CN114334172B - Epidemic situation risk assessment method, system and readable storage medium - Google Patents
Epidemic situation risk assessment method, system and readable storage medium Download PDFInfo
- Publication number
- CN114334172B CN114334172B CN202111522302.1A CN202111522302A CN114334172B CN 114334172 B CN114334172 B CN 114334172B CN 202111522302 A CN202111522302 A CN 202111522302A CN 114334172 B CN114334172 B CN 114334172B
- Authority
- CN
- China
- Prior art keywords
- risk
- current value
- patients
- dimension
- village
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000013058 risk prediction model Methods 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000011161 development Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 39
- 238000011156 evaluation Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 208000024891 symptom Diseases 0.000 claims description 9
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 24
- 238000004458 analytical method Methods 0.000 description 11
- 230000002265 prevention Effects 0.000 description 7
- 206010035664 Pneumonia Diseases 0.000 description 5
- 230000036541 health Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 230000007480 spreading Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 241000711573 Coronaviridae Species 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 108010014173 Factor X Proteins 0.000 description 1
- 208000002979 Influenza in Birds Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 206010064097 avian influenza Diseases 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 229940124579 cold medicine Drugs 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000000586 desensitisation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides an epidemic situation risk assessment method, a system and a readable storage medium, wherein the method comprises the steps of determining historical risk assessment data associated with epidemic situation risks by combining a quantity numerical dimension for reflecting the quantity of risk assessment factors, a space density dimension for reflecting the risk degree of a corresponding statistical epidemic situation associated region on a floor area and a population density dimension for reflecting the per-capita risk degree of the corresponding epidemic situation associated region; constructing a training sample set according to the historical risk assessment data, and training a risk prediction model by using a preset machine learning algorithm; the machine learning algorithm comprises an AdaBoost algorithm; and processing the determined real-time risk assessment data through the trained risk prediction model to obtain the development trend of the epidemic situation in the future preset days. The implementation of the method can improve the comprehensiveness of risk assessment.
Description
Technical Field
The application relates to the technical field of big data processing, in particular to an epidemic situation risk assessment method and system and a readable storage medium.
Background
According to the requirement of 'fully applying methods such as big data analysis and the like to support the new coronary pneumonia epidemic situation prevention and control work' in the new coronary pneumonia epidemic situation prevention and control, by referring to the epidemic situation prevention and control experiences such as SARS, avian influenza and the like, all regions have fully utilized supporting means such as big data, informatization technology and the like, and have developed the construction and application work of real-time big data report, health code and the like of the epidemic situation, and the application of the data and the health code plays an important role in the epidemic situation prevention and control work. However, the existing epidemic prevention and control support means generally have limited statistical areas in terms of statistics and risk assessment, and the current assessment is more, so that the problem of incomplete risk assessment exists.
Disclosure of Invention
The embodiment of the application aims to provide an epidemic situation risk assessment method, system and readable storage medium, so that the comprehensiveness of risk assessment can be improved.
The embodiment of the application also provides an epidemic situation risk assessment method, which comprises the following steps:
determining historical risk evaluation data associated with the epidemic risk by combining a quantity numerical dimension for reflecting the quantity of the risk evaluation factors, a space density dimension for reflecting the risk degree on the floor area of the corresponding statistical epidemic situation associated region and a population density dimension for reflecting the per-capita risk degree of the corresponding epidemic situation associated region;
constructing a training sample set according to the historical risk assessment data, and training a risk prediction model by using a preset machine learning algorithm; the machine learning algorithm comprises an AdaBoost algorithm;
and processing the determined real-time risk assessment data through the trained risk prediction model to obtain the development trend of the epidemic situation in the future preset days.
In a second aspect, an embodiment of the present application further provides an epidemic situation risk assessment system, which includes a data processing module, a model training module, and a risk prediction module, wherein:
the data processing module is used for determining historical risk evaluation data associated with the epidemic situation risk by combining a numerical value dimension for reflecting the number of the risk evaluation factors, a space density dimension for reflecting the risk degree of the corresponding statistical epidemic situation associated region on the occupied area and a population density dimension for reflecting the average risk degree of the corresponding epidemic situation associated region;
the model training module is used for constructing a training sample set according to the historical risk assessment data and training a risk prediction model by a preset machine learning algorithm; the machine learning algorithm comprises an AdaBoost algorithm;
and the risk prediction module is used for processing the determined real-time risk evaluation data through the trained risk prediction model to obtain the development trend of the epidemic situation in the future preset days.
In a third aspect, an embodiment of the present application further provides a readable storage medium, where the readable storage medium includes an epidemic situation risk assessment method program, and when the epidemic situation risk assessment method program is executed by a processor, the steps of the epidemic situation risk assessment method described in any one of the above are implemented.
As can be seen from the above, the epidemic situation risk assessment method, the system and the readable storage medium provided in the embodiments of the present application determine the historical risk assessment data associated with the epidemic situation risk through the numerical dimension, the spatial density dimension and the population density dimension, thereby improving the comprehensiveness of risk assessment. In the aspect of statistics, compared with the prior art that only the city level is reached, the epidemic situation propagation risk assessment can be carried out through the occupied area of the epidemic situation associated region and the per capita risk degree, the related statistical range is wider, and the finally obtained prediction analysis result can be matched with the actual propagation trend of the epidemic situation.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an epidemic risk assessment method according to an embodiment of the present disclosure.
FIG. 2 is a graph showing the number of risk changes of high and medium epidemic situations in streets (towns) and communities (villages) of the experimental study in one embodiment.
FIG. 3 is a graph of the change in the risk index of epidemic status in a city under experimental study in one embodiment.
