Big data-based virus propagation path analysis system and method

Abstract

The invention relates to the technical field of virus propagation path analysis, and discloses a virus propagation path analysis system and method based on big data, and the system comprises a propagation collection module and an intelligent analysis module. According to the system, management data of all municipal areas, management data of virus infected patients and all environmental factors affecting virus propagation are acquired through a propagation acquisition module and classified to form a data set, an intelligent analysis module sets a monitoring period, prevalence indexes are generated for the municipal areas where zero patients appear, and the prevalence indexes are analyzed. According to the method, the transmission range, the harm degree and the comprehensive condition of environment influence of viruses in jurisdictions are visually reflected, the multi-dimensional assessment precision is high, an intelligent analysis module focuses on transmission paths of three dimensions of population flow, material circulation and medical resources, the virus transmission risk degree between adjacent jurisdictions is assessed, risk indexes are generated, and the risk indexes are analyzed. Corresponding virus propagation prevention and control suggestions are output according to different virus types, a scientific prevention and control strategy which is graded according to popularity and applied according to propagation risks is established, and the intelligent prevention and control effect is good.

Description

Technical Field

[0001] This invention relates to the field of virus transmission path analysis technology, specifically to a virus transmission path analysis system and method based on big data. Background Technology

[0002] Viruses are a type of simple, non-cellular organism, consisting only of nucleic acid and a protein coat. Some viruses also have an envelope. They cannot perform life activities independently and must parasitize host cells to replicate and multiply. From common influenza viruses and the novel coronavirus to hepatitis B viruses and HIV, viruses vary in morphology, genome, and transmission methods, but all possess extremely high infectivity and pathogenicity. They not only cause symptoms such as fever and fatigue in individuals, but in severe cases can lead to serious illness or even death. They can also spread rapidly among the population, posing a significant threat to public health and safety. Virus transmission path analysis is a core aspect of epidemic prevention and control. Accurate path analysis can pinpoint key nodes in virus transmission, clarify the complete chain from the source of infection to susceptible populations, provide a scientific basis for cutting off transmission links, and help management personnel allocate medical resources and stockpile prevention and control materials in advance, avoiding medical resource shortages.

[0003] Currently, traditional virus transmission path analysis systems are unable to conduct differentiated analysis for different types of viruses, such as respiratory viruses and digestive viruses. They cannot accurately match the actual transmission characteristics of various viruses, nor can they accurately determine the current prevalence of viruses. In addition, the prevention and control recommendations for novel viruses are relatively general and cannot provide customized prevention and control plans based on virus type and prevalence. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a virus transmission path analysis system and method based on big data. It has the advantages of high accuracy in multi-dimensional assessment and excellent intelligent prevention and control effects, and solves the problem that traditional virus transmission path analysis systems are unable to conduct differentiated analysis for virus types and cannot provide customized prevention and control solutions.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a virus transmission path analysis system based on big data, comprising a transmission collection module and an intelligent analysis module; The transmission data collection module connects to the database, hospital HIS system and big data platform through the network to obtain management data of all municipal districts, management data of virus-infected patients and all environmental factors affecting virus transmission, and classifies them into district datasets, patient datasets and environmental datasets. The intelligent analysis module consists of an epidemiological analysis unit, a risk assessment unit, and a prevention and control management unit. The epidemiological analysis unit is set with a fixed monitoring period. Then, by combining the district dataset, patient dataset, and environmental dataset, the prevalence of each virus is analyzed, and a corresponding prevalence index is generated. The risk assessment unit assesses the risk of virus transmission between adjacent jurisdictions based on the jurisdictional dataset and generates a corresponding risk index. The prevention and control management unit is set with a fixed epidemic threshold value. and risk threshold Combined with the popularity index and risk index They will provide corresponding recommendations for virus transmission prevention and control.

[0006] Preferably, the jurisdictional dataset includes the number of permanent residents, the number of inter-district population movements, the volume of inter-district goods circulation, and the number of open beds in each municipal district.

[0007] Preferably, the patient dataset includes the diagnosis time point, diagnosis jurisdiction, and symptom level for each virus-infected patient, wherein the virus type includes respiratory viruses, gastrointestinal viruses, fluid-borne viruses, and vector-borne viruses, and the symptom level includes mild, severe, and death.

