Infectious disease trend analysis method based on big data

Abstract

The present invention relates to the field of infectious disease data processing technology, and specifically to an infectious disease trend analysis method based on big data. The present invention obtains personnel data, prevention and control measures, and the number of infected patients before and after the adoption of different types of prevention and control measures in different regions during the infectious disease transmission process; obtains the population coefficient of each region based on the changes in personnel data in each region and regional development; obtains the degree of infectious disease suppression of each prevention and control measure based on the changes in the number of patients before and after the adoption of each prevention and control measure; obtains the traditional infectious disease prediction model of the target region based on the number change characteristics of each population in the target region within the predicted time when no prevention and control measures are adopted; obtains the final infectious disease prediction model by combining the population coefficient and the degree of infectious disease suppression; and analyzes the infectious disease trend according to the model. The present invention obtains a relatively accurate final infectious disease prediction model, making the infectious disease trend analysis more in line with the actual situation.

Description

Technical Field

[0001] The present invention relates to the technical field of infectious disease data processing, and in particular to an infectious disease trend analysis method based on big data. Background Art

[0002] With the rapid development of information technology, big data technology has become an important tool for acquiring, storing and processing massive amounts of data, providing more data sources and more powerful computing power for infectious disease research. Infectious diseases are a global public health challenge, and understanding the spread and trends of infectious diseases is crucial to taking effective preventive measures in a timely manner. At the same time, with the increasing maturity of data science and technology, people can use machine learning, data mining, statistical analysis and other methods to process and analyze large-scale data, providing powerful tools and methods for infectious disease trend analysis.

[0003] In the process of infectious disease transmission, relevant personnel usually use big data technology and data science methods to study and analyze the transmission trend of infectious diseases. The technical advantage is that it can process massive multi-source data to reveal the transmission patterns of infectious diseases. However, traditional prediction models do not take into account the different populations in different regions, resulting in large differences in the transmission trends of infectious diseases in different regions after prevention and control measures are taken. At this time, the traditional prediction models cannot accurately analyze the trend of infectious diseases. Summary of the invention

[0004] In order to solve the technical problem that the traditional prediction model does not take into account the different populations in different regions, resulting in large differences in the spread trends of infectious diseases in different regions after prevention and control measures are taken, and thus the traditional prediction model cannot accurately perform infectious disease trend analysis, the purpose of the present invention is to provide an infectious disease trend analysis method based on big data, and the technical scheme adopted is as follows: A method for analyzing infectious disease trends based on big data, the method comprising: Obtain data on people in different regions during the spread of infectious diseases, different types of prevention and control measures, and the number of infected patients before and after the adoption of different types of prevention and control measures; Select any region as the target region; obtain the population coefficient of the target region based on the change characteristics of the personnel data and regional development characteristics of the target region; select any prevention and control measure as the target prevention and control measure; in the process of the spread of different types of infectious diseases, obtain the degree of infectious disease suppression of the target prevention and control measure based on the change characteristics of the number of infected patients in the target region before and after the target prevention and control measure is taken; Obtaining a traditional infectious disease prediction model for the target area; adjusting the traditional infectious disease prediction model according to the population coefficient of the target area and the degree of infectious disease suppression of all types of prevention and control measures in the target area to obtain a final infectious disease prediction model; The infectious disease trends are analyzed based on the final infectious disease prediction model.

[0005] Furthermore, the method for obtaining the population coefficient includes: The population data includes the number of permanent residents in different regions, the number of inflows and outflows in different regions during a preset first period; Combine the number of inflows and outflows in the first preset period with the number of permanent residents in the target area to obtain the degree of population mobility in the target area; Obtaining preset regional development factors of target areas; The population coefficient in the target area is obtained according to the population mobility degree, population density and the preset regional development factor in the target area, wherein the population coefficient is positively correlated with the population mobility degree, population density and the preset regional development factor.

[0006] Furthermore, the method for obtaining the degree of population mobility includes: The difference between the number of inflow and outflow population in the target area during the first preset period is taken as the number of non-resident population; The ratio between the number of non-resident population and the number of resident population in the target area is taken as the population mobility level of the target area.

[0007] Furthermore, the method for obtaining the preset regional development factor includes: All areas of first-tier cities are considered first-tier areas, all areas of second-tier cities are considered second-tier areas, all areas of third-tier cities are considered third-tier areas, and all areas of other non-tier cities are considered fourth-tier areas; Different preset regional development factors are set for the first-tier region, the second-tier region, the third-tier region and the fourth-tier region, wherein the preset regional development factors of the first-tier region, the second-tier region, the third-tier region to the fourth-tier region gradually decrease.