Fig. 4 is a schematic structural diagram of an epidemic risk assessment system according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. The components of embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
In one or more embodiments of the present invention, as shown in fig. 1, an epidemic situation risk prediction method is provided, which is described by taking as an example that the method is applied to a computer device (the computer device may specifically be a terminal or a server, and the terminal may specifically be, but is not limited to, various personal computers, laptops, smartphones, tablet computers, and portable wearable devices).
And step S100, determining historical risk assessment data associated with the epidemic risk by combining a quantity numerical dimension for reflecting the quantity of the risk assessment factors, a space density dimension for reflecting the risk degree on the floor area of the corresponding statistical epidemic situation associated region and a population density dimension for reflecting the average risk degree of the corresponding epidemic situation associated region.
Specifically, when the historical risk assessment data relates to a plurality of assessment factors, (1) the numerical dimension can be used to reflect the numerical value of any single assessment factor. (2) In terms of spatial density dimension, if the epidemic risk propagation degree is predicted based on the number of confirmed patients, it can be determined that the relative risk probability of propagation is higher in a region with a smaller floor area when the number of confirmed patients is the same. (3) Or, for example, the number of patients to be diagnosed, if the area is a dense area (i.e., a dense area), the risk level is relatively high.
In one embodiment, for the obtained historical risk assessment data, the computer device performs weighted calculation according to three dimensions of numerical values, space density and population density, and in the calculation process, a reference line is set according to historical level data in each calculation dimension. And finally, calculating specific values of the evaluation factors according to a range method.
S200, constructing a training sample set according to the historical risk assessment data, and training a risk prediction model by using a preset machine learning algorithm; the machine learning algorithm comprises an AdaBoost algorithm.
Specifically, the AdaBoost algorithm is an iterative algorithm, and the core idea is to train different classifiers (weak classifiers) for the same training set, and then assemble the weak classifiers to form a stronger final classifier (strong classifier). The algorithm is a simple weak classification algorithm promotion process, and the classification capability of the data can be improved through continuous training in the process.
And step S300, processing the determined real-time risk assessment data through the trained risk prediction model to obtain the development trend of the epidemic situation in the future preset days.
Specifically, the computer device obtains real-time risk assessment data based on the same calculation principle as that in step S100. The computer equipment processes the real-time risk assessment data through the trained risk prediction model so as to predict and obtain the risk development trend of the epidemic situation in a plurality of days in the future. For example, based on the real-time risk assessment data of the date t, the risk development trend of the epidemic situation on the date t +1 (i.e. the day after) can be predicted based on the step. And then, gradually increasing the real-time risk assessment data sets of corresponding days, and so on, so that the risk development trends of the next day in the future, the third day in the future and the like can be obtained.
From the above, the epidemic situation risk prediction method provided by the embodiment of the application determines the historical risk assessment data associated with the epidemic situation risk through the numerical value dimension, the space density dimension and the population density dimension, so that the risk assessment comprehensiveness is improved. In the aspect of statistics, compared with the prior art that only to the district level, the epidemic situation propagation risk assessment can be carried out through the occupied area of the epidemic situation associated region and the per capita risk degree, the related statistical range is wider, and the finally obtained prediction analysis result can be matched with the actual epidemic situation propagation trend.
In one embodiment, the risk assessment data is determined according to the number of patients, wherein the types of the patients comprise at least one of patients with confirmed illness, patients with high risk, suspected persons with illness, persons with sensitive symptoms, persons who return from high-risk areas in parking and persons who flow into the high-risk areas.
Specifically, in order to make the numerical value have good intelligibility, the relevant personnel can conveniently recognize the numerical value; therefore, in order to make the obtained numerical value accord with the epidemic situation development rule and accurately reflect the processes of epidemic situation outbreak, control and extinction; and, in order to make the values taken comparable between different regions; and, in order to make the obtained numerical values, while maintaining the independence of the respective regions, the influence on the local upper and lower membership relationship can be considered, for example, if a certain prefecture is administered by 6 prefectures, one prefecture is already classified as a high risk region, and the other five prefectures are already classified as low risk regions, the prefecture should be classified as at least a medium risk region.
Therefore, in the current embodiment, the patient types are selected by combining various types of data which are disclosed at present and reflect the epidemic situation control trend, so as to predict the future trend of the epidemic situation.
It can be determined that: (1) the more the number of the patients and the greater the population density, the higher the risk of epidemic spread. (2) The high-risk sick people refer to people who closely contact or have the same line with the confirmed sick people, and the number and population density of the high-risk sick people are positively correlated with the epidemic spread risk. (3) The suspected sick persons refer to the number of the related persons defined according to the suspected diagnosis standard of the national health commission office 'notice of diagnosis and treatment scheme for pneumonia infected by novel coronavirus (fifth edition)' and 'notice of prevention and control scheme for pneumonia infected by novel coronavirus (fourth edition)', and the number and population density of the persons are positively correlated with the risk of spreading epidemic. (4) The sensitive symptom personnel refer to the number of the fever outpatient cases, the online inquiry of an interconnection network platform (containing personnel who purchase fever and cold medicines online), and the like, and the number, the population density and the generation frequency of the sensitive symptom personnel are generally in positive correlation with the epidemic spread risk. (5) The high-risk region parking return personnel refer to the number of personnel returned by local residents from epidemic areas (such as medium and high risk areas), and the higher the epidemic risk degree, the more the personnel number and the higher the population density of the layer parking area, the greater the epidemic spread risk. (6) The inflow of personnel in the high-risk area refers to the quantity of personnel entering the local area from other places, and the influence of the inflow of personnel is consistent with the quantity of personnel returned from the parking in the high-risk area.
