Intelligent hospital epidemic situation prevention and control method and system

Abstract

The invention relates to the technical field of public health, in particular to an intelligent hospital epidemic situation prevention and control method and system, and the method comprises the following steps: analyzing the medical record, medical detection result and interpersonal contact historical information of a patient based on the symptom examination information of the patient, evaluating the health condition and infection risk of a plurality of patients, and generating an infection risk evaluation framework. According to the invention, through analyzing patient symptom examination information and interpersonal contact historical information, evaluating health conditions and infection risks of a plurality of patients and identifying key propagation nodes, the identification capability of an infectious disease propagation path is improved, the accuracy and efficiency of identifying an incubation period infected person are optimized, and real-time epidemic situation data are combined, so that the accuracy and efficiency of identifying the incubation period infected person are improved. The system simulates and predicts the development trend of epidemic situations, optimizes the efficiency and matching degree of hospital resource scheduling, improves the speed and efficiency of epidemic situation response, reduces the outbreak and diffusion of epidemic situations in hospitals, guarantees the safety of medical staff and patients, and improves the responsiveness of hospitals to epidemic situations.

Description

Technical Field

[0001] The present invention relates to the field of public health technology, and in particular to a smart hospital epidemic prevention and control method and system. Background Art

[0002] The field of public health technology aims to achieve multiple goals of disease prevention, life extension, and health promotion through various social organizations and collectives, including disease monitoring, vaccine development, health data analysis, environmental health, health education, and policy making. It controls the spread of infectious diseases, improves sanitary conditions, reduces environmental hazards, and enhances community health awareness. It uses epidemiological surveys, disease monitoring systems, health data analysis, and epidemic response strategies, combined with big data, cloud computing, and artificial intelligence to improve the efficiency of disease prevention and control, conduct health education and behavioral intervention, reduce public health threats, and improve the overall social health.

[0003] Among them, the smart hospital epidemic prevention and control method aims to monitor, prevent and control the spread of infectious diseases through information and communication technology in the hospital environment, including the use of automated systems to monitor the health status of patients and medical staff and the sanitary conditions within the hospital in real time, and predict the development trend of the epidemic through data analysis, respond to health emergencies, optimize the allocation of human resources and materials during the epidemic, reduce the outbreak and spread of the epidemic within the hospital, protect the safety of medical staff and patients, and improve the hospital's response capabilities to public health emergencies.

[0004] Traditional epidemic prevention and control technologies rely on traditional epidemiological surveys and disease monitoring systems, and have deficiencies in data processing and epidemic prediction. In a rapidly changing epidemic environment, the identification of latently infected persons and the prediction of epidemic trends are not accurate enough, resulting in delayed and mismatched epidemic response measures. There is a lack of flexibility and foresight in resource allocation, which means that resources can only be adjusted after the outbreak, increasing the risk of hospital-acquired infections and leading to waste and shortage of resources. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a smart hospital epidemic prevention and control method and system.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solution, a smart hospital epidemic prevention and control method, comprising the following steps:

[0007] S1: Based on the patient symptom examination information, analyze the patient's medical records, medical test results, and interpersonal contact history information, evaluate the health status and infection risk of multiple patients, and generate an infection risk assessment framework;

[0008] S2: Based on the infection risk assessment framework, by analyzing the pathological characteristics and interpersonal contact information of multiple patients, the impact of multiple patients on the infection risk is evaluated, key transmission nodes are identified, and transmission node analysis results are obtained;

[0009] S3: Based on the analysis results of the transmission nodes, combined with the patient's contact history and movement trajectory, predict and identify infected persons in the incubation period to form an incubation period prediction result;

[0010] S4: Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, simulate and predict the development trend of the epidemic to obtain epidemic trend assessment information;

[0011] S5: Based on the epidemic trend assessment information and combined with historical material consumption data, hospital resource demand is predicted in real time, material and manpower allocation is adjusted, and resource demand calculation data is formed;

[0012] S6: Based on the resource demand calculation data, adjust the work schedule of medical staff, optimize human resource allocation and utilization, and generate hospital prevention and control scheduling information.

[0013] As a further scheme of the present invention, the infection risk assessment framework includes information on the stage of symptoms of the infected person, virus infectiousness score information, and patient immunity level information; the transmission node analysis results include key infected person identification results, contact frequency data, and infection probability assessment information; the incubation period prediction results include a list of risk infected persons, incubation period assessment results, and infection development probability information; the epidemic trend assessment information includes an epidemic growth curve, virus mutation analysis results, and epidemic spread speed prediction information; the resource demand calculation data includes medical supplies demand prediction results, human resources demand prediction information, and resource allocation results at key time points; the hospital prevention and control scheduling information includes work schedule optimization records, job personnel allocation information, and emergency response team configuration information.