[0008] Preferably, the environmental dataset includes daily temperature, daily humidity, and daily PM2.5 concentration.

[0009] Preferably, the popularity index The calculation process is as follows: S11. Based on the jurisdiction dataset, extract the first... Management data for each municipal district, known to be the first The first infection occurred in a municipal district. The index patient of the virus, and the first Time point of diagnosis and monitoring period of the index patient of the virus The starting time points are consistent, and the first The number of permanent residents in each municipal district is recorded as follows: ; S12. Based on the patient dataset, extract the monitoring period. within, no. All infections in the city's districts Patient management data for this type of virus will be monitored over a period of time. within, no. The infection rate in the municipal districts The number of confirmed cases of this virus is recorded as The monitoring cycle within, no. The infection rate in the municipal districts The number of patients with severe illness and death from this virus is recorded as follows: ; S13, Calculate the monitoring cycle within, no. The first of the municipal districts Incidence density of the virus ; S14. Calculate the monitoring cycle within, no. The first of the municipal districts Severe mortality rate of the virus ; S15. Based on the environmental dataset, the monitoring cycle... within, no. The daily temperature of each municipal district is recorded as follows: , Indicates the monitoring period The total number of days will be the monitoring period. within, no. The daily humidity of each municipal district is recorded as follows: The monitoring cycle within, no. The daily PM2.5 concentration in each municipal district is recorded as follows: ; S16. Calculate the monitoring cycle within, no. The average daily temperature of each municipal district Daily average humidity and daily average PM2.5 concentration ; S17. Based on S11-S16, calculate the monitoring period according to virus type using a weighted method. within, no. The first of the municipal districts The prevalence index of the virus .

[0010] Preferably, the risk index The calculation process is as follows: S21. Based on the dataset of the jurisdiction, extract the first... Management data for each municipal district, known to have appeared the first The first patient of the virus The municipal districts and the first The two municipal districts are adjacent, and the first The number of permanent residents in each municipal district is recorded as follows: The monitoring cycle within, no. The municipal districts and the first The number of inter-district population movements between municipal districts is denoted as The monitoring cycle within, no. The municipal districts and the first The volume of inter-district goods flow between municipal districts is recorded as follows: The monitoring cycle within, no. The number of open beds in each municipal district is recorded as follows: The monitoring cycle within, no. The number of open beds in each municipal district is recorded as follows: ; S22, Calculate the first Population base of each municipal district ; S23, Calculate the monitoring cycle within, no. The municipal districts and the first Difference in the number of open beds between municipal districts ; S24. Based on S21-S23, calculate the monitoring cycle using a weighted method. within, no. The virus in the The municipal districts and the first Risk index between municipal districts .

[0011] Preferably, the first Prevalence index of respiratory viruses ≥prevalence threshold When, it indicates the first The prevalence of this respiratory virus is high, and triggering measures include timely reminders to residents in the area to wear masks, reducing the probability of contact transmission, and prioritizing vaccine research and development. Prevalence index of gastrointestinal viruses ≥prevalence threshold When, it indicates the first The prevalence of this gastrointestinal virus is high. Triggering measures include timely investigation of contaminated food and water sources, comprehensive disinfection of public places, reminding residents to wash their hands frequently, and high-temperature disinfection of tableware and food.

[0012] Preferably, the first The prevalence of viruses transmitted through bodily fluids ≥prevalence threshold When, it indicates the first The prevalence of viruses transmitted through bodily fluids is high. Triggering measures include timely tracing of the index patient's activity trajectory, strict control over the use of blood products, and urging personnel within the jurisdiction to increase the intensity of disinfection and sterilization and the frequency of use of disposable items. The prevalence index of vector-borne viruses ≥prevalence threshold When, it indicates the first The prevalence of vector-borne viruses is high. Triggering measures include timely investigation of the activity areas of the index patient, urban stagnant water and garbage accumulation sites, disinfection and cleaning of mosquito breeding grounds, reminding residents to use safe and effective insecticides and mosquito repellent products, and reducing outdoor activities.