It should be noted that the numbers of patients, high-risk patients and suspected patients are generally provided by the health and police departments in various regions. Symptomatic sensitive personnel are typically provided by health departments, internet inquiries, and e-commerce platforms. And calculating and acquiring management data and signaling data of a community (village) management department when the high-risk area stops returning personnel and the inflow quantity of the personnel in the high-risk area. If sensitive data (such as name, identification number and other information) are also involved in each item of data provided above, desensitization processing is also required to be performed on the data, so as to avoid leakage of personal information of the user.
In the embodiment, the data of confirmed patients, suspected patients and isolators are adopted, and the related analysis data is more comprehensive based on cross-region personnel flow and internet inquiry data, so that the data analysis from multiple angles is ensured, and the accuracy of the risk prediction result is improved.
In one embodiment, the determining the historical risk assessment index value by combining the numerical dimension, the spatial density dimension and the population density dimension in step S100 includes:
step S1001, a range method is adopted to calculate to obtain a first target current value according to a value set which is obtained in a numerical value dimension in the past of the number of patients and a first initial current value which is obtained in the numerical value dimension in the present of the number of patients and is determined according to an epidemic situation spreading trend.
It should be noted that (1) the range method usually refers to using the maximum value minus the minimum value in a set of data, and aims to observe the interval span between the maximum observed value and the minimum observed value of the variable. (2) When the number of patients is determined, if the type of the related patient is determined to be sick personnel, high-risk sick personnel or suspected sick personnel, the activity track of the type of the patient within 14 days is matched to the community (village), so that the number of the diagnosed patients, the number of the high-risk personnel or the number of the suspected personnel corresponding to the community (village) involved in each day is calculated. (3) And if the type of the concerned patient is the sensitive symptom personnel, the address of the sensitive symptom personnel on the current day is matched to the community (village), so that the number of the sensitive symptom personnel in the concerned community (village) is calculated. (4) If the type of the related patient is the high-risk region parking return personnel and the high-risk region personnel inflow, determining the risk coefficient of the epidemic situation of each country and city through the global epidemic situation data, analyzing the quantity of the personnel of residents from different risk countries and cities after parking in each community (village), and analyzing the quantity of the personnel of the different risk countries and cities in each community (village) (the personnel of the different risk countries and the cities are previously resident in the local region outside the local region).
Step S1002, calculating to obtain a second target current value by adopting a range method according to a value set which is acquired in the space density dimension by the number of patients in the past and a second initial current value which is determined according to the first target current value and the area correspondence of the relevant adjacent area.
Specifically, the second initial current value a may be obtained by further calculating a division result between the first target current value B and the area C of the associated adjacent area. When carrying out range calculation, the computer equipment firstly screens out corresponding maximum values and minimum values from the value sets which are obtained in the space density dimension in the past by the number of patients; and then, substituting the maximum obtained value, the minimum obtained value and the second initial current value into a preset range calculation formula (the specific calculation formula may refer to the formula (3), and certainly, in different embodiments, the formula (3) may also be deformed to adapt to different calculation requirements), so as to calculate to obtain a second target current value.
Step S1003, calculating to obtain a third target current value by adopting a range method according to a value set which is acquired by the number of patients in the past in the population density dimension and a third initial current value which is determined according to the first target current value and the number of the standing population of the associated adjacent area.
Specifically, the third initial current value D is calculated based on the first target current value E and the result of the division between the first target current value E and the number F of the permanent population of the associated adjacent area (for example, D is calculated based on the result of the division of "E/F", in other embodiments, D may also be calculated based on a modified form of the above formula, which is not limited in this embodiment of the present application). The calculation principle of the current value of the third target may refer to the embodiment disclosed in step S1002, which is not described in more detail in this application.
Step S1004, performing weighted calculation on the obtained first target current value, second target current value, and third target current value, and determining a historical risk assessment index value based on the obtained weighted calculation result.
Specifically, for each patient type, the computer device performs value calculation from the numerical quantity, the spatial density and the population density three-dimensional dimensions, and if the value calculation is performed on the numerical quantity, the spatial density and the population density three-dimensional dimensions, the calculation of the specific score is performed. That is, in the case of a calculation method in which an index of any patient type (e.g., diagnosed patient) is known, other indices of parking return staff, such as high-risk areas, can be further obtained based on the calculation method.
In one embodiment, the sum score X is calculated for patients with confirmed diagnosis 1 (i.e., the historical risk assessment index value corresponding to the confirmed patient), the following weighted calculation formula may be referred to:
X 1 =ω m X 1,m +ω a X 1,a +ω p X 1,p ; (4)
wherein, w m 、w a 、w p The weighting coefficients of the factors of the confirmed patients in the risk values of three dimensions of numerical value, space density and population density are respectively. X 1,m Numerical scores for patients confirmed in the corresponding Community (village), X 1,a Score in spatial density dimension, X, for confirmed patients in the corresponding Community (village) 1,p The scores of the patients diagnosed in the corresponding community (village) in the population density dimension are determined.
It should be noted that, with reference to the above-mentioned method for evaluating risk in a community (village), the risk index of the statistical unit such as a street (village and town), a district (county), a city, etc. may also be calculated step by step, and the calculation process in the embodiment of the present application is not limited to a lot.
In the above embodiment, in terms of calculation, the present application quantitatively characterizes by indexes, and performs risk assessment from several analysis dimensions of numerical values, spatial density and population density, thereby improving the comprehensiveness of analysis. In the aspect of statistics, compared with the prior art that only the county level is reached, streets (towns) and even communities (villages) can be used as statistical units, the related statistical range is wider, and the finally obtained prediction analysis result can be matched with the actual spreading trend of epidemic situations.