[0008] Furthermore, the method for obtaining the degree of inhibition of infectious diseases includes: The number of infected patients increased in the preset second period before the target prevention and control measures are adopted in the process of each infectious disease transmission is obtained as the number of first infected patients; the number of infected patients increased in the preset second period after the target prevention and control measures are adopted is obtained as the number of second infected patients; According to the change in the number of infected patients before and after the targeted prevention and control measures are taken during the transmission of different infectious diseases, the degree of infectious disease suppression of the targeted prevention and control measures is obtained.

[0009] Furthermore, according to the change in the number of infected patients before and after the target prevention and control measures are taken during the transmission of different infectious diseases, the degree of infectious disease suppression of the target prevention and control measures is obtained, including: Calculate the difference between the first number of infected patients and the second number of infected patients in the transmission process of each infectious disease as a first difference; Using the ratio between the first difference and the first number of infected patients as the infectious disease suppression coefficient of the target prevention and control measures in the process of each infectious disease transmission; The infectious disease suppression coefficients of the target prevention and control measures during the spread of all types of infectious diseases are averaged to obtain the infectious disease suppression degree of the target prevention and control measures.

[0010] Furthermore, the method for obtaining the traditional infectious disease prediction model includes: All people in the target area are divided into uninfected people, infected people and recovered immune people; based on the change characteristics of the number of uninfected people, infected people and recovered immune people in the target area within the preset prediction time when no prevention and control measures are adopted, the traditional infectious disease prediction model of the target area is obtained.

[0011] Furthermore, based on the quantitative change characteristics of the uninfected population, infected population, and recovered immune population in the target area within the preset prediction time when no prevention and control measures are adopted, the traditional infectious disease prediction model of the target area is obtained, including: The increased number of infected patients in the preset second period when no prevention and control measures are adopted is obtained as the number of third infected patients; the product of the uninfected population and the infected population in the target area is taken as the number of close contacts of people; the ratio between the number of third infected patients and the number of close contacts of people is taken as the population infection rate in the target area; Obtain the average recovery time of each person in the recovered immune population; use the reciprocal of the average recovery time as the population recovery rate in the target area; The product of the population infection rate and the preset prediction time is used as the infection probability, and the product of the number of close contacts between the persons and the infection probability is used as the increase in the number of infected people within the preset prediction time; The product of the population recovery rate and the preset prediction time is used as the recovery probability, and the product of the infected population and the recovery probability is used as the increase in the number of people who have recovered within the preset prediction time; The difference between the increase in the number of recovered people and the increase in the number of infected people within the preset prediction time is used as a traditional infectious disease prediction model for the preset prediction time in the target area.

[0012] Furthermore, the method for obtaining the final infectious disease prediction model includes: The inverse of the population coefficient of the target area and the product of the degree of infectious disease suppression after the target area adopts the target prevention and control measures are negatively correlated to obtain the infection rate adjustment coefficient; the product of the infection rate adjustment coefficient and the population infection rate is used as the final infection rate of the target area after the target prevention and control measures are taken; The traditional infectious disease prediction model is adjusted according to the final infection rate to obtain a final infectious disease prediction model.

[0013] Furthermore, the traditional infectious disease prediction model is adjusted according to the final infection rate to obtain a final infectious disease prediction model, including: The product of the final infection rate after adopting the target prevention and control measures and the preset prediction time is used as the final infection probability, and the product of the number of close contacts between people and the final infection probability is used as the final increase in the number of infected people within the preset prediction time after adopting the target prevention and control measures; Change the target prevention and control measures to obtain the final increase in the number of infected people within the preset prediction time after adopting each prevention and control measure; The difference between the increase in the number of recovered people within the preset prediction time and the increase in the number of each type of final infected population is used as the final infectious disease prediction model for the preset prediction time in the target area.