[0014] As a further solution of the present invention, based on the patient symptom examination information, the patient's medical records, medical test results, and interpersonal contact history information are analyzed to evaluate the health status and infection risk of multiple patients. The steps of generating an infection risk assessment framework are specifically as follows:

[0015] S101: Based on the patient's symptom examination information, collect and organize the patient's medical records, medical test results, and interpersonal contact history information to generate a patient medical record data set;

[0016] S102: Based on the patient medical record data set, analyzing the health conditions and interpersonal contact history of multiple patients, recording the social activity frequency and number of contacts of the target patient, calculating the infection risk index, and generating contact history analysis results;

[0017] S103: Based on the contact history analysis results, the infection risks of multiple patients are evaluated, and the influence of health status and social behavior are considered to generate an infection risk assessment framework.

[0018] As a further solution of the present invention, based on the infection risk assessment framework, by analyzing the pathological characteristics and interpersonal contact information of multiple patients, evaluating the degree of influence of multiple patients on the infection risk, identifying key transmission nodes, and obtaining the transmission node analysis results are specifically as follows:

[0019] S201: Based on the infection risk assessment framework, analyze and record the pathological characteristics and interpersonal contact information of the patients, evaluate and identify the risk influencing factors of multiple patients, and generate infection impact analysis data;

[0020] S202: Based on the infection impact analysis data, calculate the virus transmission risk data of multiple patients, identify key patients who affect the spread of the epidemic, and obtain key node calculation results;

[0021] S203: Based on the calculation results of the key nodes, the propagation capabilities of multiple virus propagation nodes are analyzed, the nodes that affect the spread of the epidemic are identified, and the propagation node analysis results are obtained.

[0022] As a further solution of the present invention, based on the propagation node analysis results, combined with the patient's contact history and movement trajectory, the infected person in the incubation period is predicted and identified, and the steps of forming the incubation period prediction result are specifically as follows:

[0023] S301: Based on the propagation node analysis results, by analyzing key propagation patients, recording the contact history and movement trajectory of the target patient, and the contact history data, a contact analysis data set is generated;

[0024] S302: Based on the contact analysis data set, using a K-nearest neighbor algorithm, analyzing the contact times and durations of multiple contacts, calculating the infection risk scores of the multiple contacts, matching risk levels for the multiple contacts, and generating infection risk assessment data;

[0025] S303: Based on the infection risk assessment data and in combination with real-time epidemic data, identify infected contacts, analyze and record the incubation period characteristics of multiple risk contacts, and generate incubation period prediction results.

[0026] As a further solution of the present invention, based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, the steps of simulating and predicting the epidemic development trend and obtaining epidemic trend assessment information are specifically as follows:

[0030] S401: Based on the incubation period prediction result, combined with real-time epidemic data, including confirmed cases and recovered cases, analyze the time series characteristics in the epidemic data and build an epidemic data model to generate an epidemic data analysis record;

[0031] S402: Based on the epidemic data analysis record, analyzing and identifying epidemic change indicators, including the ratio of new cases to recovered cases, performing trend analysis on the infection data, and generating change trend analysis data;

[0032] S403: Utilize the change trend analysis data to simulate and predict the epidemic development path, combine the historical epidemic change data, calculate the infection curve changes, and generate epidemic trend assessment information.

[0033] As a further solution of the present invention, based on the epidemic trend assessment information, combined with historical material consumption data, real-time prediction of hospital resource demand, adjustment of material and manpower allocation, and formation of resource demand calculation data are specifically performed as follows:

[0034] S501: Analyze the historical epidemic material consumption according to the epidemic trend assessment information, and evaluate and calculate the real-time resource demand changes in combination with the real-time epidemic information to obtain a material consumption comparison result;

[0035] S502: Based on the material consumption comparison result, combined with the real-time available hospital beds and human resources, predict and calculate material and human resource requirements to obtain expected demand analysis information;

[0036] S503: According to the expected demand analysis information, the hospital's material allocation and human resource allocation are adjusted to optimize the consistency between resource allocation and actual demand, and form resource demand calculation data.

[0037] As a further solution of the present invention, based on the resource demand calculation data, the steps of adjusting the work schedule of medical staff, optimizing human resource allocation and utilization, and generating hospital prevention and control scheduling information are specifically as follows:

[0038] S601: Based on the resource demand calculation data, the work intensity and work schedule of multiple medical staff are evaluated in real time to obtain a work time evaluation result;

[0039] S602: Based on the working time evaluation result, according to the personnel type and work intensity, taking into account the alternating shifts and emergency response needs, the medical staff's shift schedule is adjusted to obtain a shift schedule calculation result;

[0040] S603: Using the scheduling time calculation result, taking into account the response speed and medical quality, adjusting the human resource allocation in real time, optimizing the human resource allocation and utilization rate, and generating hospital prevention and control scheduling information.