[0013] Preferably, the first The virus in the The municipal districts and the first Risk index between municipal districts ≥ Risk threshold When this occurs, it indicates a high risk of virus transmission between adjacent jurisdictions, triggering measures including [measures related to the first / secondary jurisdiction]. The municipal districts and the first All virus-infected individuals and close contacts within the city's jurisdiction will be placed under quarantine and control to cut off the chain of transmission. The level of [unclear - likely referring to a specific level or measure] will be raised accordingly. The municipal districts and the first Increase the frequency of disinfection of supplies in each city's districts to reduce cross-infection.

[0014] The method for analyzing virus transmission paths based on big data includes the following steps: Step 1: By connecting to the database, hospital HIS system and big data platform through the network, obtain management data of all municipal districts, management data of virus-infected patients and all environmental factors affecting the spread of the virus, and classify them into district datasets, patient datasets and environmental datasets; Step 2: Set a fixed monitoring period Then, by combining the district dataset, patient dataset, and environmental dataset, the prevalence of each virus is analyzed, and a corresponding prevalence index is generated. ; Step 3: Based on the dataset from the jurisdiction, assess the risk of virus transmission between adjacent jurisdictions and generate corresponding risk indices. ; Step 4: Set a fixed popularity threshold and risk threshold Combined with the popularity index and risk index They will provide corresponding recommendations for virus transmission prevention and control.

[0015] Compared with existing technologies, this invention provides a virus transmission path analysis system and method based on big data, which has the following beneficial effects: 1. This invention uses a transmission and acquisition module to connect to a database, hospital HIS system, and big data platform to obtain management data from all municipal districts, management data of virus-infected patients, and all environmental factors affecting virus transmission. These data are then categorized into district datasets, patient datasets, and environmental datasets, comprehensively covering multidimensional data during the virus transmission process. The intelligent analysis module is set to monitor data over a fixed period. By combining the district dataset, patient dataset, and environmental dataset, a corresponding epidemic index is generated for the municipal district where patient zero appeared. It intuitively reflects the scope of virus transmission, degree of harm, and overall environmental impact within the jurisdiction, and the multidimensional assessment has high accuracy.

[0016] 2. This invention, through an intelligent analysis module, focuses on the transmission paths across three dimensions—population flow, goods circulation, and medical resources—based on a dataset from the jurisdiction, assesses the risk of virus transmission between adjacent jurisdictions, and generates corresponding risk indices. The intelligent analysis module sets fixed thresholds and outputs corresponding virus transmission prevention and control suggestions for different virus types. It takes into account both precise prevention and control within a single jurisdiction and cross-regional collaborative governance, and establishes a scientific prevention and control strategy based on the degree of prevalence and the risk of transmission. This can reduce the waste of prevention and control resources, improve the efficiency of prevention and control, and achieve good results in intelligent prevention and control. Attached Figure Description