[0014] The present invention has the following beneficial effects: The present invention needs to analyze the trend of infectious disease transmission in different regions. Since the personnel composition of different regions is different and the impact on the spread of infectious diseases is different, the personnel data of different regions are obtained. After the spread of infectious diseases, decision makers will take a variety of prevention and control measures to suppress the trend of infectious disease transmission, so different types of prevention and control measures are obtained; since the prevention and control measures will have an inhibitory effect on the spread of infectious diseases after a certain period of time, the number of infected patients before and after the adoption of different types of prevention and control measures is obtained, and the inhibitory effect is analyzed through the change in quantity; since the population density of the target area affects the trend of infectious disease transmission, and the regional economic development affects the population mobility in the target area, according to the change characteristics of the personnel data in the target area and Regional development characteristics, obtain the population coefficient of each region; since different prevention and control measures have different effects on the prevention and control of infectious diseases, analyze the degree of infectious disease suppression of each prevention and control measure; since decision makers will sort out the infection situation of personnel in the target area after discovering the spread of infectious diseases, and predict and analyze the trend of the subsequent infectious disease transmission process, obtain the traditional infectious disease prediction model of the target area; since the prevention and control measures have an inhibitory effect on the trend of infectious disease transmission and the population coefficient of the target area has an enhancing effect on the trend of infectious disease transmission, the traditional infectious disease prediction model is adjusted using the population coefficient and the degree of infectious disease suppression to obtain the final infectious disease prediction model; analyze the infectious disease trend according to the final infectious disease prediction model. The present invention combines the population changes in the region and the inhibitory effects of different prevention and control measures on the spread of infectious diseases to obtain a more accurate final infectious disease prediction model, so that the infectious disease trend analysis is more in line with the actual situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of an infectious disease trend analysis method based on big data provided by an embodiment of the present invention; Figure 2 A flow chart of a method for obtaining a population coefficient provided by one embodiment of the present invention; Figure 3 A flow chart of a method for obtaining the degree of suppression of an infectious disease provided by one embodiment of the present invention; Figure 4 A flow chart of a method for obtaining a final infectious disease prediction model provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of an infectious disease trend analysis method based on big data proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a method for analyzing infectious disease trends based on big data provided by the present invention in conjunction with the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of an infectious disease trend analysis method based on big data provided by an embodiment of the present invention, the method comprising: Step S1: Obtain personnel data from different regions during the spread of infectious diseases, different types of prevention and control measures, and the number of infected patients before and after the adoption of different types of prevention and control measures.

[0021] The embodiment of the present invention is mainly applied to the scenario of infectious disease trend prediction. Due to the different personnel composition and environment in different regions, the spread trend of infectious diseases in different regions is different. In order to analyze the process of infectious disease transmission, the population quantity characteristics of different regions, that is, personnel data, are first obtained. In reality, after the spread of infectious diseases, decision makers will take a variety of prevention and control measures to suppress the spread trend of infectious diseases, so different types of prevention and control measures are obtained; after a certain period of time, the prevention and control measures will have an inhibitory effect on the spread of infectious diseases, and the inhibitory effect can be judged and analyzed by the changes in the number of infected patients before and after the adoption of different types of prevention and control measures, so the number of infected patients before and after the adoption of different types of prevention and control measures is obtained.

[0022] In one embodiment of the present invention, different types of prevention and control measures specifically include: isolation and quarantine, vaccine development and vaccination, public health publicity and education, travel restrictions and blockade measures, and medical resource allocation and support. It should be noted that in other embodiments of the present invention, other prevention and control measures such as vector control, mental health support, community participation and mobilization may also be adopted, which are not limited here.

[0023] In an embodiment of the present invention, the population coefficient of each region is obtained according to the flow of personnel and regional development in each region, and the infectious disease suppression degree of the target prevention and control measures is obtained according to the change characteristics of the number of infected patients before and after the target prevention and control measures are adopted during the spread of the infectious disease; the traditional infectious disease prediction model of the target region is obtained according to the change in the number of each population in the target region within a preset prediction time when no prevention and control measures are adopted; the traditional infectious disease prediction model is adjusted using the population coefficient and the infectious disease suppression degree to obtain the final infectious disease prediction model; the above process can be seen in the following embodiment.

[0024] Step S2: select any region as the target region; obtain the population coefficient of the target region according to the change characteristics of the personnel data and the regional development characteristics of the target region; select any prevention and control measure as the target prevention and control measure; in the process of the spread of different types of infectious diseases, obtain the infectious disease suppression degree of the target prevention and control measure according to the change characteristics of the number of infected patients in the target region before and after the target prevention and control measure is taken.

[0025] During the spread of infectious diseases, since different prevention and control measures have different effects in areas with different population densities, the population size characteristics of different regions are first analyzed when studying the spread trend of infectious diseases. In reality, the better the economic development of a region, the greater the population density of the region, and the flow of people within the region also has a greater impact on the population characteristics of the region. Therefore, in an embodiment of the present invention, the population coefficient of each region is obtained based on the personnel data change characteristics and regional development characteristics of the target region.

[0026] See also Figure 2 , which shows a flow chart of a method for obtaining a population coefficient: Step S201: The population data includes the number of permanent residents in different regions, the number of inflow population in different regions within a preset first period, and the number of outflow population.

[0027] In actual situations, the population characteristics in the target area include the number of non-resident population and resident population in the target area within a certain period of time, and in the embodiment of the present invention, the number of non-resident population needs to be obtained by the difference between the number of inflow population and the number of outflow population in the preset first period. Therefore, in the embodiment of the present invention, the number of inflow population and the number of outflow population in the preset first period and the number of resident population in the target area are obtained from the personnel data of the target area.

[0028] In one embodiment of the present invention, the preset first period is set to 1 year. It should be noted that in other embodiments of the present invention, the preset first period can be set voluntarily, which is not limited here.