[0041] A smart hospital epidemic prevention and control system, the smart hospital epidemic prevention and control system is used to execute the above-mentioned smart hospital epidemic prevention and control method, the system includes:

[0042] The patient information assessment module analyzes the patient's symptom examination information, medical records, medical test results, and interpersonal contact history information based on the patient's symptom examination information, assesses health status and infection risk, calculates health and infection indexes, and generates risk patient profile information;

[0043] The impact path analysis module analyzes the patient's pathological characteristics and interpersonal contact information based on the risk patient's profile information, evaluates the patient's impact on the infection risk, identifies key transmission nodes, and generates node impact assessment information;

[0044] The infection probability calculation module analyzes the patient's contact history and movement trajectory based on the node impact assessment information, evaluates the infection probability of multiple contacts, and generates an infection risk analysis record;

[0045] The epidemic spread assessment module simulates and analyzes the epidemic spread and development trend based on the infection risk analysis records and real-time epidemic data, and generates development trend forecast information;

[0046] Based on the development trend forecast information, the epidemic prevention resource scheduling module combines historical material consumption data and real-time resource status to adjust the hospital's material and human resource allocation, optimize the medical staff's work schedule, and generate hospital prevention and control scheduling information.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by analyzing the patient's symptom examination information and interpersonal contact history information, the health status and infection risk of multiple patients are evaluated, key transmission nodes are identified, the ability to identify the transmission path of infectious diseases is improved, and the accuracy and efficiency of identifying latent infected persons are optimized, which helps hospitals to make prevention and control preparations in advance. In combination with real-time epidemic data, the development trend of the epidemic is simulated and predicted, the accuracy of the prediction is improved, the efficiency and matching degree of hospital resource scheduling are optimized, the speed and efficiency of epidemic response are improved, the outbreak and spread of the epidemic within the hospital are reduced, the safety of medical staff and patients is guaranteed, and the hospital's response ability to the epidemic is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0056] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0059] Embodiment 1

[0060] See also Figure 1 The present invention provides a technical solution, a smart hospital epidemic prevention and control method, comprising the following steps:

[0061] S1: Based on the patient symptom examination information, analyze the patient's medical records, medical test results, and interpersonal contact history information, evaluate the health status and infection risk of multiple patients, and generate an infection risk assessment framework;

[0062] S2: Based on the infection risk assessment framework, by analyzing the pathological characteristics and interpersonal contact information of multiple patients, the impact of multiple patients on the infection risk is evaluated, key transmission nodes are identified, and the transmission node analysis results are obtained;

[0063] S3: Based on the results of the propagation node analysis, combined with the patient's contact history and movement trajectory, predict and identify infected people in the incubation period to form an incubation period prediction result;

[0064] S4: Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, simulate and predict the development trend of the epidemic to obtain epidemic trend assessment information;

[0065] S5: Based on the epidemic trend assessment information and combined with historical material consumption data, hospital resource needs are predicted in real time, and material and manpower allocation are adjusted to form resource demand calculation data;

[0066] S6: Based on resource demand calculation data, adjust the work schedule of medical staff, optimize human resource allocation and utilization, and generate hospital prevention and control scheduling information.

[0067] The infection risk assessment framework includes information on the stage of symptoms of the infected person, virus infectivity score information, and patient immunity level information. The results of the transmission node analysis include key infected person identification results, contact frequency data, and infection probability assessment information. The incubation period prediction results include a list of risk infected persons, incubation period assessment results, and infection development probability information. The epidemic trend assessment information includes the epidemic growth curve, virus mutation analysis results, and epidemic spread speed prediction information. The resource demand calculation data includes the forecast results of medical supplies demand, human resources demand forecast information, and resource allocation results at key time points. Hospital prevention and control dispatch information includes work schedule optimization records, job personnel allocation information, and emergency response team configuration information.

[0068] See also Figure 2 Based on the patient symptom examination information, the patient's medical records, medical test results, and interpersonal contact history information are analyzed to evaluate the health status and infection risk of multiple patients. The specific steps to generate the infection risk assessment framework are as follows:

[0069] S101: Based on the patient's symptom examination information, collect and organize the patient's medical records, medical test results, and interpersonal contact history information, and generate the patient's medical record data set in the following specific steps;

[0070] In sub-step S101, based on the patient's symptom examination information, the patient's medical records, medical test results, and interpersonal contact history information are collected and organized. The patient's medical records for each visit are collected in real time, encoded and stored. The medical test results are automatically updated through the medical information system. The interpersonal contact history is organized through the access records. The medical record integration algorithm is used to associate and synchronize the data. The data is pre-processed, including removing irrelevant items and erroneous items. The correlation algorithm is used to determine the correlation between the data. The formula is: Where f(D) represents the integration function of the medical record dataset, d i represents the i-th data item, w i is the weight coefficient, which indicates the importance of the target data item in the integration and generates the patient medical record dataset.