[0017] Figure 1 This is a system flowchart of the present invention; Figure 2 This is a diagram illustrating the steps of the method of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example Please see Figure 1 , Figure 2 Based on the experimental data of the prevalence index in Table 1 and the experimental data of the risk index in Table 2, this invention provides a virus transmission path analysis system and method based on big data. A virus transmission path analysis system based on big data, including a transmission data collection module and an intelligent analysis module; The transmission data collection module connects to the database, hospital HIS system and big data platform through the network to obtain management data of all municipal districts, management data of virus-infected patients and all environmental factors that affect the spread of the virus, and classifies them into district datasets, patient datasets and environmental datasets. The dataset for each municipality includes the number of permanent residents, the number of inter-district population movements, the volume of inter-district goods circulation, and the number of open hospital beds. The patient dataset includes the time of diagnosis, the jurisdiction of diagnosis, and the symptom level for each virus-infected patient. The virus types include respiratory viruses, gastrointestinal viruses, fluid-borne viruses, and vector-borne viruses. The symptom levels include mild, severe, and death. Specifically, respiratory viruses are mainly transmitted through droplets, such as influenza virus and COVID-19; digestive tract viruses are mainly transmitted through food, such as norovirus and rotavirus; viruses transmitted through bodily fluids are transmitted through blood contact, bodily fluid exchange, or injection, such as hepatitis B virus and HIV; and vector-borne viruses are mainly transmitted through mosquito bites, such as dengue fever virus and Zika virus. The environmental dataset includes daily temperature, daily humidity, and daily PM2.5 concentration; The intelligent analysis module is set to monitor for a fixed duration. Then, by combining the district dataset, patient dataset, and environmental dataset, the prevalence of each virus is analyzed, and a corresponding prevalence index is generated. The calculation process is as follows: S11. Based on the jurisdiction dataset, extract the first... Management data for each municipal district, known to be the first The first infection occurred in a municipal district. The index patient of the virus, and the first Time point of diagnosis and monitoring period of the index patient of the virus The starting time points are consistent, and the first The number of permanent residents in each municipal district is recorded as follows: ; Specifically, patient zero refers to the first individual medically confirmed to be infected with a specific virus and possessing the potential to spread the virus. It is not the same as the source of the virus. Once patient zero is clearly identified, the core and primary task is to systematically analyze the transmission chain, spread range, and transmission patterns of the novel virus based on key information such as the patient's activity trajectory and the people they have been in contact with, so as to provide a scientific basis for subsequent precise prevention and control and to block the spread of the epidemic. S12. Based on the patient dataset, extract the monitoring period. within, no. All infections in the city's districts Patient management data for this type of virus will be monitored over a period of time. within, no. The infection rate in the municipal districts The number of confirmed cases of this virus is recorded as The monitoring cycle within, no. The infection rate in the municipal districts The number of patients with severe illness and death from this virus is recorded as follows: ; S13, Calculate the monitoring cycle within, no. The first of the municipal districts Incidence density of the virus Its expression is as follows:

[0020] S14. Calculate the monitoring cycle within, no. The first of the municipal districts Severe mortality rate of the virus Its expression is as follows:

[0021] S15. Based on the environmental dataset, the monitoring cycle... within, no. The daily temperature of each municipal district is recorded as follows: , Indicates the monitoring period The total number of days will be the monitoring period. within, no. The daily humidity of each municipal district is recorded as follows: The monitoring cycle within, no. The daily PM2.5 concentration in each municipal district is recorded as follows: ; S16. Calculate the monitoring cycle within, no. The average daily temperature of each municipal district Daily average humidity and daily average PM2.5 concentration Its expression is as follows:

[0022]

[0023]

[0024] S17. Based on S11-S16, calculate the monitoring period according to virus type using a weighted method. within, no. The first of the municipal districts The prevalence index of the virus Its expression is as follows: If the first This virus belongs to the respiratory virus family.

[0025] In the formula, This represents the conversion factor for the number of confirmed cases of patients processed in a dimensionless manner. This represents the weight of the number of confirmed cases after dimensionless processing. The conversion factor represents the dimensionless treatment incidence density. The weights representing the disease density after dimensionless treatment. This represents the conversion factor for dimensionless treatment of severe illness mortality. This represents the weight of the critical illness mortality rate after dimensionless treatment. This represents the standard value used to measure the average daily temperature. This represents the conversion factor for the ratio of the dimensionless standard value to the daily average temperature. This represents the weight of the ratio of the dimensionless standard value to the daily average temperature. This represents the standard value used to measure average daily humidity. This represents the conversion factor between the dimensionless standard value and the ratio of daily average humidity. This indicates the weight of the ratio of the dimensionless standard value to the daily average humidity. This represents the standard value used to measure the daily average PM2.5 concentration. This represents the conversion factor for the dimensionless treatment of the ratio of daily average PM2.5 concentration to the standard value. This represents the weight of the ratio of the dimensionless treated daily average PM2.5 concentration to the standard value. , , , , and All are constants, and , Indicates the monitoring period within, no. The first of the municipal districts The prevalence index of respiratory viruses; If the first This virus belongs to the gastrointestinal tract.