[0029] Step S202: Combine the number of inflow population, the number of outflow population and the number of resident population in the target area to obtain the degree of population mobility in the target area.

[0030] Preferably, in one embodiment of the present invention, the method for obtaining the degree of population mobility includes: The difference between the number of inflow population and the number of outflow population in the target area during the preset first period is taken as the number of non-resident population.

[0031] The ratio between the number of non-resident population and the number of permanent population in the target area is taken as the degree of population mobility in the target area. The larger the number of non-resident population, the more population inflow into the target area during the preset first period, and the greater the degree of population inflow into the target area at this time.

[0032] Step S203: Obtaining a preset regional development factor of the target region.

[0033] The population density of the target area has a huge impact on the spread of infectious diseases. In reality, the higher the population density, the faster the spread of infectious diseases. Therefore, the population density of the target area is calculated by the ratio between the number of permanent residents in the target area and the area of ​​the target area. In one embodiment of the present invention, the population density calculation formula is as follows: In the formula, Indicates the target area; Indicates the population density in the target area during the preset first period; Indicates the number of permanent residents in the target area; Indicates the area of ​​the target region.

[0034] In reality, people usually flock to areas with larger cities and higher economic development, so the higher the line level of the city to which the target area belongs, the larger the population size of the target area. Therefore, in the embodiment of the present invention, the preset regional development factor of the target area is obtained according to the line level of the city to which the target area belongs.

[0035] Preferably, in one embodiment of the present invention, the method for obtaining the preset regional development factor includes: All areas of first-tier cities are regarded as first-tier areas, all areas of second-tier cities are regarded as second-tier areas, all areas of third-tier cities are regarded as third-tier areas, and all areas of other non-tier cities are regarded as fourth-tier areas.

[0036] Different preset regional development factors are set for the first-tier regions, the second-tier regions, the third-tier regions, and the fourth-tier regions, wherein the preset regional development factors of the first-tier regions, the second-tier regions, the third-tier regions, and the fourth-tier regions gradually decrease. In one embodiment of the present invention, the preset regional development factor of the first-tier regions is set to 0.9, the preset regional development factor of the second-tier regions is set to 0.8, the preset regional development factor of the third-tier regions is set to 0.7, and the preset regional development factor of the fourth-tier regions is set to 0.6. It should be noted that in other embodiments of the present invention, the preset regional development factor can be set arbitrarily, and is not limited here.

[0037] Step S204: Obtaining a population coefficient in the target area according to the population mobility, population density and preset regional development factor in the target area, wherein the population coefficient is positively correlated with the population mobility, population density and preset regional development factor.

[0038] In one embodiment of the present invention, the population coefficient calculation formula is as follows: In the formula, Indicates the target area; represents the population coefficient of the target area; It indicates the number of inflow population in the target area during the preset first period; It indicates the number of outflow population in the target area during the preset first period; Indicates the number of permanent residents in the target area; Indicates the population density in the target area during the preset first period; represents the preset regional development factor of the target area; Indicates the degree of population mobility within the target area during the preset first period; represents a normalization function. In one embodiment of the present invention, a sigmoid function is used for normalization, which is not limited herein.

[0039] In the population coefficient calculation formula, the population mobility level of the target area in the first period is preset The larger the value is, the more floating population there is in the target area during the first period, which means the population in the target area is larger, that is, the larger the population coefficient is. The population density in the target area during the first period is The larger it is, the larger the population in the target area, that is, the larger the population coefficient; the larger the preset regional development factor of the target area, the better the economic development of the target area, and the more it can attract people to gather, and the larger the population coefficient of the target area.

[0040] After the infectious disease begins to spread, decision makers will take a series of prevention and control measures to suppress the spread of the infectious disease according to the scale of the spread. Different prevention and control measures have different prevention and control effects on infectious diseases, that is, there are differences in the number of infected patients before and after the adoption of different prevention and control measures. Therefore, in the embodiment of the present invention, the degree of infectious disease suppression of the target prevention and control measures is obtained according to the change characteristics of the number of infected patients in the target area before and after the adoption of the target prevention and control measures.

[0041] See also Figure 3 , which shows a flow chart of a method for obtaining the degree of suppression of infectious diseases: Step S211: During the transmission of each infectious disease, the number of infected patients increased within the preset second period before the target prevention and control measures are adopted is obtained as the first number of infected patients; the number of infected patients increased within the preset second period after the target prevention and control measures are adopted is obtained as the second number of infected patients.

