calculated from all cleaning task completion times. M DELAY represents the mean value of the task delay duration, which is calculated by statistically analyzing all task delay times. M DELAY_MAX represents the maximum value of the task delay duration. M DELAY_MIN represents the minimum value of the task delay duration. R MISS represents the proportion of unexecuted tasks, which is calculated by statistically analyzing the number of unexecuted tasks and the total number of planned tasks. D THRESH represents the cleaning task execution deviation threshold, which is set by historical data. When screening the wards where the cleaning task execution deviation exceeds the task specification threshold, set the cleaning task execution deviation threshold D THRESH , if D CLN > D THRESH , then mark this ward as having an excessive cleaning task deviation, adjust the cleaning task quality evaluation parameters in combination with the cleaning area coverage rate, and finally generate the cleaning task deviation information

[0091] The cleaning execution deviation level classification sub-module classifies the cleaning task execution deviation level based on the cleaning task deviation information, according to the pollution event growth rate and the cleaning task deviation, and establishes the analysis result of the deviation degree

[0092] The cleaning execution deviation level classification sub-module classifies based on the cleaning task deviation information, according to the pollution event growth rate G PEV and the cleaning task deviation D CLN for classification. The classification basis for the pollution event growth rate is set as low growth rate G PEV < 30%, medium growth rate 30% ≤ G PEV < 60%, high growth rate G PEV≥60%, the cleaning task execution deviation classification is set to low deviation D CLN <12, medium deviation 12 ≤ D CLN <20, high deviation D CLN ≥20, after cross - matching, establish the cleaning task execution deviation level, and finally establish the deviation degree analysis result.

[0093] Please refer to Figure 2 and Figure 7 , the hospital hygiene assessment module includes:

[0094] The ward cleaning compliance rate calculation sub - module, based on the deviation degree analysis result, obtains the cleaning task execution data of each ward, extracts the cleaning task completion rate, cleaning coverage area, and cleaning task delay duration, calculates the ward cleaning compliance rate, screens the wards with a cleaning compliance rate lower than the cleaning benchmark threshold, and combines the cleaning task deviation level to generate ward cleaning compliance rate data;

[0095] The ward cleaning compliance rate calculation sub - module, based on the deviation degree analysis result, obtains the cleaning task execution data of each ward. First, extract the cleaning task logs of each ward, and obtain the cleaning task completion rate, cleaning coverage area, and cleaning task delay duration. The calculation method of the cleaning task completion rate is the number of completed cleaning tasks C 完成 compared with the planned number of cleaning tasks C 计划 The ratio. Suppose the planned number of cleaning tasks in a ward is 10 and the actual number of completed tasks is 8, then: The cleaning coverage area is the actual cleaned area S measured by the post - cleaning detection equipment 清洁 compared with the total ward area S 总 The calculation. Suppose the total ward area is 50㎡ and the actual cleaned area is 40㎡, then: The cleaning task delay duration D 延误 is obtained by the difference between the planned start cleaning time D 计划 and the actual start cleaning time D 实际 . Suppose the planned cleaning time is 14:00, the actual start time is 14:15, and the maximum allowable delay duration is 60 minutes, then: Calculate the ward cleaning compliance rate: Then compare the calculated ward cleaning compliance rate with the set cleaning benchmark threshold R 阈值 . Suppose the benchmark threshold is 0.6 and the R of this ward 清洁 = 0.48 < 0.6, then this ward does not meet the standard. Combining the cleaning task deviation levels of these wards, generate ward cleaning compliance rate data.

[0096] Based on the data of the ward cleaning compliance rate, the environmental safety index calculation sub-module calls the change in the frequency of pollution incidents, calculates the correlation coefficient between the growth rate of pollution incidents and the ward cleaning compliance rate, and combines the dynamic risk ward boundary to adjust the environmental safety evaluation standard and generate the ward environmental safety index;

[0097] Based on the data of the ward cleaning compliance rate, the environmental safety index calculation sub-module calls the data on the change in the frequency of pollution incidents obtained from the hospital environmental monitoring system and calculates the growth rate G of pollution incidents 污染 The method is to compare the current recorded number of pollution incidents E 当前 with the number of pollution incidents E in the previous period 前一周期 , assuming that there were 20 pollution incidents in the previous period and 30 pollution incidents in the current period, then: Then calculate the correlation coefficient C between the growth rate of pollution incidents and the cleaning compliance rate of each ward 安全 , assuming that the cleaning compliance rate R of a certain ward 清洁 = 48%, and the growth rate of pollution incidents G 污染 = 50%, then: Calculate the ward environmental safety index: I 安全 = C 安全 ×R 清洁 = 0.96 × 48 = 46.08. Finally, combine the dynamic risk ward boundary to adjust the environmental safety evaluation standard and generate the ward environmental safety index.