In one embodiment, in step S1001, the first initial current value is determined through the following steps:
step S10011, based on the change rule of epidemic propagation risk with time attenuation, determining the overall risk propagation coefficient lambda (t) by the following formula (1):
wherein, beta 0 Is 0 to t 0 A first attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; beta is a 1 Is t 0 ~t 1 A second attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; t is the number of days between the current date and the date that the person to be examined has confirmed a disease, t 0 Days required for the overall Risk propagation coefficient to begin to decrease faster, t 1 The number of days required for the overall risk spread coefficient to drop to 0.
It should be noted that, for example, new coronary pneumonia is similar to other traditional infectious diseases, and has corresponding transmission rules. At present, strict, timely and effective control measures are adopted in epidemic situation prevention and control in China, and it can be determined that epidemic situation propagation risks generated by patients, suspected persons and high-risk persons who are diagnosed can be attenuated along with time until the epidemic situation propagation risks are reduced to 0. Based on this rule, the present application defines the above formula (1), and determines risk propagation coefficients of diagnosed patients, suspected persons, and high-risk persons based on the formula (1). Wherein, according to the prior medical statistical experience, the parameter t 0 Usually the value is 7, parameter t 1 Usually the value 14, parameter β 0 Is generally greater than the parameter beta 1 。
Step S10012, according to the overall risk propagation coefficient lambda (t), the predefined neighboring community (village) risk propagation coefficient lambda (t) neighbor The determined number of patients in the target community (village) generated each day and the number of patients in the adjacent community (village) associated with the target community (village) generated each day are calculated by the following formula (2) to obtain a first initial current value:
wherein, X 1,m A first initial current value is taken for a corresponding disease type m of a community (village) in a numerical value dimension, N is the total number of adjacent communities, and M (t) isThe number of patients produced in the target community (village) at the t day, and M (t, i) is the number of patients produced in the i community (village) associated with the target community (village) at the t day.
Specifically, taking the calculation of the risk score of the diagnosed patient in numerical quantity as an example, the calculation principle of the above formula is: the computer equipment defines the propagation coefficient lambda of adjacent community neighbor . Then, the number of patients diagnosed in the community (village) per day is multiplied by the propagation coefficient of the adjacent community (village) to be matched with the adjacent community (village) (namely, the adjacent community (village) with the propagation risk is accurately positioned). Then, integrating the number M (t) of patients confirmed by the community (village) and the number M (t, i) of patients confirmed by the adjacent community (village) positioned by the community (village), and combining the risk propagation coefficients lambda (t) and lambda (lambda) neighbor Obtaining the risk score X of the community (village) confirmed patients on numerical quantity through the formula (2) 1,m 。
In one embodiment, in step S1001, the first target current value is obtained by the following calculation:
step S10011, determining a maximum value according to a value set which is acquired in numerical value dimensions in the past by the number of patientsAnd minimum already-valued
Specifically, the computer device may screen out the corresponding maximum value and the minimum value from the value set based on a bubble sorting method, a simple selection sorting method, and the like. Since the above sorting methods are all the prior art, the embodiments of the present application do not limit this too much.
Step S10012, determining a first initial current value X 1,m Maximum value already takenAnd minimum already-valuedSubstituting into the following range calculation formula (3), and calculating to obtain the corresponding first target current value
It should be noted that, for the calculation methods of the second target current value and the third target current value, reference may also be made to steps S10011 to S10012 in this embodiment, for example, when obtaining the second target current value, a calculation formula that may be referred to includes:wherein,a minimum and a maximum already-determined value, X, determined on the basis of the respective value sets 1,a And the second initial current value is determined correspondingly.
In one embodiment, in step S200, the constructing a training sample set according to the historical risk assessment data, and performing risk prediction model training with a preset machine learning algorithm includes:
step S2001, carrying out weighted calculation on historical risk evaluation data related to a plurality of different patient types to obtain an epidemic situation current situation risk evaluation index of a community (village).
Specifically, when the types of patients include 6 types, namely, patients with confirmed illness, patients with high risk, suspected illness, sensitive symptoms, high-risk area parking return personnel, and high-risk area personnel, historical risk assessment data X corresponding to each type of patient is obtained according to the steps S1001 to S1004 1 ~X 6 Then, the epidemic situation current situation risk index of the community (village) is obtained according to the following formula:
wherein f is i For the influence weight of each factor index on the epidemic situation status risk index, when the initial historical data is less, the experience can determine that f 1 ~f 6 Respectively 0.3, 0.2, 0.1. Along with the continuous accumulation of data, the weighting accuracy of each index can be continuously improved through the gradual iteration of the AdaBoost machine learning algorithm.
Step S2002, a training sample set is constructed according to the historical risk assessment data with the generation date t and the epidemic situation status risk assessment index with the generation date t + 1.
Specifically, for the community (village) m, 6 risk factors of the date t are selectedAnd epidemic situation status risk assessment index R of date t +1 m,t+1 Form a training sample set (X) m,t ,R m,t+1 ). Then for all communities (villages), the formed training sample set is:
T={(X 1,t ,R 1,t+1 ),...,(X i,t ,R i,t+1 ),...,(X M,t ,R M,t+1 )}; (6)
where M is the total number of all communities (villages).
And step S2003, performing model training by using an AdaBoost algorithm, taking a trend risk coefficient set for the historical risk assessment data with the date t as an estimation object in the training process, and performing parameter estimation by gradually increasing training sample sets with different days.
And step S2004, when the estimated trend risk coefficient meets the training end condition, obtaining a trained risk prediction model.
Specifically, if order:
where ω is set to the corresponding risk factor X i,t The trend risk coefficient of (i ═ 1.,. M), then, has y ═ X ω, where ω will be solved based on this formula during the training process. In one embodiment, the computer device performs parameter estimation by gradually increasing sample sets of different days, and ends iteration when it is determined that the value of ω gradually converges and is fixed, so as to obtain the trained risk prediction model.