[0042] In order to analyze the inhibitory effect of the target prevention and control measures on the spread of infectious diseases, it is necessary to compare the changes in the number of infected patients before and after the adoption of the target prevention and control measures within the preset second period to make a judgment, wherein, the smaller the number of infected patients after the adoption of the target prevention and control measures compared to the number of infected patients before the adoption of the target prevention and control measures, the more obvious the inhibitory effect of the target prevention and control measures on the spread of infectious diseases is. Therefore, in an embodiment of the present invention, the increase in the number of infected patients in the preset second period before the adoption of the target prevention and control measures and the increase in the number of infected patients in the preset second period after the adoption of the target prevention and control measures in the process of each infectious disease transmission are obtained for subsequent analysis.

[0043] In one embodiment of the present invention, the preset second period is set to 1 day. It should be noted that in other embodiments of the present invention, the preset second period can be set voluntarily, which is not limited here.

[0044] Step S212: Obtain the infectious disease suppression degree of the target prevention and control measures according to the change in the number of infected patients before and after the target prevention and control measures are taken during the transmission of different infectious diseases.

[0045] Preferably, in one embodiment of the present invention, according to the degree of change in the number of infected patients before and after the target prevention and control measures are taken during the transmission of different infectious diseases, the degree of infectious disease suppression of the target prevention and control measures is obtained, including: Calculate the difference between the first number of infected patients and the second number of infected patients in the process of each infectious disease transmission as the first difference; take the ratio of the first difference to the first number of infected patients as the infectious disease suppression coefficient of the target prevention and control measures in the process of each infectious disease transmission, where the larger the infectious disease suppression coefficient, the larger the first difference, that is, the fewer the number of infected patients after adopting the target prevention and control measures.

[0046] Since the target prevention and control measures have different inhibitory effects in the process of spreading different infectious diseases, the infectious disease inhibition coefficients of the target prevention and control measures in the process of spreading all types of infectious diseases are averaged to obtain the infectious disease inhibition degree of the target prevention and control measures. In one embodiment of the present invention, the infectious disease inhibition degree calculation formula is as follows: In the formula, Indicates the target control measures; Indicates the degree of infectious disease suppression of the target control measures; Indicates the number of types of infectious diseases; Indicated in The number of infected patients in the preset second period before the targeted prevention and control measures are adopted during the spread of an infectious disease, i.e. the number of first infected patients; Indicated in During the spread of an infectious disease, the number of infected patients in the preset second period after the targeted prevention and control measures are adopted, that is, the second number of infected patients.

[0047] In the formula for calculating the degree of infectious disease suppression, The infectious disease suppression coefficient of the target prevention and control measures in the process of the spread of infectious diseases Reflects the targeted control measures in The inhibitory effect of the spread of infectious diseases, among which the first difference The larger the value, the fewer the number of infected patients will be after adopting the targeted prevention and control measures. The larger the infectious disease suppression coefficient of the target prevention and control measures in the process of the spread of an infectious disease, the average of the infectious disease suppression coefficients of the target prevention and control measures in the process of the spread of each infectious disease is taken to obtain the infectious disease suppression degree of the target prevention and control measures for multiple infectious diseases.

[0048] Step S3: Obtain a traditional infectious disease prediction model for the target area; adjust the traditional infectious disease prediction model according to the population coefficient of the target area and the degree of infectious disease suppression of all types of prevention and control measures in the target area to obtain a final infectious disease prediction model.

[0049] In reality, after an infectious disease event occurs in a target area, decision makers will sort out the infection situation of people in the target area after discovering the spread of the infectious disease, and conduct predictive analysis on the trend of the subsequent infectious disease spread process. At this time, the target area has not taken any prevention and control measures. Therefore, in an embodiment of the present invention, a traditional infectious disease prediction model for the target area is first obtained.

[0050] Preferably, in one embodiment of the present invention, obtaining a traditional infectious disease prediction model for a target area includes: Divide all people in the target area into uninfected, infected, and recovered immune groups; The increase in the number of infected patients in the preset second period when no prevention and control measures are adopted is obtained as the number of the third infected patients; since close contact may occur between everyone in the uninfected population and everyone in the infected population, the product of the uninfected population and the infected population in the target area is taken as the number of close contacts of the people; the ratio between the number of the third infected patients and the number of close contacts of the people is taken as the population infection rate in the target area, among which, the larger the number of the third infected patients, the more contagious the infectious disease is, and the greater the population infection rate in the target area.

[0051] Obtain the average recovery time of each person in the recovered immune population; take the inverse of the average recovery time as the population recovery rate in the target area, where the longer the average recovery time is, the more difficult it is to suppress the infectious disease, and at this time, the lower the population recovery rate in the target area.

[0052] The product of the infection rate of the population and the preset prediction time is used as the infection probability, and the product of the number of close contacts between people and the infection probability is used as the increase in the number of infected people within the preset prediction time, wherein the greater the infection probability, the greater the increase in the number of infected people within the preset prediction time. In one embodiment of the present invention, the preset prediction time is 1 week. It should be noted that in other embodiments of the present invention, the preset prediction time can be set voluntarily and is not limited here.