[0071] S102: Based on the patient medical record data set, the health status and interpersonal contact history of multiple patients are analyzed, the social activity frequency and number of contacts of the target patient are recorded, the infection risk index is calculated, and the specific steps of generating the contact history analysis result are as follows;

[0072] In sub-step S102, based on the patient medical record data set, the health status and interpersonal contact history of multiple patients are analyzed, the social activity frequency and number of contacts of the target patient are recorded, and the infection risk index is calculated. The social activity frequency of each patient is determined by the frequency analysis algorithm, and the contact network construction algorithm is used to establish the contact network of each patient. The infection risk index is calculated. The formula is: ,

[0073] Among them, R is the infection risk index, f soc represents the frequency of social activities, n con is the number of contacts, β is the transmission parameter, and c is the adjustment coefficient, which determines the relative importance of social frequency and the number of contacts in risk assessment and generates the results of contact history analysis.

[0074] S103: Based on the results of contact history analysis, the infection risk of multiple patients is evaluated, and the influence of health status and social behavior are considered. The specific steps of generating an infection risk assessment framework are as follows;

[0075] In sub-step S103, based on the results of the contact history analysis, the infection risk of multiple patients is evaluated, the influence of health status and social behavior is considered, a risk matrix is ​​generated based on health data and social data, and the risk assessment formula is applied for analysis. The probability of infection is predicted by considering the health status and social behavior of individuals. The formula is P = γ·(h·w h +s·w s ), where P represents the risk of infection, h is the health status indicator, s is the social behavior indicator, and w h and w s are the weight coefficients of health and sociality respectively, and γ is the adjustment coefficient to generate the infection risk assessment framework.

[0076] See also Figure 3 Based on the infection risk assessment framework, by analyzing the pathological characteristics and interpersonal contact information of multiple patients, the impact of multiple patients on the infection risk is evaluated, and key transmission nodes are identified. The specific steps for obtaining the transmission node analysis results are as follows:

[0077] S201: Based on the infection risk assessment framework, analyze and record the patient's pathological characteristics and interpersonal contact information, evaluate and identify the risk factors of multiple patients, and generate infection impact analysis data in the following specific steps;

[0078] In sub-step S201, based on the infection risk assessment framework, the patient's pathological characteristics and interpersonal contact information are analyzed and recorded, and the risk influencing factors of multiple patients are evaluated and identified. The pathological characteristic analysis module is used to record the clinical pathological data of each patient, integrate the patient's social network data, identify the frequency and intensity of multiple contact levels, and calculate the risk score through the risk factor assessment algorithm. The formula is F = α·(p·w p +c·w c ), where F represents the risk score, p is the pathological feature score, c is the interpersonal contact intensity, and w p and w c are the weight coefficients for pathology and contact, respectively, and α is the adjustment factor for risk assessment to generate infection impact analysis data.

[0079] S202: Based on the infection impact analysis data, the virus transmission risk data of multiple patients are calculated, key patients affecting the spread of the epidemic are identified, and the specific steps for obtaining the calculation results of key nodes are as follows;

[0080] In sub-step S202, based on the infection impact analysis data, the virus transmission risk data of multiple patients are calculated to identify key patients who affect the spread of the epidemic. According to the pathological characteristics and social network information in the infection impact analysis data, the virus transmission model is applied to quantify the transmission risk of each patient. The key patient identification algorithm is used to identify the key nodes of the epidemic by comparing and sorting the transmission risk values. The formula is: Among them, R k represents the risk value of the key node, v i is the viral load of the ith patient, r i is the contact network risk value of the i-th patient, δ is the adjustment factor of the transmission risk, and the calculation results of the key nodes are obtained.

[0081] S203: Based on the calculation results of key nodes, the propagation capabilities of multiple virus propagation nodes are analyzed to identify the nodes that affect the spread of the epidemic. The specific steps of obtaining the propagation node analysis results are as follows;

[0082] In sub-step S203, based on the calculation results of key nodes, the propagation capabilities of multiple virus transmission nodes are analyzed, the nodes that affect the spread of the epidemic are identified, and the node propagation capability analysis module is used to evaluate the propagation capability of each key node, including the contact frequency and the sensitivity of the contact population. The propagation model optimization algorithm is applied to analyze and optimize the propagation capability data, and the spread path of the epidemic is predicted and controlled. The formula is: Among them, S represents the node's propagation ability score, f j is the contact frequency of the jth node, s j is the sensitivity score of the contact population, θ is the optimization factor, and the propagation node analysis results are obtained.