[0098] Based on the ward environmental safety index, the hospital overall hygiene assessment sub-module calls the cleaning task deviation level, analyzes the change trend of the ward hygiene risk, screens the wards with abnormal risk fluctuations, combines the hospital's overall ward hygiene data, calculates the hospital overall hygiene assessment value, and establishes the hospital ward hygiene assessment result.

[0099] Based on the ward environmental safety index, the hospital overall hygiene assessment sub-module first collects and analyzes the environmental safety index data of each ward, and then combines the cleaning task deviation level data to calculate the change trend T of the ward hygiene risk 风险 , assuming that the ward environmental safety index I in the previous period 安全前一周期 = 50, and the current period I 安全当前 = 40, then: Screen the wards with abnormal risk fluctuations, and set the risk fluctuation threshold T 阈值 , assuming that the threshold is 15%, then |T 风险 | = 20% > 15%, and this ward is marked as a ward with abnormal risk fluctuations. Combine the hospital's overall ward hygiene data to calculate the hospital overall hygiene assessment value H 医院 , assuming that the total number of wards in the hospital is B 病房= 100, and the sum of the safety indices of all wards is 4200, then: The overall hospital hygiene assessment value H 医院 = 42. According to the hospital hygiene assessment standard, different hospitals may adopt different hygiene level classification methods. Usually, it can be classified according to the following intervals (example standard): 80 - 100: Excellent (The overall hospital hygiene condition is extremely good, the cleaning tasks are well executed, and the pollution incidents are extremely low); 60 - 79: Good (The overall hospital hygiene condition is relatively good, the cleaning tasks basically meet the standards, and pollution incidents occur occasionally); 40 - 59: Average (The overall hospital hygiene condition is ordinary, the cleaning tasks of some wards do not meet the standards, and there is a certain pollution risk); 20 - 39: Poor (The hospital hygiene condition is poor, the cleaning tasks of most wards have problems, and there are many pollution incidents); 0 - 19: Extremely poor (The hospital hygiene condition seriously fails to meet the standards, the cleaning tasks are poorly executed, and the pollution risk is extremely high). In this example, 42 corresponds to the "average" hygiene level, indicating that the overall cleaning condition of the hospital is acceptable, but there are cases where the cleaning tasks of some wards do not meet the standards, which may lead to certain hygiene hazards. For example, some wards may affect environmental safety due to delayed cleaning tasks, insufficient coverage area, or frequent pollution incidents. The hospital management needs to take targeted measures, such as optimizing the cleaning process, strengthening disinfection management, or increasing the frequency of cleaning tasks, to prevent further deterioration and finally establish the hospital ward hygiene assessment results.

[0100] It should be understood that the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0101] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following (items)" or its similar expressions refer to any combination of these items, including any combination of single (item) or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0102] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0104] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0105] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0106] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0108] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0109] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A hospital health assessment system based on data stream, characterized in that: The system comprises: The medical waste pollution diffusion identification module obtains medical waste flow data, analyzes the residence time, calculates the pollution diffusion range based on temperature, humidity and airflow direction, screens areas that exceed the contact threshold, and generates abnormal medical waste contact risk analysis results; The risk ward dynamic determination module calculates the contact density based on the abnormal contact risk analysis results of medical waste and the patient trajectory in the ward, screens the risk wards, and generates dynamic risk ward boundaries; The pollution event trend analysis module is based on the dynamic risk ward boundaries, according to bacteria detection, air quality, and violation disposal records, and selects wards with growth rates exceeding the threshold value to generate pollution event trend assessment results; The cleaning task execution deviation analysis module obtains the cleaning task execution data based on the pollution event trend assessment result, calculates the execution deviation value, screens the wards with cleaning frequency lower than the threshold, and obtains the deviation degree analysis result; The hospital hygiene assessment module is based on the deviation degree analysis results, compares the ward cleaning compliance rate, calculates the environmental safety index in combination with the change in the frequency of pollution events, analyzes the hygiene change trend, and obtains the hospital ward hygiene assessment results.