[0053] In one embodiment of the present invention, the formula for calculating the increase in the number of infected people is as follows: In the formula, It indicates the increase in the number of infected people in the target area at the preset prediction time; represents the uninfected population in the target area; represents the infected population in the target area; represents the infection rate of the population in the target area; Indicates the length of the preset prediction time; Indicates the number of close contacts of people in the target area; Represents the infection probability of the target area.

[0054] The product of the population recovery rate and the preset prediction time is used as the recovery probability, and the product of the infected population and the recovery probability is used as the number of people who have recovered within the preset prediction time. In one embodiment of the present invention, the formula for calculating the number of people who have recovered is as follows: In the formula, It indicates the increase in the number of people who will recover in the target area within the preset forecast time; represents the infected population in the target area; represents the recovery rate of the population in the target area; Indicates the length of the preset prediction time; Represents the probability of recovery in the target area.

[0055] The difference between the number of recovered people and the number of infected people within the preset prediction time is used as the traditional infectious disease prediction model for the preset prediction time in the target area. In the traditional infectious disease prediction model, when the difference is a positive number, it means that the spread of infectious diseases is being suppressed; when the difference is a negative number, it means that the spread of infectious diseases has increased and intervention is needed as soon as possible.

[0056] Since decision-makers in the target area often intervene and take various prevention and control measures as soon as they receive news of the spread of infectious diseases, and the larger the population in the target area, the more serious the spread of infectious diseases may become, the traditional infectious disease prediction model does not take into account the inhibitory effect of prevention and control measures on the trend of infectious disease spread and the increase in the population coefficient of the target area on the trend of infectious disease spread, which leads to the insufficient accuracy of the traditional infectious disease prediction model. Therefore, in an embodiment of the present invention, the traditional infectious disease prediction model is adjusted according to the population coefficient of the target area and the degree of infectious disease suppression of all types of prevention and control measures in the target area to obtain the final infectious disease prediction model.

[0057] See also Figure 4 , which shows a flow chart of a method for obtaining a final infectious disease prediction model: Step S311: negatively correlate the inverse of the population coefficient of the target area and the product of the degree of infectious disease suppression after the target area adopts the target prevention and control measures to obtain the infection rate adjustment coefficient; the product of the infection rate adjustment coefficient and the population infection rate is used as the corresponding final infection rate of the target area after the target prevention and control measures are taken.

[0058] During the spread of infectious diseases in the target area, if the population coefficient of the target area is larger, it means that the possibility of close contact between the uninfected population and the infected population in the target area is greater, and the spread of infectious diseases may be greater. At this time, the population infection rate needs to be increased; the greater the degree of infectious disease suppression after the target area adopts the target prevention and control measures, the better the suppression effect of the target prevention and control measures on the spread of infectious diseases. At this time, the population infection rate needs to be reduced. Therefore, the product of the inverse of the population coefficient of the target area and the degree of infectious disease suppression after the target area adopts the target prevention and control measures is negatively correlated to obtain the infection rate adjustment coefficient. Then, the infection rate adjustment coefficient is used to adjust the population infection rate to obtain the corresponding final infection rate of the target area after taking different prevention and control measures.

[0059] Step S312: adjusting the traditional infectious disease prediction model according to the final infection rate to obtain a final infectious disease prediction model.

[0060] Preferably, in one embodiment of the present invention, the traditional infectious disease prediction model is adjusted according to the final infection rate to obtain the final infectious disease prediction model, including: The product of the final infection rate after adopting the target prevention and control measures and the preset prediction time is taken as the final infection probability, and the product of the number of close contacts between people and the final infection probability is taken as the final increase in the number of infected people within the preset prediction time after adopting the target prevention and control measures; Change the target prevention and control measures to obtain the final increase in the number of infected people within the preset prediction time after adopting each prevention and control measure.

[0061] The difference between the increase in the number of recovered people within the preset prediction time and the increase in the number of each type of final infected population is used as the final infectious disease prediction model for the preset prediction time in the target area.

[0062] In the final infectious disease prediction model, when the difference is positive, it means that the spread of infectious diseases is being suppressed; when the difference is negative, it means that the spread of infectious diseases has increased and intervention is needed as soon as possible.

[0063] Step S4: Analyze the infectious disease trend based on the final infectious disease prediction model.

[0064] In one embodiment of the present invention, a method for analyzing infectious disease trends according to a final infectious disease prediction model is provided, which specifically includes: According to the final infectious disease prediction model you described, the infectious disease trend can be analyzed by the difference between the increase in the number of recovered people and the increase in the number of infected people within the preset prediction time. The detailed trend analysis can be carried out according to the following steps: 1. Data preparation: Collect and organize infectious disease data in the target area, including the number of newly confirmed cases per day, the number of newly recovered cases per day, etc.