[0083] See also Figure 4 Based on the results of the propagation node analysis, combined with the patient's contact history and movement trajectory, the infected persons in the incubation period are predicted and identified. The specific steps for forming the incubation period prediction results are as follows:

[0084] S301: Based on the propagation node analysis results, by analyzing key propagation patients, recording the contact history and movement trajectory of the target patient, and the contact history data, the specific steps of generating a contact analysis data set are as follows;

[0085] In sub-step S301, based on the results of the propagation node analysis, by analyzing the key propagation patients, the contact history and movement trajectory of the target patients are recorded, and the geographic location data of each key propagation patient is collected by using the movement trajectory recording module. The time, duration and contact information of each contact event are recorded through the location tracking device and mobile phone application data, and the contact relationship is analyzed to form a structured contact data set. The formula is Among them, C i represents the contact analysis score of the ith patient, h k is the historical intensity of the kth contact event, λ k It is the time weighting coefficient, which reflects the distance of contact time and generates the contact analysis data set.

[0086] S302: Based on the contact analysis data set, the K-nearest neighbor algorithm is used to analyze the contact times and durations of multiple contacts, calculate the infection risk scores of multiple contacts, match the risk levels of multiple contacts, and generate infection risk assessment data. The specific steps are as follows;

[0087] In sub-step S302, based on the contact analysis data set, the number of contacts and duration of each contact recorded in the data set are counted, and by constructing a contact behavior feature vector, including contact frequency and total contact duration, the K-nearest neighbor algorithm is used to cluster the behavior patterns of similar contacts. According to the contact behavior and clustering results of each contact, the infection risk score is calculated, and an evaluation is performed based on the similarity between the number and duration of contacts and infection cases. The calculated risk score is mapped to multiple risk levels, and the risk level is matched for each contact, the epidemic transmission chain is identified, and the infection risk assessment data is generated.

[0088] S303: Based on the infection risk assessment data, combined with the real-time epidemic data, identifying the infected contacts, analyzing and recording the incubation period characteristics of multiple risk contacts, and generating the incubation period prediction results are as follows;

[0094] In sub-step S303, based on the infection risk assessment data, combined with real-time epidemic data, the infected contacts are identified, the incubation period characteristics of multiple risk contacts are analyzed and recorded, the real-time epidemic data and the health status data of the contacts are collected, the incubation period prediction algorithm is applied, the data trend and time series are analyzed, and the range of the incubation period is calculated. The incubation period prediction formula is: Among them, L p represents the incubation period prediction result, t is the current time, t0 is the contact time, τ is the time decay constant, and η is the normalization constant, which is used to adjust the prediction accuracy and generate the incubation period prediction result.

[0095] See also Figure 5 Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, the steps to simulate and predict the epidemic development trend and obtain epidemic trend assessment information are as follows:

[0096] S401: Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, the time series characteristics in the epidemic data are analyzed and an epidemic data model is constructed. The specific steps of generating an epidemic data analysis record are as follows;

[0097] In sub-step S401, based on the incubation period prediction results and combined with real-time epidemic data, including confirmed cases and recovered cases, target data are collected and integrated, and time series analysis is performed on the data to identify key time nodes and changing trends in the development of the epidemic, extract the cyclical patterns of epidemic growth and slowdown, and build an epidemic data model to analyze historical data and real-time data in combination with the incubation period data to improve the accuracy of the prediction, help medical institutions and public health officials identify epidemic dynamics, and generate epidemic data analysis records.

[0098] S402: Based on the epidemic data analysis records, analyze and identify epidemic change indicators, including the ratio of new and recovered cases, and perform trend analysis on the infection data. The specific steps of generating change trend analysis data are as follows;

[0099] In sub-step S402, based on the epidemic data analysis records, analyze and identify epidemic change indicators, including the ratio of new and recovered cases, perform trend analysis on infection data, calculate the daily ratio of new and recovered cases, use target data to evaluate the development speed and control effect of the epidemic, use linear regression analysis method to perform trend analysis on the target ratio, predict the development of the epidemic, and generate change trend analysis data.

[0100] S403: The specific steps of using the change trend analysis data to simulate and predict the epidemic development path, combining the historical epidemic change data, calculating the infection curve change, and generating the epidemic trend assessment information are as follows;

[0101] In sub-step S403, the trend analysis data is used to simulate and predict the development path of the epidemic. The infection curve changes are calculated by combining the historical epidemic change data. The epidemic simulation module is used to build an infection curve model based on historical and current trend data to predict the development of the epidemic. The exponential smoothing method is used to predict the infection curve. Control the impact of historical data on predictions and generate epidemic trend assessment information.