[0026] In the formula, This represents the weight of the number of confirmed cases after dimensionless processing. The weights representing the disease density after dimensionless treatment. This represents the weight of the critical illness mortality rate after dimensionless treatment. This represents the weight of the ratio of the dimensionless standard value to the daily average temperature. This indicates the weight of the ratio of the dimensionless standard value to the daily average humidity. This represents the weight of the ratio of the dimensionless treated daily average PM2.5 concentration to the standard value. , , , , and All are constants, and , , , Indicates the monitoring period within, no. The first of the municipal districts The prevalence index of various gastrointestinal viruses; If the first This virus is a type of virus that is transmitted through bodily fluids.

[0027] In the formula, This represents the weight of the number of confirmed cases after dimensionless processing. The weights representing the disease density after dimensionless treatment. This represents the weight of the critical illness mortality rate after dimensionless treatment. This represents the weight of the ratio of the dimensionless standard value to the daily average temperature. This indicates the weight of the ratio of the dimensionless standard value to the daily average humidity. This represents the weight of the ratio of the dimensionless treated daily average PM2.5 concentration to the standard value. , , , , and All are constants, and , , Indicates the monitoring period within, no. The first of the municipal districts The prevalence index of viruses transmitted through bodily fluids; If the first This virus belongs to the arbovirus family.

[0028] In the formula, This represents the weight of the number of confirmed cases after dimensionless processing. The weights representing the disease density after dimensionless treatment. This represents the weight of the critical illness mortality rate after dimensionless treatment. This represents the weight of the ratio of the dimensionless standard value to the daily average temperature. This indicates the weight of the ratio of the dimensionless standard value to the daily average humidity. This represents the weight of the ratio of the dimensionless treated daily average PM2.5 concentration to the standard value. , , , , and All are constants, and , , , Indicates the monitoring period within, no. The first of the municipal districts The prevalence index of vector-borne viruses; Specifically, the number of confirmed cases is a basic quantitative indicator of the epidemic scale, directly reflecting the spread of the virus and the base of infection in the region. The incidence density accurately reflects the intensity of virus transmission and the risk of local clustering. The severe mortality rate is related to the pathogenicity of the virus, the carrying capacity of regional medical resources and the effectiveness of prevention and control measures, and is a key indicator for assessing the degree of epidemic harm. Environmental temperature and humidity are key factors that trigger the spread of the virus. Among them, the higher the temperature, the longer the survival time of gastrointestinal viruses, body fluid-transmitted viruses and vector-borne viruses on the surface of contaminated objects. The higher the humidity, the slower the rate of virus inactivation, which is more conducive to the survival of mosquitoes. The following is the experimental data of the popularity index, as shown in Table 1: Table 1: Experimental Data of Popularity Index

[0029] Table 1 shows the experimental data on the prevalence index, selecting the same municipal district. The respiratory virus A, gastrointestinal virus B, bodily fluid-borne virus C, and arbovirus D, which appeared as patient zero at the same time point, were used as experimental targets. Statistics were compiled for the municipal districts. The permanent resident population is 1 million, and the monitoring period is... Set to 30 days, the time point of diagnosis for patient zero and the monitoring period The start time is consistent, and the monitoring cycle is consistent. Within 30 days, the municipal districts The average daily temperature is 22℃, the average daily humidity is 65%, and the average daily PM2.5 concentration is 42μg / m³. These are the standard values ​​used to measure the average daily temperature. Set to 25℃, the standard value for measuring average daily humidity. Set to 60%, the standard value used to measure daily average PM2.5 concentration. Set to 35 μg / m³, conversion factor to All are 1, representing the weight for respiratory viruses. , , , , , Weighting of viruses in the digestive tract , , , , , Weighting of viruses transmitted through bodily fluids , , , , , Weighting of arboviruses , 4, , , , ; Popularity threshold Used to measure the prevalence of a virus over a short period of time, the prevalence threshold is shown in Table 1, the experimental data for the prevalence index. The preferred value is set to 0.8. Based on the assessment, the prevalence index of viral C transmitted through bodily fluids is [value missing]. >Popularity threshold The prevalence of viral load C (Biovirus C) is high. Triggering measures include timely tracing of the activity trajectory of the index patient for viral load C, strict control over the use of blood products, and urging residents to increase the intensity of disinfection and sterilization and the frequency of use of disposable items. The prevalence index of arbovirus D is also mentioned. >Popularity threshold This indicates a high prevalence of vector-borne virus D. Triggering measures include timely investigation of the activity areas of the zero patient of vector-borne virus D, urban stagnant water and garbage accumulation sites, disinfection and cleaning of mosquito breeding grounds, reminding residents to use safe and effective insecticides and mosquito repellent products, and reducing outdoor activities. The intelligent analysis module assesses the risk of virus transmission between adjacent jurisdictions based on the jurisdictional dataset and generates a corresponding risk index. The calculation process is as follows: S21. Based on the dataset of the jurisdiction, extract the first... Management data for each municipal district, known to have appeared the first The first patient of the virus The municipal districts and the first The two municipal districts are adjacent, and the first The number of permanent residents in each municipal district is recorded as follows: The monitoring cycle within, no. The municipal districts and the first The number of inter-district population movements between municipal districts is denoted as The monitoring cycle within, no. The municipal districts and the first The volume of inter-district goods flow between municipal districts is recorded as follows: The monitoring cycle within, no. The number of open beds in each municipal district is recorded as follows: The monitoring cycle within, no. The number of open beds in each municipal district is recorded as follows: ; S22, Calculate the first Population base of each municipal district Its expression is as follows:

[0030] In the formula, This represents a correction factor for the number of migrant workers; S23, Calculate the monitoring cycle within, no. The municipal districts and the first Difference in the number of open beds between municipal districts Its expression is as follows:

[0031] S24. Based on S21-S23, calculate the monitoring cycle using a weighted method. within, no. The virus in the The municipal districts and the first Risk index between municipal districts Its expression is as follows:

[0032] In the formula, This represents the conversion factor for dimensionless population base processing. This represents the weight of the population base after dimensionless processing. This represents the conversion coefficient for dimensionless processing of inter-regional material flow. This represents the weight of the inter-regional material flow volume after dimensionless processing. This represents the conversion factor for the dimensionless processing of the difference in the number of open beds. This represents the weight of the difference in the number of open beds after dimensionless processing. , and All are constants, and

[0033] The following is the experimental data for the risk index, as shown in Table 2: Table 2: Experimental Data of Risk Index

[0034] Table 2 shows the experimental data for the risk index. Adjacent municipal districts X, Y, and Z were selected as the experimental targets, with a monitoring period of... Given a 30-day period, the index case of influenza A virus is known to have appeared in district X of the city, and district X has 800 available hospital beds. What is the correction factor for the number of migrant workers? Set to 0.8, conversion factor , , Weight , , ; Risk threshold Used to measure the risk of H1N1 virus transmission between adjacent jurisdictions, the risk threshold is shown in Table 2, the experimental data for the risk index. The preferred value is set to 0.5. Based on the assessment, this represents the risk index of the spread of influenza A virus between municipal districts X and Y. > Risk threshold This indicates a high risk of H1N1 virus transmission between municipal district X and municipal district Y. Triggering measures include isolating and managing all infected individuals and close contacts in municipal districts X and Y to cut off the transmission chain, increasing the frequency of disinfection of materials in municipal districts X and Y respectively, and reducing cross-infection.

[0035] The method for analyzing virus transmission paths based on big data includes the following steps: Step 1: By connecting to the database, hospital HIS system and big data platform through the network, obtain management data of all municipal districts, management data of virus-infected patients and all environmental factors affecting the spread of the virus, and classify them into district datasets, patient datasets and environmental datasets; Step 2: Set a fixed monitoring period Then, by combining the district dataset, patient dataset, and environmental dataset, the prevalence of each virus is analyzed, and a corresponding prevalence index is generated. ; Step 3: Based on the dataset from the jurisdiction, assess the risk of virus transmission between adjacent jurisdictions and generate corresponding risk indices. ; Step 4: Set a fixed popularity threshold and risk threshold Combined with the popularity index and risk index They will provide corresponding recommendations for virus transmission prevention and control.