[0065] 2. Model calculation: During the preset forecast period, the increase in the number of recovered people and the final increase in the number of infected people are calculated.

[0066] 3. Trend analysis: The difference is positive: the number of recovered people is increasing faster than the number of infected people, indicating that the spread of infectious diseases is being controlled. Current prevention and control measures (such as isolation, treatment, vaccination, etc.) are effective and should be maintained.

[0067] The difference is negative: the number of infected people is increasing faster than the number of recovered people, indicating that the spread of infectious diseases is expanding. Immediate and enhanced prevention and control measures are needed, such as increasing testing efforts, increasing vaccination rates, and strengthening isolation and quarantine.

[0068] 4. Further intervention measures: If the difference is negative, specific intervention strategies need to be developed, including but not limited to: Increase vaccination rates: Accelerate the promotion and implementation of vaccination, especially for high-risk groups.

[0069] Strengthen public health measures: such as increasing social distance, limiting large gatherings, and increasing mask wearing rates.

[0070] Improve testing and tracing capabilities: expand the scope of testing, and promptly trace and isolate close contacts.

[0071] Improve medical resources: Ensure that hospitals and medical institutions have sufficient resources to cope with new cases, including beds, medicines, and medical staff.

[0072] 5. Dynamic adjustment and monitoring: Regularly update the data input of the final infectious disease prediction model, recalculate the difference, and monitor the trend of infectious diseases in real time. Adjust the prevention and control strategy according to the latest difference changes to ensure the timeliness and effectiveness of prevention and control measures.

[0073] 6. Result evaluation and reporting: Regularly evaluate the effectiveness of prevention and control measures and the accuracy of the final infectious disease prediction model, and generate reports. Inform public health decision-makers and the public about current infectious disease trends and prevention and control measures taken.

[0074] 7. Long-term monitoring and research: Conduct long-term data monitoring and analysis, continuously optimize the final infectious disease prediction model, and improve its accuracy and reliability. Study the potential factors and laws of infectious disease transmission to provide a scientific basis for future infectious disease prevention and control.

[0075] It should be noted that in other embodiments of the present invention, other methods may be used to analyze infectious disease trends using the final infectious disease prediction model, which is not limited here.

[0076] In summary, the personnel data of different regions, different types of prevention and control measures, and the number of infected patients before and after the adoption of different types of prevention and control measures are obtained during the transmission process of infectious diseases; any region is selected as the target region; the population coefficient of each region is obtained based on the change characteristics of the personnel data in the target region and the regional development characteristics; any prevention and control measure is selected as the target prevention and control measure; during the transmission of different types of infectious diseases, the degree of infectious disease suppression of the target prevention and control measures is obtained based on the change characteristics of the number of infected patients in the target region before and after the target prevention and control measures are taken; the traditional infectious disease prediction model for the target region is obtained; the traditional infectious disease prediction model is adjusted based on the population coefficient of the target region and the degree of infectious disease suppression of all types of prevention and control measures in the target region to obtain the final infectious disease prediction model; the infectious disease trend is analyzed based on the final infectious disease prediction model.

[0077] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for analyzing infectious disease trends based on big data, characterized in that: The method comprises: Obtain data on people in different regions during the spread of infectious diseases, different types of prevention and control measures, and the number of infected patients before and after the adoption of different types of prevention and control measures; Select any region as the target region; obtain the population coefficient of the target region based on the change characteristics of the personnel data and regional development characteristics of the target region; select any prevention and control measure as the target prevention and control measure; in the process of the spread of different types of infectious diseases, obtain the degree of infectious disease suppression of the target prevention and control measure based on the change characteristics of the number of infected patients in the target region before and after the target prevention and control measure is taken; Obtaining a traditional infectious disease prediction model for the target area; adjusting the traditional infectious disease prediction model according to the population coefficient of the target area and the degree of infectious disease suppression of all types of prevention and control measures in the target area to obtain a final infectious disease prediction model; The infectious disease trends are analyzed based on the final infectious disease prediction model.

2. The infectious disease trend analysis method based on big data according to claim 1, characterized in that: The method for obtaining the population coefficient includes: The population data includes the number of permanent residents in different regions, the number of inflows and outflows in different regions during a preset first period; Combine the number of inflows and outflows in the first preset period with the number of permanent residents in the target area to obtain the degree of population mobility in the target area; Obtaining preset regional development factors of target areas; The population coefficient in the target area is obtained according to the population mobility degree, population density and the preset regional development factor in the target area, wherein the population coefficient is positively correlated with the population mobility degree, population density and the preset regional development factor.

3. The infectious disease trend analysis method based on big data according to claim 2, characterized in that: The method for obtaining the population mobility degree includes: The difference between the number of inflow and outflow population in the target area during the first preset period is taken as the number of non-resident population; The ratio between the number of non-resident population and the number of resident population in the target area is taken as the population mobility level of the target area.