In one embodiment, prior to determining the risk assessment data, the method further comprises: acquiring basic information of an administrative district, wherein the basic information comprises at least one of vector image layer data and human mouth cardinality information, and the administrative district comprises at least one of a community (village), a street (village and town) and a region; and performing spatial positioning on the risk assessment data based on the basic information of the administrative division.
Specifically, the population base is a concept of demographics, that is, a basic amount of the population used when the statistical population changes, and on the basis of the basic amount, the change of the population, such as the growth rate and the growth amount, is calculated. The same growth rate, if population cardinality is large, the calculated amount of growth is high. Simply stated, the population before change.
In one embodiment, population base information can be obtained through a local government's yearbook channel, community (village) management channel, census related efforts, and telecommunications carrier signaling. Wherein, the related positioning precision is only required to be in the community (village).
In one embodiment, the computer device can also perform multidimensional display on the current situation analysis result, the risk prediction analysis result, and other analysis results in combination with the visual and visual characteristics of the GIS, for example, the computer device can operate according to different levels of statistical units such as provinces (cities), districts (counties), streets (towns), and communities (villages) based on the time and space dimension query, browse, and statistical analysis functions provided by the GIS (Geographic Information systems), and provide a change display of the time axis (days, weeks, months, and so on) for different statistical units. For example, the computer device may also provide thematic map display functions such as hierarchical coloring, histogram, pie chart, and the like based on the thematic map function provided by the GIS. For another example, the computer device may also display the corresponding analysis results on the visual interface in an ordered or reversed order according to the ranking order of different levels such as a district (county), a street (town), a community (village) and the like based on the ordered query display function provided by the GIS.
In one embodiment, taking the experimental research area in XX as an example, it should be noted that the total area of the district in XX is 1.XX ten thousand square kilometers, and XX districts, xxx streets (towns) and xxxx communities (villages) are under the district. The population base number in each related statistical unit is obtained by combining XX mobile, XX communication and XX telecommunication three-home telecommunication carrier data and XX city statistical yearbook population data in a fusion manner. The population data of the telecom operator is obtained by a relevant calculation model according to parameters such as regional base station parameters, daily stay time, monthly stay days, annual stay months and the like; on the basis, checking and optimizing are carried out by utilizing the population data of the annual statistics book, and then the population base number of each statistical unit is calculated.
In the present embodiment, the actual conditions of the XX region are combined with the actual conditions of the β in the formula (1) 0 And beta 1 Comparing and analyzing the rationality of the damping system through different value combinations, fitting the damping law to the maximum extent, and finally respectively taking 0.8 and 0.6; for λ in equation (2) neighbor The initial value is iteratively optimized by 0.5; for ω in equation (4) m 、ω a 、ω p Iteration is carried out by respectively taking 0.4, 0.3 and 0.3 as initialization values; the value for ω in equation (7) will end up by iterating: ω T ═ 0.9541.0381.0162.9842.0312.033]。
Please refer to fig. 2, which shows the variation trend of the high and medium epidemic risk number in the streets (towns) and communities (villages) in 2020, 4, 15. Since the epidemic situation, until 1 month and 15 days in 2021, the XX market epidemic situation status risk index change curve has three peaks which respectively correspond to three wave epidemic situations before and after 2-4 months, 6-7 months and 2021 year's day of New year (as shown in FIG. 3); numerically, the relative burst, violence of the second wave; from the control effect, the last two times are relatively shorter than the first duration period, and the third time is relatively stable, which indirectly reflects the value of accumulated treatment coping experience.
In summary, in the embodiment of the application, XX is used as a research area, the sample time is from 2020 to 2021, 2 months to 2021 months, the space range covers streets (towns) and communities (villages) in XX, and the samples have good breadth and depth in time and space dimensions.
Referring to fig. 4, an epidemic risk assessment system 400 provided in the embodiment of the present application includes a data processing module 401, a model training module 402, and a risk prediction module 403, where:
the data processing module 401 is configured to determine historical risk assessment data associated with epidemic situation risks in combination with a numerical dimension for reflecting the number of risk assessment factors, a spatial density dimension for reflecting the risk degree of the corresponding statistical epidemic situation-associated area in the floor area, and a population density dimension for reflecting the per-capita risk degree of the corresponding epidemic situation-associated area.
The model training module 402 is configured to construct a training sample set according to the historical risk assessment data, and train a risk prediction model according to a preset machine learning algorithm; the machine learning algorithm includes an AdaBoost algorithm.
The risk prediction module 403 is configured to process the determined real-time risk assessment data through the trained risk prediction model to obtain a development trend of the epidemic situation in the future preset days.
In one embodiment, the risk assessment data is determined according to the number of patients, wherein the types of the patients comprise at least one of confirmed sick people, high-risk sick people, suspected sick people, sensitive people, high-risk area parking return people and high-risk area personnel inflow.
In one embodiment, the data processing module 401 is further configured to calculate, according to a value set that the number of patients has been taken in a numerical value dimension in the past and a first initial current value that the number of patients determined according to the epidemic situation propagation trend is taken in the numerical value dimension at present, a first target current value by using a range method; calculating to obtain a second target current value by adopting a range method according to a value set which is acquired in the space density dimension by the number of patients in the past and a second initial current value which is determined according to the first target current value and the area correspondence of the relevant adjacent area; calculating to obtain a third target current value by adopting a range method according to a value set which is acquired in a population density dimension in the past by the number of patients and a third initial current value which is determined according to the first target current value and the number of the standing population of the associated adjacent area; and performing weighted calculation on the obtained first target current value, the second target current value and the third target current value, and determining a historical risk evaluation index value based on the obtained weighted calculation result.