2. The data stream-based hospital health assessment system according to claim 1, characterized in that: The abnormal contact risk analysis results of medical waste include the abnormal contact rate of medical equipment, the number of abnormal contacts of medical staff, and the pollution diffusion coverage area. The dynamic risk ward boundaries include the contaminated ward area, the patient contact density level, and the ward infection risk level. The pollution event trend assessment results include the hospital pollution event incidence rate, the pollution event growth rate, and the spatial distribution range of pollution events. The deviation degree analysis results include the cleaning task completion rate, the cleaning task delay time, and the ward cleaning deviation level. The hospital ward hygiene assessment results include the hospital's overall hygiene index, the ward environmental safety score, and the ward hygiene risk level.

3. The hospital health assessment system based on data stream according to claim 1 is characterized in that: The medical waste pollution diffusion identification module includes: The medical waste flow analysis submodule obtains the medical waste flow data of the hospital's infectious disease department, emergency room, and operating room, extracts the waste generation time, storage location, and processing time, calculates the residence time of medical waste, and screens medical waste with abnormal pollution diffusion conditions based on the waste storage environment temperature, humidity, and airflow direction. It calls the waste type classification parameters, determines the proportion of infectious waste, and generates medical waste pollution characteristics; The pollution diffusion range calculation submodule, based on the pollution characteristics of the medical waste, calls the storage environment temperature, humidity, and airflow direction, calculates the pollution diffusion radius, extracts the pollution diffusion path data, screens the areas covered by medical equipment and personnel activities, analyzes the pollution diffusion impact range, and screens the areas where the pollution duration exceeds the preset storage time limit in combination with the medical waste residence time, and generates the medical waste pollution diffusion range; The abnormal contact risk identification submodule, based on the medical waste contamination diffusion range, calls the medical equipment use frequency, equipment contact time, and personnel operation records, calculates the frequency of medical equipment contact contamination, screens the contaminated contact areas that exceed the equipment use safety threshold, calculates the medical staff's residence time within the contamination diffusion range, determines the abnormal contact situation, screens the medical areas that exceed the contact time threshold or the contact frequency threshold, and generates the medical waste abnormal contact risk analysis results.

4. The hospital health assessment system based on data stream according to claim 1 is characterized in that: The risk ward dynamic determination module includes: The patient activity data analysis submodule obtains the patient activity trajectory data of the inpatient ward and the intensive care unit based on the abnormal contact risk analysis results of the medical waste, extracts the patient's stay time and the number of patient movements per unit time, screens patients whose movement frequency between wards exceeds the preset movement frequency threshold, calls the ward type data, determines the changing trend of the patient density, and generates the patient activity distribution characteristics; The ward contact density calculation submodule, based on the patient activity distribution characteristics, calls the patient's stay time and the number of patients per unit area of ​​the ward, calculates the ward contact density, compares the ward infection risk threshold, screens the wards that exceed the infection risk threshold, and adjusts the ward infection risk level in combination with the abnormal medical waste contact risk analysis results to generate the ward contact risk index; The dynamic risk ward boundary generation submodule calls the medical waste pollution diffusion radius based on the ward contact risk index, screens the wards within the pollution diffusion range, calculates the intersection area between the ward contact risk index and the pollution impact range, adjusts the ward division boundary, screens the wards with abnormal risk level changes, and establishes dynamic risk ward boundaries.