4. The infectious disease trend analysis method based on big data according to claim 2, characterized in that: The method for obtaining the preset regional development factor includes: All areas of first-tier cities are considered first-tier areas, all areas of second-tier cities are considered second-tier areas, all areas of third-tier cities are considered third-tier areas, and all areas of other non-tier cities are considered fourth-tier areas; Different preset regional development factors are set for the first-tier region, the second-tier region, the third-tier region and the fourth-tier region, wherein the preset regional development factors of the first-tier region, the second-tier region, the third-tier region to the fourth-tier region gradually decrease.

5. The infectious disease trend analysis method based on big data according to claim 1, characterized in that: The method for obtaining the degree of suppression of infectious diseases includes: The number of infected patients increased in the preset second period before the target prevention and control measures are adopted in the process of each infectious disease transmission is obtained as the number of first infected patients; the number of infected patients increased in the preset second period after the target prevention and control measures are adopted is obtained as the number of second infected patients; According to the change in the number of infected patients before and after the targeted prevention and control measures are taken during the transmission of different infectious diseases, the degree of infectious disease suppression of the targeted prevention and control measures is obtained.

6. The infectious disease trend analysis method based on big data according to claim 5, characterized in that: According to the change in the number of infected patients before and after the targeted prevention and control measures are taken during the transmission of different infectious diseases, the degree of infectious disease suppression of the targeted prevention and control measures is obtained, including: Calculate the difference between the first number of infected patients and the second number of infected patients in the transmission process of each infectious disease as a first difference; Using the ratio between the first difference and the first number of infected patients as the infectious disease suppression coefficient of the target prevention and control measures in the process of each infectious disease transmission; The infectious disease suppression coefficients of the target prevention and control measures during the spread of all types of infectious diseases are averaged to obtain the infectious disease suppression degree of the target prevention and control measures.

7. The infectious disease trend analysis method based on big data according to claim 1, characterized in that: The method for obtaining the traditional infectious disease prediction model includes: All people in the target area are divided into uninfected people, infected people and recovered immune people; based on the change characteristics of the number of uninfected people, infected people and recovered immune people in the target area within the preset prediction time when no prevention and control measures are adopted, the traditional infectious disease prediction model of the target area is obtained.

8. The infectious disease trend analysis method based on big data according to claim 7, characterized in that: According to the change characteristics of the number of uninfected people, infected people and recovered immune people in the target area within the preset prediction time when no prevention and control measures are taken, the traditional infectious disease prediction model of the target area is obtained, including: The increased number of infected patients in the preset second period when no prevention and control measures are adopted is obtained as the number of third infected patients; the product of the uninfected population and the infected population in the target area is taken as the number of close contacts of people; the ratio between the number of third infected patients and the number of close contacts of people is taken as the population infection rate in the target area; Obtain the average recovery time of each person in the recovered immune population; and use the reciprocal of the average recovery time as the population recovery rate in the target area; The product of the population infection rate and the preset prediction time is used as the infection probability, and the product of the number of close contacts between the persons and the infection probability is used as the increase in the number of infected people within the preset prediction time; The product of the population recovery rate and the preset prediction time is used as the recovery probability, and the product of the infected population and the recovery probability is used as the increase in the number of people who have recovered within the preset prediction time; The difference between the increase in the number of recovered people and the increase in the number of infected people within the preset prediction time is used as a traditional infectious disease prediction model for the preset prediction time in the target area.

9. The infectious disease trend analysis method based on big data according to claim 8, characterized in that: The method for obtaining the final infectious disease prediction model includes: The inverse of the population coefficient of the target area and the product of the degree of infectious disease suppression after the target area adopts the target prevention and control measures are negatively correlated to obtain the infection rate adjustment coefficient; the product of the infection rate adjustment coefficient and the population infection rate is used as the final infection rate of the target area after the target prevention and control measures are taken; The traditional infectious disease prediction model is adjusted according to the final infection rate to obtain a final infectious disease prediction model.

10. The infectious disease trend analysis method based on big data according to claim 9, characterized in that: The traditional infectious disease prediction model is adjusted according to the final infection rate to obtain a final infectious disease prediction model, including: The product of the final infection rate after adopting the target prevention and control measures and the preset prediction time is used as the final infection probability, and the product of the number of close contacts between people and the final infection probability is used as the final increase in the number of infected people within the preset prediction time after adopting the target prevention and control measures; Change the target prevention and control measures to obtain the final increase in the number of infected people within the preset prediction time after adopting each prevention and control measure; The difference between the increase in the number of recovered people within the preset prediction time and the increase in the number of each type of final infected population is used as the final infectious disease prediction model for the preset prediction time in the target area.

Images