[0102] See also Figure 6 Based on the epidemic trend assessment information and combined with historical material consumption data, the hospital resource demand is predicted in real time, and the material and manpower allocation is adjusted to form the resource demand calculation data. The specific steps are as follows:

[0103] S501: Analyze the historical epidemic material consumption according to the epidemic trend assessment information, and evaluate and calculate the real-time resource demand changes in combination with the real-time epidemic information to obtain the material consumption comparison results in the following specific steps;

[0104] In sub-step S501, based on the epidemic trend assessment information, the historical epidemic material consumption is analyzed, combined with the real-time epidemic information, the real-time resource demand changes are evaluated and calculated, the historical material consumption data and the current epidemic data are collected, and the trend analysis method is used to evaluate the changes in resource demand by comparing the consumption of the same period in history with the current real-time data. The resource demand forecasting model is described by the following formula: , where Q t represents the resource demand at time point t, D t and D t-1 They represent the epidemic data at time points t and t-1 respectively, and ρ is the adjustment coefficient, which reflects the impact of epidemic changes on resource demand, and the comparison results of material consumption are obtained.

[0105] S502: Based on the comparison result of material consumption, combined with the real-time available beds and human resources of the hospital, the specific steps of predicting and calculating the material and human resources demand to obtain the expected demand analysis information are as follows;

[0106] In sub-step S502, based on the material consumption comparison results, combined with the hospital's real-time available beds and human resources, the material and manpower requirements are predicted and calculated. The resource matching module is used to calculate the material and manpower requirements based on the material consumption comparison results and the hospital's real-time resource data, including the availability of beds and medical staff. The expected demand model uses the formula Among them, N t represents the expected total resource demand, Q t is the predicted material demand, B t and H t are the available numbers of hospital beds and medical staff respectively, σ and μ are the resource allocation coefficients, and the expected demand analysis information is obtained.

[0107] S503: According to the expected demand analysis information, the specific steps of adjusting the hospital's material allocation and human resource allocation, optimizing the consistency between resource allocation and actual demand, and forming resource demand calculation data are as follows;

[0108] In sub-step S503, according to the expected demand analysis information, the hospital's material allocation and human resource allocation are adjusted to optimize the consistency between resource allocation and actual demand. According to the expected demand results, a material and human resource reallocation plan is formulated. Through dynamic adjustment strategies, the resource allocation is ensured to be consistent with the actual demand and the resource utilization efficiency is improved. The resource adjustment model is A t =δ·N t +(1-δ)·A t-1 , where A t represents the adjusted resource allocation, N t is the newly calculated resource demand, δ is the adjustment response coefficient, A t-1 It forms resource demand calculation data for resource allocation in the previous cycle.

[0109] See also Figure 7 , based on the resource demand calculation data, adjust the work schedule of medical staff, optimize the allocation and utilization of human resources, and generate hospital prevention and control scheduling information. The specific steps are:

[0110] S601: Based on the resource demand calculation data, the specific steps of evaluating the work intensity and work schedule of multiple medical staff in real time and obtaining the work time evaluation result are as follows;

[0111] In sub-step S601, based on the resource demand calculation data, the work intensity and work schedule of multiple medical staff are evaluated in real time. The work intensity evaluation module is used to collect the current work records and resource demand data of medical staff. The workload of each medical staff is calculated through the workload analysis algorithm, and the work intensity is predicted. The work time evaluation model adopts the formula Among them, W t represents the total work intensity at time point t, t i is the working hours of the i-th medical staff, l i is the corresponding workload coefficient, κ is the work efficiency adjustment coefficient, and the working time evaluation result is obtained.

[0112] S602: Based on the working time evaluation result, according to the personnel type and work intensity, taking into account the alternating shifts and emergency response needs, the medical staff's shift schedule is adjusted, and the specific steps for obtaining the shift schedule calculation result are as follows;

[0113] In sub-step S602, based on the work time evaluation results, according to the personnel type and work intensity, taking into account the alternating shifts and emergency response needs, the medical staff's shift schedule is adjusted. The shift optimization module is used to build a shift system according to the work intensity and professional type of each medical staff member. The shift time calculation model uses the formula Among them, S t represents the optimal value of the shift schedule, f j is the job type factor of the jth medical staff, x j Assign variables to working time, θ is the scheduling efficiency coefficient, and the calculation results of the shift schedule are obtained.