In one embodiment, the data processing module 401 is further configured to determine the overall risk propagation coefficient λ (t) based on a change rule of the epidemic propagation risk with time through the following formula (1):
wherein, beta 0 Is 0 to t 0 A first attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; beta is a 1 Is t 0 ~t 1 A second attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; t is the number of days between the current date and the date that the patient is confirmed by the person to be examined, t 0 Days required to start an accelerated decrease in the overall risk spread coefficient, t 1 The number of days required for the overall risk spread coefficient to fall to 0;
predefining according to the overall risk propagation coefficient lambda (t)Adjacent community (village) risk propagation coefficient lambda of neighbor And calculating a first initial current value by the following formula (2) according to the determined number of the patients generated in the target community (village) every day and the number of the patients generated in the adjacent community (village) associated with the target community (village):
wherein, X 1,m Obtaining a first initial current value of a corresponding patient type M of a community (village) in a numerical value dimension, wherein N is the total number of adjacent communities, M (t) is the number of patients in a target community (village) on the t day, and M (t, i) is the number of patients in an i community (village) associated with the target community (village) on the t day.
In one embodiment, the data processing module 401 is further configured to determine the maximum value according to the past value set that has been obtained in the numerical dimension according to the number of patientsAnd minimum already-valuedThe determined first initial current value X is taken as a value 1,m Maximum value already takenAnd minimum taken valueThe current value of the corresponding first target is obtained by calculation by substituting the current value into the following range calculation formula (3)
In one embodiment, the model training module 402 is further configured to perform a weighted calculation on historical risk assessment data related to a plurality of different patient types to obtain an epidemic situation status risk assessment index of a community (village); constructing a training sample set according to historical risk assessment data with a generation date of t and epidemic situation current situation risk assessment indexes with a generation date of t + 1; performing model training by using an AdaBoost algorithm, taking a trend risk coefficient set for the historical risk assessment data with the date t as an estimation object in the training process, and performing parameter estimation by gradually increasing training sample sets with different days; and obtaining a trained risk prediction model when the estimated trend risk coefficient meets the training end condition.
In one embodiment, the system 400 further comprises a data preprocessing module, wherein:
the data preprocessing module is used for acquiring basic information of an administrative division, wherein the basic information comprises at least one of vector graph layer data and population base information, and the administrative division comprises at least one of communities (villages), streets (villages and towns) and regions; and carrying out space positioning on the risk assessment data based on the basic information of the administrative division.
Therefore, according to the epidemic situation risk prediction system provided by the embodiment of the application, the historical risk assessment data associated with the epidemic situation risk is determined through the numerical value dimension, the space density dimension and the population density dimension, and the risk assessment comprehensiveness is improved. In the aspect of statistics, compare in prior art only to district and county level, this application also can carry out epidemic situation propagation risk assessment through the area in epidemic situation associated region and per capita risk degree, and the statistical range that relates to is wider for the prediction analysis result that finally obtains can with the actual propagation trend phase-match of epidemic situation.
The embodiment of the present application provides a storage medium, and when being executed by a processor, the computer program performs the method in any optional implementation manner of the foregoing embodiment. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM-Only Memory), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (6)
1. An epidemic risk prediction method is characterized by comprising the following steps:
determining historical risk evaluation data associated with the epidemic risk by combining a quantity numerical dimension for reflecting the quantity of the risk evaluation factors, a space density dimension for reflecting the risk degree of the corresponding statistical epidemic situation associated region on the occupied area and a population density dimension for reflecting the per-capita risk degree of the corresponding epidemic situation associated region;
constructing a training sample set according to the historical risk assessment data, and training a risk prediction model by using a preset machine learning algorithm; the machine learning algorithm comprises an AdaBoost algorithm;
processing the determined real-time risk assessment data through the trained risk prediction model to obtain the development trend of the epidemic situation in the future preset days;
the risk assessment data is determined according to the number of patients, wherein the types of the patients comprise at least one type of confirmed sick personnel, high-risk sick personnel, suspected sick personnel, sensitive symptom personnel, high-risk area parking return personnel and high-risk area personnel inflow;
determining a historical risk assessment index value in combination with the numerical dimension, the spatial density dimension, and the population density dimension, comprising:
calculating to obtain a first target current value by adopting a range method according to a value set which is obtained in a numerical value dimension in the past by the number of patients and a first initial current value which is obtained in the numerical value dimension at present by the number of patients and is determined according to an epidemic situation propagation trend;
calculating to obtain a second target current value by adopting a range method according to a value set which is acquired in the past by the number of patients in the spatial density dimension and a second initial current value which is determined according to the first target current value and the area correspondence of the relevant adjacent area;
calculating to obtain a third target current value by adopting a range method according to a value set which is acquired in a population density dimension in the past by the number of patients and a third initial current value which is determined according to the first target current value and the number of the standing population of the associated adjacent area;
performing weighted calculation on the obtained first target current value, second target current value and third target current value, and determining a historical risk assessment index value based on the obtained weighted calculation result;
the first initial current value is determined by the following steps:
based on the change rule of the epidemic propagation risk with the time attenuation, the overall risk propagation coefficient lambda (t) is determined by the following formula (1):
wherein, beta 0 Is 0 to t 0 A first attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; beta is a 1 Is t 0 ~t 1 A second attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; t is the number of days between the current date and the date that the person to be examined confirms the patient, t 0 Days required for the overall risk spread coefficient to start to decrease rapidly, t 1 The number of days required for the overall risk spread coefficient to fall to 0;
according to the overall risk propagation coefficient lambda (t) and the predefined adjacent community (village) risk propagation coefficient lambda (t) neighbor The number of the patients generated in each day in the determined target community (village) and the number of the patients generated in each day in the adjacent community (village) associated with the target community (village) are calculated by the following formula (2)Taking values:
wherein, X 1,m The method comprises the steps of obtaining a first initial current value of a corresponding disease type M of a community (village) in a numerical dimension, wherein N is the total number of adjacent communities, M (t) is the number of patients in a target community (village) on the t th day, and M (t, i) is the number of patients in an i community (village) associated with the target community (village) on the t th day.