5. The hospital health assessment system based on data stream according to claim 1 is characterized in that: The pollution event trend analysis module includes: The pollution event data extraction submodule obtains the environmental pollution event data in the hospital based on the dynamic risk ward boundary, extracts the bacterial detection results, air quality monitoring data, medical waste illegal disposal records and the number of pollution events within a specified time, selects the wards where the number of pollution events exceeds the pollution alarm threshold, adjusts the pollution event statistical range based on the ward contact density, and generates pollution event distribution data; The pollution event growth rate calculation submodule obtains pollution event data in adjacent time periods based on the pollution event distribution data, calculates the pollution event growth rate, screens wards whose pollution event growth rate exceeds the growth threshold, adjusts the list of abnormal pollution event wards in combination with the dynamic risk ward boundaries, and generates pollution event growth trend information; Based on the pollution event growth trend information, the pollution trend assessment submodule calls the pollution event distribution data and ward contact density, calculates the correlation between the pollution event growth rate and the ward contact risk, screens the wards where the pollution event growth rate and the contact density change rate increase synchronously, adjusts the list of risky pollution wards, and establishes the pollution event trend assessment results.

6. The data stream-based hospital health assessment system according to claim 5, characterized in that: For extracting bacterial test results, air quality monitoring data, medical waste illegal disposal records and the number of pollution incidents within a specified time, the formula is used: N PEV =N BEX +N AQX +N MWV ; Calculate the total number of pollution events N PEV ; Among them, N BEX Represents the number of events where the bacterial culture results exceeded the standard, N AQX Represents the number of events where air quality monitoring data exceeds the standard, N MWV Represents the number of incidents of illegal storage of medical waste.

7. The hospital health assessment system based on data stream according to claim 5, characterized in that: For calculating the pollution event growth rate G PEV , using the formula: Among them, N CUR Represents the total number of pollution events in the current time period, N PREV Represents the total number of pollution events in the previous time period.

8. The data stream-based hospital health assessment system according to claim 5, characterized in that: For calculating the correlation between the growth rate of contamination events and the risk of exposure in wards, C PEV_CD_MOD , using the formula: Among them, G PEV represents the growth rate of pollution events, represents the mean growth rate of pollution events, R CD represents the change rate of contact density in the ward, represents the mean value of the change rate of contact density in the ward, E SRC represents the pollution source diffusion impact factor, T PEV_DEV Represents the pollution event timing deviation parameter.

9. The hospital health assessment system based on data stream according to claim 1, characterized in that: The cleaning task execution deviation analysis module includes: The cleaning task data extraction submodule obtains the cleaning task execution data of the infectious disease department, wards, and operating rooms based on the pollution event trend assessment results, extracts the cleaning task completion time, task delay duration, number of unexecuted tasks, and cleaning area coverage, calculates the cleaning task completion ratio within the specified time, screens wards with abnormal cleaning task execution, and establishes cleaning task execution status data in combination with dynamic risk ward boundaries; The cleaning task deviation calculation submodule, based on the cleaning task execution status data, calls the cleaning task completion time, task delay duration, and number of unexecuted tasks, calculates the cleaning task execution deviation value, screens the wards whose cleaning task execution deviation exceeds the task specification threshold, and adjusts the cleaning task quality evaluation parameters in combination with the cleaning area coverage rate to generate cleaning task deviation information; The cleaning execution deviation level classification submodule classifies the cleaning task execution deviation level based on the cleaning task deviation information according to the pollution event growth rate and the cleaning task deviation, and establishes a deviation degree analysis result.

10. The hospital health assessment system based on data stream according to claim 1, characterized in that: The hospital health assessment module includes: The ward cleaning compliance rate calculation submodule obtains the cleaning task execution data of each ward based on the deviation degree analysis result, extracts the cleaning task completion rate, cleaning coverage area, and cleaning task delay duration, calculates the ward cleaning compliance rate, screens the wards whose cleaning compliance rate is lower than the cleaning benchmark threshold, and generates the ward cleaning compliance rate data in combination with the cleaning task deviation level; The environmental safety index calculation submodule is based on the ward cleaning compliance rate data, calls the pollution event frequency change, calculates the relationship coefficient between the pollution event growth rate and the ward cleaning compliance rate, combines the dynamic risk ward boundary, adjusts the environmental safety evaluation standard, and generates the ward environmental safety index; The hospital overall hygiene assessment submodule is based on the ward environmental safety index, calls the cleaning task deviation level, calculates the ward hygiene risk change trend, screens wards with abnormal risk fluctuations, combines the hospital's overall ward hygiene data, calculates the hospital's overall hygiene assessment value, and establishes the hospital ward hygiene assessment results.

Images