[0114] S603: Using the scheduling time calculation results, considering the response speed and medical quality, adjusting the human resource allocation in real time, optimizing the human resource allocation and utilization rate, and generating the hospital prevention and control scheduling information. The specific steps are:

[0115] In sub-step S603, the scheduling time calculation results are used to consider the response speed and medical quality, adjust the human resource allocation in real time, optimize the human resource allocation and utilization rate, and dynamically adjust the human resource allocation to match the changing workload through the human resource optimization module, combining the scheduling time calculation results and actual medical needs. The human resource adjustment model adopts the formula Among them, H t represents the adjusted human resource allocation, g k is the work intensity score of the kth medical staff, v k is the change in work demand, ξ is the resource adjustment response coefficient, H t-1 Generate hospital prevention and control scheduling information for the human resource allocation of the previous calculation cycle.

[0116] See also Figure 8 A smart hospital epidemic prevention and control system is provided, and the smart hospital epidemic prevention and control system is used to execute the above-mentioned smart hospital epidemic prevention and control method, and the system includes:

[0117] The patient information assessment module analyzes the patient's symptom examination information, medical records, medical test results, and interpersonal contact history information based on the patient's symptom examination information, assesses health status and infection risk, calculates health and infection indexes, and generates risk patient profile information;

[0118] The impact path analysis module analyzes the patient's pathological characteristics and interpersonal contact information based on the risk patient's archival information, evaluates the patient's impact on the infection risk, identifies key transmission nodes, and generates node impact assessment information;

[0119] The infection probability calculation module analyzes the patient's contact history and movement trajectory based on the node impact assessment information, evaluates the infection probability of multiple contacts, and generates infection risk analysis records;

[0120] The epidemic spread assessment module simulates and analyzes the epidemic spread and development trends based on infection risk analysis records and real-time epidemic data, and generates development trend forecast information;

[0121] The epidemic prevention resource scheduling module adjusts the hospital's material and human resource allocation, optimizes the medical staff's work schedule, and generates hospital prevention and control scheduling information based on development trend forecast information, combined with historical material consumption data and real-time resource status.

[0122] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A smart hospital epidemic prevention and control method, characterized in that: The following steps are involved: Based on the patient symptom examination information, analyze the patient's medical records, medical test results, and interpersonal contact history information, evaluate the health status and infection risk of multiple patients, and generate an infection risk assessment framework; Based on the infection risk assessment framework, by analyzing the pathological characteristics and interpersonal contact information of multiple patients, the impact of multiple patients on the infection risk is assessed, key transmission nodes are identified, and transmission node analysis results are obtained; Based on the transmission node analysis results, combined with the patient's contact history and movement trajectory, predict and identify infected persons in the incubation period to form an incubation period prediction result; Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, the epidemic development trend is simulated and predicted to obtain epidemic trend assessment information; Based on the epidemic trend assessment information and combined with historical material consumption data, hospital resource needs are predicted in real time, material and manpower allocation is adjusted, and resource demand calculation data is formed; Based on the resource demand calculation data, the work schedule of medical staff is adjusted, human resource allocation and utilization are optimized, and hospital prevention and control scheduling information is generated.

2. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: The infection risk assessment framework includes information on the stage of symptoms of the infected person, virus infectiousness score information, and patient immunity level information. The transmission node analysis results include key infected person identification results, contact frequency data, and infection probability assessment information. The incubation period prediction results include a list of risk infected persons, incubation period assessment results, and infection development probability information. The epidemic trend assessment information includes the epidemic growth curve, virus mutation analysis results, and epidemic spread speed prediction information. The resource demand calculation data includes medical supplies demand prediction results, human resources demand prediction information, and resource allocation results at key time points. The hospital prevention and control scheduling information includes work schedule optimization records, job personnel allocation information, and emergency response team configuration information.

3. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: Based on the patient symptom examination information, the patient's medical records, medical test results, and interpersonal contact history information are analyzed to evaluate the health status and infection risk of multiple patients. The specific steps to generate the infection risk assessment framework are as follows: Based on the patient's symptom examination information, collect and organize the patient's medical records, medical test results, and interpersonal contact history information to generate a patient medical record data set; Based on the patient medical record data set, the health status and interpersonal contact history of multiple patients are analyzed, the social activity frequency and number of contacts of the target patient are recorded, the infection risk index is calculated, and the contact history analysis results are generated; Based on the contact history analysis results, the infection risks of multiple patients are evaluated, and the influence of health status and social behavior are considered to generate an infection risk assessment framework.

4. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: Based on the infection risk assessment framework, by analyzing the pathological characteristics and interpersonal contact information of multiple patients, assessing the impact of multiple patients on the infection risk, identifying key transmission nodes, and obtaining the transmission node analysis results are specifically as follows: Based on the infection risk assessment framework, analyzing and recording the patient's pathological characteristics and interpersonal contact information, evaluating and identifying risk influencing factors of multiple patients, and generating infection impact analysis data; Based on the infection impact analysis data, the virus transmission risk data of multiple patients are calculated, key patients affecting the spread of the epidemic are identified, and key node calculation results are obtained; Based on the calculation results of the key nodes, the propagation capabilities of multiple virus propagation nodes are analyzed, the nodes that affect the spread of the epidemic are identified, and the propagation node analysis results are obtained.

5. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: Based on the propagation node analysis results, combined with the patient's contact history and movement trajectory, the infected person in the incubation period is predicted and identified, and the steps for forming the incubation period prediction result are as follows: Based on the propagation node analysis results, by analyzing key propagation patients, recording the contact history and movement trajectory of the target patients, and contact history data, a contact analysis data set is generated; Based on the contact analysis data set, a K-nearest neighbor algorithm is used to analyze the contact times and durations of multiple contacts, calculate the infection risk scores of multiple contacts, match risk levels for multiple contacts, and generate infection risk assessment data; Based on the infection risk assessment data, combined with real-time epidemic data, infected contacts are identified, the incubation period characteristics of multiple risk contacts are analyzed and recorded, and incubation period prediction results are generated.

6. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, the steps of simulating and predicting the epidemic development trend and obtaining the epidemic trend assessment information are as follows: Based on the incubation period prediction results, combined with real-time epidemic data, including confirmed cases and recovered cases, analyze the time series characteristics in the epidemic data and build an epidemic data model to generate an epidemic data analysis record; Based on the epidemic data analysis records, analyze and identify epidemic change indicators, including the ratio of new cases to recovered cases, perform trend analysis on infection data, and generate change trend analysis data; The change trend analysis data is used to simulate and predict the development path of the epidemic, and the historical epidemic change data is combined to calculate the changes in the infection curve to generate epidemic trend assessment information.

7. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: Based on the epidemic trend assessment information, combined with historical material consumption data, the hospital resource demand is predicted in real time, and the material and manpower allocation is adjusted to form the resource demand calculation data. The specific steps are as follows: According to the epidemic trend assessment information, the historical epidemic material consumption is analyzed, and combined with the real-time epidemic information, the real-time resource demand changes are evaluated and calculated to obtain the material consumption comparison results; Based on the material consumption comparison results, combined with the real-time available hospital beds and human resources, the material and manpower requirements are predicted and calculated to obtain expected demand analysis information; According to the expected demand analysis information, the hospital's material allocation and manpower allocation are adjusted to optimize the consistency between resource allocation and actual demand, thus forming resource demand calculation data.

8. The smart hospital epidemic prevention and control method according to claim 1, characterized in that: Based on the resource demand calculation data, the steps of adjusting the work schedule of medical staff, optimizing human resource allocation and utilization, and generating hospital prevention and control scheduling information are as follows: Based on the resource demand calculation data, the work intensity and work schedule of multiple medical staff are evaluated in real time to obtain a work time evaluation result; Based on the working time evaluation results, according to the personnel type and work intensity, taking into account the alternating shifts and emergency response needs, the medical staff's shift schedule is adjusted to obtain a shift time calculation result; By utilizing the calculation results of the shift scheduling, taking into account the response speed and medical quality, the allocation of human resources is adjusted in real time, the allocation and utilization of human resources are optimized, and the hospital prevention and control scheduling information is generated.

9. A smart hospital epidemic prevention and control system, characterized in that: According to the smart hospital epidemic prevention and control method according to any one of claims 1 to 8, the system comprises: The patient information assessment module analyzes the patient's symptom examination information, medical records, medical test results, and interpersonal contact history information based on the patient's symptom examination information, assesses health status and infection risk, calculates health and infection indexes, and generates risk patient profile information; The impact path analysis module analyzes the patient's pathological characteristics and interpersonal contact information based on the risk patient's profile information, evaluates the patient's impact on the infection risk, identifies key transmission nodes, and generates node impact assessment information; The infection probability calculation module analyzes the patient's contact history and movement trajectory based on the node impact assessment information, evaluates the infection probability of multiple contacts, and generates an infection risk analysis record; The epidemic spread assessment module simulates and analyzes the epidemic spread and development trend based on the infection risk analysis records and real-time epidemic data, and generates development trend forecast information; Based on the development trend forecast information, the epidemic prevention resource scheduling module combines historical material consumption data and real-time resource status to adjust the hospital's material and human resource allocation, optimize the medical staff's work schedule, and generate hospital prevention and control scheduling information.

Images