2. The method of claim 1, wherein the first target current value is calculated by:
determining the maximum value according to the value set which is acquired in the numerical value dimension in the past according to the number of patientsAnd minimum already-valued
The determined first initial current value X is taken as a value 1,m Maximum already-valuedAnd minimum already-valuedThe current value of the corresponding first target is obtained by calculation by substituting the current value into the following range calculation formula (3)
3. The method according to claim 1, wherein the constructing a training sample set according to the historical risk assessment data and performing the training of the risk prediction model with a preset machine learning algorithm comprises:
carrying out weighted calculation on historical risk evaluation data related to a plurality of different patient types to obtain an epidemic situation current situation risk evaluation index of a community (village);
constructing a training sample set according to historical risk assessment data with a generation date of t and epidemic situation current situation risk assessment indexes with a generation date of t + 1;
performing model training by using an AdaBoost algorithm, taking a trend risk coefficient set for the historical risk assessment data with the date t as an estimation object in the training process, and performing parameter estimation by gradually increasing training sample sets with different days;
and obtaining a trained risk prediction model when the estimated trend risk coefficient meets the training end condition.
4. The method of any one of claims 1-3, wherein prior to determining risk assessment data, the method further comprises:
acquiring basic information of an administrative district, wherein the basic information comprises at least one of vector graphics layer data and population cardinality information, and the administrative district comprises at least one of a community (village), a street (village and town) and a region;
and carrying out spatial positioning on the risk assessment data based on the basic information of the administrative division.
5. The epidemic situation risk assessment system is characterized by comprising a data processing module, a model training module and a risk prediction module, wherein:
the data processing module is used for determining historical risk evaluation data associated with the epidemic situation risk by combining a numerical value dimension for reflecting the number of the risk evaluation factors, a space density dimension for reflecting the risk degree of the corresponding statistical epidemic situation associated region on the occupied area and a population density dimension for reflecting the average human risk degree of the corresponding epidemic situation associated region;
the model training module is used for constructing a training sample set according to the historical risk assessment data and training a risk prediction model by using a preset machine learning algorithm; the machine learning algorithm comprises an AdaBoost algorithm;
the risk prediction module is used for processing the determined real-time risk evaluation data through a trained risk prediction model to obtain the development trend of the epidemic situation in the future preset days;
the risk assessment data is determined according to the number of patients, wherein the types of the patients comprise at least one type of confirmed sick personnel, high-risk sick personnel, suspected sick personnel, sensitive symptom personnel, high-risk area parking return personnel and high-risk area personnel inflow;
determining a historical risk assessment index value in combination with the numerical dimension, the spatial density dimension, and the population density dimension, comprising:
calculating to obtain a first target current value by adopting a range method according to a value set which is obtained in a numerical value dimension in the past by the number of patients and a first initial current value which is obtained in the numerical value dimension at present by the number of patients and is determined according to an epidemic situation propagation trend;
calculating to obtain a second target current value by adopting a range method according to a value set which is acquired in the space density dimension by the number of patients in the past and a second initial current value which is determined according to the first target current value and the area correspondence of the relevant adjacent area;
calculating to obtain a third target current value by adopting a range method according to a value set which is acquired in a population density dimension in the past by the number of patients and a third initial current value which is determined according to the first target current value and the number of the standing population of the associated adjacent area;
performing weighted calculation on the obtained first target current value, second target current value and third target current value, and determining a historical risk assessment index value based on the obtained weighted calculation result;
the first initial current value is determined by the following steps:
based on the change rule of the epidemic propagation risk with the time attenuation, the overall risk propagation coefficient lambda (t) is determined by the following formula (1):
wherein, beta 0 Is 0 to t 0 A first attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; beta is a 1 Is t 0 ~t 1 A second attenuation coefficient of the epidemic propagation risk attenuating with time in the time phase; t is the number of days between the current date and the date that the person to be examined confirms the patient, t 0 Days required for the overall Risk propagation coefficient to begin to decrease faster, t 1 The number of days required for the overall risk spread coefficient to fall to 0;
according to the overall risk propagation coefficient lambda (t) and the predefined adjacent community (village) risk propagation coefficient lambda (t) neighbor The number of patients generated every day in the determined target community (village) and the number of patients generated every day in the adjacent community (village) associated with the target community (village) are calculated by the following formula (2) to obtain a first initial current value:
wherein, X 1,m The method comprises the steps that a first initial current value is taken by a corresponding patient type M of a community (village) in a numerical value dimension, N is the total number of adjacent communities, M (t) is the number of patients in a target community (village) on the t th day, and M (t, i) is the number of patients in an i community (village) associated with the target community (village) on the t th day.