[0036] In this embodiment, the transmission acquisition module connects to the database, hospital HIS system, and big data platform via a network to acquire management data from all municipal districts, management data of virus-infected patients, and all environmental factors affecting virus transmission. These data are then categorized into district datasets, patient datasets, and environmental datasets, comprehensively covering multidimensional data during the virus transmission process. The intelligent analysis module, targeting the municipal district where patient zero was identified, integrates core information such as resident population, number of confirmed cases, number of severe cases and deaths, as well as environmental factors such as daily average temperature, humidity, and PM2.5 concentration. Based on the transmission characteristics of different viruses, it calculates the prevalence index using corresponding weighting methods. It intuitively reflects the overall situation of the virus's spread, harm, and environmental impact within the jurisdiction. The intelligent analysis module focuses on the transmission paths of three dimensions: population flow, material circulation, and medical resources, and generates corresponding risk indices through weighted calculations. It accurately captures the potential for transmission brought about by population movement, the risk carrier role of material circulation, and the indirect transmission risk caused by population movement due to differences in medical resources. It provides data support for cross-regional prevention and control. The intelligent analysis module sets fixed thresholds and outputs corresponding virus transmission prevention and control suggestions for different virus types. It takes into account both precise prevention and control within a single jurisdiction and covers collaborative governance across regions. It establishes a scientific prevention and control strategy based on the degree of prevalence and the implementation of policies according to the risk of transmission, which can reduce the waste of prevention and control resources and improve the efficiency of prevention and control.

[0037] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0038] The above formulas are all derived from software simulation using a large amount of data and are selected to be close to the actual values. The coefficients in the formulas are set by those skilled in the art according to the actual situation. The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the protection scope of the present invention.

Claims

1. A system for analyzing the path of virus propagation based on big data, characterized in that: The application comprises a propagation collection module and an intelligent analysis module. The propagation collection module connects a database, a hospital HIS system and a big data platform through a network, acquires management data of all municipal districts, management data of virus-infected patients and all environmental factors affecting virus propagation, and classifies and forms district data sets, patient data sets and environmental data sets. The intelligent analysis module is composed of a prevalence analysis unit, a risk assessment unit and a prevention and control management unit , combined with the jurisdiction dataset, the patient dataset and the environment dataset, the prevalence of each virus is analyzed to generate a corresponding prevalence index , the risk assessment unit assesses the risk of virus transmission between adjacent jurisdictions according to the jurisdiction dataset to generate a corresponding risk index , the prevention and control management unit sets a fixed value of the prevalence threshold and the risk threshold , combined with the prevalence index and the risk index , the corresponding virus transmission prevention and control suggestions are output.

2. The big data based virus propagation path analysis system of claim 1, wherein: The district data set comprises the number of permanent residents, the number of cross-district population flow, the cross-district material flow and the number of open beds of each municipal district.

3. The big data based virus propagation path analysis system of claim 2, wherein: The patient data set comprises the diagnosis time point, the diagnosis district and the symptom grade of each virus-infected patient, wherein the virus type comprises a respiratory virus, a digestive virus, a body fluid transmission virus and a insect-borne virus, and the symptom grade comprises mild, severe and death.

4. The big data based virus propagation path analysis system of claim 3, wherein: The environmental data set comprises daily air temperature, daily humidity and daily PM2.5 concentration.

5. The big data based virus propagation path analysis system of claim 4, wherein: The popularity index The calculation flow is as follows: S11, according to the jurisdiction dataset, extract the management data of the first municipal district, it is known that the first municipal district has a zero patient infected with the first virus, and the zero patient infected with the first virus is diagnosed at the same time point as the starting time point of the monitoring period , and the number of permanent residents in the first municipal district is recorded as ; S12, extracting a monitoring period according to the patient data set in the first municipal district, the patient management data of all patients infected with the first virus, the number of confirmed cases of patients infected with the first virus in the first municipal district in the monitoring period is recorded as , the number of severe and dead patients infected with the first virus in the first municipal district in the monitoring period is recorded as ; S13, calculate monitoring period in the first of the first of the first of the first S14, calculate monitoring period in the first of the 31 municipal districts ; S15, according to the environmental data set, the monitoring period , , , , , , , , , , ; S16, calculate monitoring period In, the first city average daily temperature , daily humidity and daily PM2.5 concentration ; S17、According to S11-S16, the epidemic index of the virus in the first municipal district in the first month of the monitoring period is calculated by weighting according to the virus type. ​ 6. The big data based virus propagation path analysis system of claim 5, wherein: The risk index The calculation proceeds as follows: S21. Based on the dataset of the jurisdiction, extract the first... Management data for each municipal district, known to have appeared the first The first patient of the virus The municipal districts and the first The two municipal districts are adjacent, and the first The number of permanent residents in each municipal district is recorded as follows: The monitoring cycle within, no. The municipal districts and the first The number of inter-district population movements between municipal districts is denoted as The monitoring cycle within, no. The municipal districts and the first The volume of inter-district goods flow between municipal districts is recorded as follows: The monitoring cycle within, no. The number of open beds in each municipal district is recorded as follows: The monitoring cycle within, no. The number of open beds in each municipal district is recorded as follows: ; S22、calculate the population base of the first municipal district ; S23, calculate monitoring period The number of open beds between the first municipal district and the second municipal district ; S24、According to S21-S23, the monitoring period is calculated by weighting The virus in the first The risk index of the virus spreading between the first The risk index of the virus spreading between the first The risk index of the virus spreading between the first .

7. The big data based virus propagation path analysis system of claim 6, wherein: The first Prevalence index of respiratory viruses ≥prevalence threshold When, it indicates the first The prevalence of this respiratory virus is high, and triggering measures include timely reminders to residents in the area to wear masks, reducing the probability of contact transmission, and prioritizing vaccine research and development. Prevalence index of gastrointestinal viruses ≥prevalence threshold When, it indicates the first The prevalence of this gastrointestinal virus is high. Triggering measures include timely investigation of contaminated food and water sources, comprehensive disinfection of public places, reminding residents to wash their hands frequently, and high-temperature disinfection of tableware and food.

8. The big data based virus propagation path analysis system of claim 7, wherein: The first The prevalence of viruses transmitted through bodily fluids ≥prevalence threshold When, it indicates the first The prevalence of viruses transmitted through bodily fluids is high. Triggering measures include timely tracing of the activity trajectory of the index patient, strict control over the use of blood products, and urging residents to increase the intensity of disinfection and sterilization and the frequency of use of disposable items. The prevalence index of vector-borne viruses ≥prevalence threshold When, it indicates the first The prevalence of vector-borne viruses is high. Triggering measures include investigating the activity areas of the index patient, stagnant water and garbage dumps in the city, disinfecting and cleaning mosquito breeding grounds, reminding residents to use safe and effective insecticides and mosquito repellent products, and reducing outdoor activities.

9. The big data based virus propagation path analysis system of claim 8, wherein: The first The virus in the The municipal districts and the first Risk index between municipal districts ≥ Risk threshold When this occurs, it indicates a high risk of virus transmission between adjacent jurisdictions, triggering measures including [measures related to the first / secondary jurisdiction]. The municipal districts and the first All virus-infected individuals and close contacts within the city's jurisdiction will be placed under quarantine and control to cut off the chain of transmission. The level of [unclear - likely referring to a specific level or measure] will be raised accordingly. The municipal districts and the first Increase the frequency of disinfection of supplies in each city's districts to reduce cross-infection.

10. The method of analyzing the path of virus propagation based on big data, applied to the system of analyzing the path of virus propagation based on big data according to any one of claims 1-9, characterized in that, The application comprises the following steps: Step one: connecting a database, a hospital HIS system and a big data platform through a network, acquiring management data of all municipal districts, management data of virus-infected patients and all environmental factors affecting virus propagation, and classifying and forming district data sets, patient data sets and environmental data sets. Step two: set a fixed monitoring period In combination with the jurisdiction dataset, patient dataset, and environmental dataset, the prevalence of each virus is analyzed to generate a corresponding prevalence index ; Step three: According to the jurisdiction dataset, assess the degree of risk of virus transmission between adjacent jurisdictions, and generate the corresponding risk index ; Step four: set a fixed value of the prevalence threshold and risk threshold , combined with the prevalence index and risk index , output the corresponding virus transmission prevention and control suggestions.

Images