6. A readable storage medium, comprising an epidemic risk assessment method program, which when executed by a processor, performs the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111522302.1A CN114334172B (en) | 2021-12-13 | 2021-12-13 | Epidemic situation risk assessment method, system and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111522302.1A CN114334172B (en) | 2021-12-13 | 2021-12-13 | Epidemic situation risk assessment method, system and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114334172A CN114334172A (en) | 2022-04-12 |
CN114334172B true CN114334172B (en) | 2022-09-02 |
Family
ID=81050993
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111522302.1A Active CN114334172B (en) | 2021-12-13 | 2021-12-13 | Epidemic situation risk assessment method, system and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114334172B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114912354B (en) * | 2022-05-07 | 2024-07-02 | 吉林大学 | Method, device and medium for predicting mosquito vector infectious disease risk |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111524611A (en) * | 2020-04-24 | 2020-08-11 | 腾讯科技(深圳)有限公司 | Method, device and equipment for constructing infectious disease trend prediction model |
CN112164472A (en) * | 2020-09-25 | 2021-01-01 | 江苏鑫合易家信息技术有限责任公司 | Infectious disease infection risk prediction system and method |
AU2021102217A4 (en) * | 2021-04-27 | 2021-06-17 | Aalam, Shamsher MR | A technique to refine an mapping and modelling pest and disease spread |
CN113161004A (en) * | 2020-07-15 | 2021-07-23 | 泰康保险集团股份有限公司 | Epidemic situation prediction system and method |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101794342B (en) * | 2009-09-30 | 2015-09-09 | 中国人民解放军防化指挥工程学院 | A kind of epidemic Forecasting Methodology based on considering quarantine measures |
CN108172301B (en) * | 2018-01-31 | 2021-02-02 | 中国科学院软件研究所 | Mosquito-borne infectious disease epidemic situation prediction method and system based on gradient lifting tree |
CN111128399B (en) * | 2020-03-30 | 2020-07-14 | 广州地理研究所 | Epidemic disease epidemic situation risk level assessment method based on people stream density |
CN111680830B (en) * | 2020-05-25 | 2024-01-26 | 广州衡昊数据科技有限公司 | Epidemic situation prevention method and device based on aggregation risk early warning |
CN111768873A (en) * | 2020-06-03 | 2020-10-13 | 中国地质大学(武汉) | COVID-19 real-time risk prediction method |
CN113517075A (en) * | 2021-06-25 | 2021-10-19 | 联通(广东)产业互联网有限公司 | Infectious disease dynamics-based infectious disease prediction method, system and medium |
CN113689959B (en) * | 2021-08-25 | 2024-04-05 | 深圳平安智慧医健科技有限公司 | Epidemic situation prevention and control decision method, device, equipment and medium based on artificial intelligence |
CN113744890A (en) * | 2021-11-03 | 2021-12-03 | 北京融信数联科技有限公司 | Reworking and production-resuming analysis method, system and storage medium |
-
2021
- 2021-12-13 CN CN202111522302.1A patent/CN114334172B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111524611A (en) * | 2020-04-24 | 2020-08-11 | 腾讯科技(深圳)有限公司 | Method, device and equipment for constructing infectious disease trend prediction model |
CN113161004A (en) * | 2020-07-15 | 2021-07-23 | 泰康保险集团股份有限公司 | Epidemic situation prediction system and method |
CN112164472A (en) * | 2020-09-25 | 2021-01-01 | 江苏鑫合易家信息技术有限责任公司 | Infectious disease infection risk prediction system and method |
AU2021102217A4 (en) * | 2021-04-27 | 2021-06-17 | Aalam, Shamsher MR | A technique to refine an mapping and modelling pest and disease spread |
Also Published As
Publication number | Publication date |
---|---|
CN114334172A (en) | 2022-04-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zou et al. | Mining Twitter data for improved understanding of disaster resilience | |
Fisher et al. | Modelling the errors in areal interpolation between zonal systems by Monte Carlo simulation | |
DiGaetano | Sample frame and related sample design issues for surveys of physicians and physician practices | |
Greenough et al. | Beyond mapping: a case for geospatial analytics in humanitarian health | |
Earnest et al. | Spatial analysis of ambulance response times related to prehospital cardiac arrests in the city-state of Singapore | |
CN114334172B (en) | Epidemic situation risk assessment method, system and readable storage medium | |
Vaitla et al. | Big Data and the Well-being of women and girls: Applications on the Social Scientific Frontier | |
Luo | Analyzing potential spatial access to primary care services with an enhanced floating catchment area method | |
Spirandelli et al. | Improving adaptation planning for future sea-level rise: understanding uncertainty and risks using a probability-based shoreline model | |
Adeoye et al. | Bayesian disease mapping and the ‘High‐Risk’oral cancer population in Hong Kong | |
Grekousis et al. | Analyzing high-risk emergency areas with GIS and neural networks: The case of Athens, Greece | |
WO2017083568A1 (en) | Estimating or forecasting health condition prevalence in a definable area and associated costs and return on investment of interventions | |
Krivoruchko et al. | Statistical tools for regional data analysis using GIS | |
Carley et al. | BioWar: Scalable multi-agent social and epidemiological simulation of bioterrorism events | |
Horn et al. | Population mobility data provides meaningful indicators of fast food intake and diet-related diseases in diverse populations | |
Zhang et al. | Hierarchies in the Decentralized Welfare State: Prioritization in the Housing Choice Voucher Program | |
Al_Sayed et al. | On the nature of urban dependencies: How Manhattan and Barcelona reinforced a natural organisation despite planning intentionality | |
CN110633890A (en) | Land utilization efficiency judgment method and system | |
Han et al. | Creditprint: Credit investigation via geographic footprints by deep learning | |
Xiao et al. | Crime exposure along my way home: estimating crime risk along personal trajectory by visual analytics | |
Bastin et al. | Spatial aspects of MRSA epidemiology: a case study using stochastic simulation, kernel estimation and SaTScan | |
Chen et al. | Deep Learning–Based Assessment of Built Environment From Satellite Images and Cardiometabolic Disease Prevalence | |
Masters et al. | Measuring multiple dimensions and indices of nonvaccination clustering in Michigan, 2008–2018 | |
Delmelle et al. | Introduction: Spatial analysis and health | |
Kang et al. | COVID-19 Vaccine Rollout Plans Should Consider Spatial Distribution of Age-Specific Population |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |