CN111695048B - Epidemic situation tracing method and medium - Google Patents
Epidemic situation tracing method and medium Download PDFInfo
- Publication number
- CN111695048B CN111695048B CN202010387822.5A CN202010387822A CN111695048B CN 111695048 B CN111695048 B CN 111695048B CN 202010387822 A CN202010387822 A CN 202010387822A CN 111695048 B CN111695048 B CN 111695048B
- Authority
- CN
- China
- Prior art keywords
- data
- time
- places
- screened
- infection
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention relates to an epidemic situation tracing method and medium, the method comprises: data acquisition is carried out on the person with the confirmed infection, and the person with the confirmed infection and the infection source are firstly infected; constructing three-dimensional coordinates to form three-dimensional panel data; predicting the three-dimensional panel data by a machine learning method to complete the completion of the three-dimensional panel data; performing space geographic analysis, and calculating corresponding local autocorrelation coefficients of a plurality of places; and accurately screening the initial infection sources according to the places and the corresponding local autocorrelation coefficients until the screened initial infection sources are lower than a set threshold value, and visually displaying the screened initial infection sources. The beneficial effects of the invention are as follows: based on the technical means of space geographic analysis and machine learning, big data and small data are combined, and epidemic situation is traced from microscopic to macroscopic.
Description
Technical Field
The invention belongs to the field of computer data processing, and particularly relates to an epidemic situation tracing method and medium.
Background
The epidemic situation traceability in the prior art is analyzed by collecting data such as images, videos and human body temperature through equipment such as collecting equipment and sensors, and the technical scheme is very limited, and the epidemic situation traceability can only be collected and analyzed through a place provided with the device, and can not be traced according to the action track of epidemic carriers.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art, provides an epidemic situation tracing method and medium, and realizes accurate tracing of an epidemic situation by technical means based on spatial geographic analysis and machine learning.
The technical scheme of the invention comprises an epidemic situation tracing method, which is characterized by comprising the following steps: s100, corresponding data acquisition is carried out on the places, the stay time and the suspected infected persons visited by a plurality of the diagnosed infected persons within the set time, and corresponding first infected persons and corresponding first infection sources are determined according to the acquired data; s200, constructing three-dimensional coordinates according to the S100, and forming three-dimensional panel data taking the place, the residence time and the first infected person number as coordinates; s300, predicting the three-dimensional panel data through a machine learning method to obtain the number of first infectors in one or more places of a definite infected person in the missing time, and completing the completion of the three-dimensional panel data; s400, performing spatial geographic analysis, specifically, calculating corresponding local autocorrelation coefficients of a plurality of places; s500, accurately screening the first infection sources according to the sites and the corresponding local autocorrelation coefficients until the number of the screened first infection sources is lower than a set threshold value, and visually displaying the screened first infection sources.
According to the epidemic situation tracing method, S100 further includes: identifying suspected infected persons at corresponding places according to the places where the infected persons are visited in the set time or more, the stay time and the suspected infected persons; specifically, if the suspected infected person is diagnosed, repeating the step S100 to complete data acquisition when the diagnosed suspected infected person is used as the diagnosed infected person; if the suspected infected person is not diagnosed, the diagnosed infected person in S100 is taken as a first infected person, and the site is taken as a first infection source.
According to the epidemic situation tracing method, the set time and the residence time are set according to epidemic disease characteristics, specifically, the epidemic disease characteristics comprise a latency period and an in-vitro survival period, the set time is set according to the latency period, and the residence time is set according to the in-vitro survival period.
According to the epidemic situation tracing method, S200 specifically includes: s210, dividing the residence time corresponding to a plurality of diagnosed infecting persons into a plurality of equal-size time periods, and counting the number of first infecting persons at the corresponding place of each time period of the diagnosed infecting persons; s220, constructing three-dimensional panel data by taking the residence time as an X axis, taking a time period as an X axis scale, taking a place as a Y axis and taking the number of first infected persons as a Z axis.
According to the epidemic situation tracing method, S300 specifically includes: predicting the three-dimensional panel deletion by using a model comprising, but not limited to, a simple exponential smoothing method, a Holt-WINTERS seasonal predictive model, an autoregressive moving average model, a naive method, a simple averaging method, a moving average method and a time sequence machine learning algorithm, and predicting to obtain first infection sources and corresponding first infection numbers at different positions of a deletion time point.
According to the epidemic situation tracing method, the prediction specifically comprises positive prediction and negative prediction; the forward prediction is to forward sequence the data along a time sequence, take the data continuously existing before the time point of the missing value data as training and verification data, and predict the data of the missing value time point; the negative prediction is to sort the data along the time sequence in the negative direction, take the data continuously existing after the time point of the missing value data as training and verification data, predict the time point data of the missing value, and finally obtain the average value of the positive and negative prediction values as the missing value.
According to the epidemic situation tracing method, S400 specifically includes: and calculating local autocorrelation coefficients and the number of the local autocorrelation coefficients between adjacent places, and accurately screening infection sources according to the local autocorrelation coefficients and the number of the local autocorrelation coefficients, wherein the local autocorrelation coefficients are calculated through Moran I indexes and Geary C indexes, and the weight values of the adjacent places can be set in a self-defined mode.
According to the epidemic situation tracing method, the precise screening specifically comprises the following steps: screening a data set with a set local positive correlation coefficient, comparing a plurality of elements in a subset of the screened data set, and screening out corresponding places with the largest local autocorrelation coefficient in each time period one by one until the places with the largest local autocorrelation coefficient cannot be screened out, and then skipping to the next time period for searching, wherein the screened places are not repeated; screening a data set with a set local negative correlation coefficient, comparing a plurality of elements in a subset of the screened data set, and screening out corresponding places with the minimum local autocorrelation coefficient but not 0 in each time period one by one until places with the minimum local autocorrelation coefficient but not 0 cannot be screened out, and then skipping to the next time period for searching, wherein the screened places are not repeated; screening and setting a data set which is not locally related, selecting all places in the screened data set as a first infection source of the current moment point, and further jumping to the next time period for searching, wherein the screened places are not repeated; selecting the intersection of a plurality of location sets in the earliest time period as an infection source; and if the number of the infection sources is lower than the set value, outputting a screening subset, and if the number of the infection sources is higher than the set value, repeatedly executing the space geographic analysis and the accurate tracing step on the screened data set.
The technical scheme of the invention also comprises a computer readable storage medium, wherein the computer readable storage medium is stored with a computer program, and the computer program is executed by a processor when being executed and is used for executing the epidemic situation tracing method.
The beneficial effects of the invention are as follows: based on the technical means of space geographic analysis and machine learning, big data and small data are combined, and epidemic situation is traced from microscopic to macroscopic. Individuation tracing of epidemic situation origin places, epidemic situation origin persons and epidemic situation propagation time from microcosmic (small data); from macroscopic (big data), accurate tracing source place and propagation time realize accurate tracing of epidemic situation to through visual show, the source of more visual demonstration epidemic situation.
Drawings
The invention is further described below with reference to the drawings and examples;
FIG. 1 is a general flow chart according to the present invention;
FIG. 2 is a flow chart of a method according to an embodiment of the invention;
FIG. 3 is a big data environment construction block diagram according to an embodiment of the present invention;
FIG. 4 is a flow chart of a preliminary traceback infection source module according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a panel data preprocessing module according to an embodiment of the present invention;
FIG. 6 is a precise tracing flow chart according to an embodiment of the invention;
fig. 7 is a flowchart of ARIMA algorithm calculation process according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to the present embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the accompanying drawings are used to supplement the description of the written description so that one can intuitively and intuitively understand each technical feature and overall technical scheme of the present invention, but not to limit the scope of the present invention.
In the description of the present invention, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement and the like should be construed broadly, and those skilled in the art can reasonably determine the specific meaning of the terms in the present invention in combination with the specific contents of the technical scheme.
Fig. 1 shows a general flow chart according to the invention. S100, corresponding data acquisition is carried out on the places, the stay time and the suspected infected persons visited by a plurality of the diagnosed infected persons within the set time, and corresponding first infected persons and corresponding first infection sources are determined according to the acquired data; s200, constructing three-dimensional coordinates according to the S100, and forming three-dimensional panel data taking places, residence time and a first infected person as coordinates; s300, predicting the three-dimensional panel data through a machine learning method to obtain the number of first infectors in one or more places of a definite infected person in the missing time, and completing the completion of the three-dimensional panel data; s400, performing spatial geographic analysis, specifically, calculating corresponding local autocorrelation coefficients of a plurality of places; s500, accurately screening the first infection sources according to the sites and the corresponding local autocorrelation coefficients until the screened first infection sources are lower than a set threshold value, and visually displaying the screened first infection sources.
FIG. 2 is a flowchart of the whole method and system, specifically including: first build up
Big data computing and displaying system and development platform based on 'hive+spark+python+mysql+java+spring' enter a data acquisition module to realize the visual display of the results of the front end of Java+spring+mysql after preliminary tracing of an infection source module, a panel data preprocessing module, a geospatial analysis module and a precise tracing module.
FIG. 3 is a block diagram of a big data environment of "hive+spark+python+mysql+java+spring", wherein hive reads json, log and other format data, and is used as a data source for storing data and reading Python models, spark is used as the whole computing environment, subsequent Python algorithms all perform computation and storage by calling pyspark, pyhive, pymysql and other related modules, python is used as a main computing and algorithm programming language, parallel computing development, preprocessing of data, panel data complement and other operations are performed, the computed and processed data are stored in hive and mysql, mysql is used as backup of computing results and input of front-end data, and a Java programming language ssm front-end building system is adopted to realize visualization of data analysis, so that users can view more conveniently.
Fig. 4 is a flowchart of a preliminary traceable infection source module, showing steps of preliminarily determining an infection source location, an infection source (initially diagnosed patient at the infection source location), and an initial infection time, that is, based on collected data, if the suspected infected person B is an infected person, the "suspected infected person b=the diagnosed infected person a" continues to perform the above data collection steps, if the suspected infected person B is a non-infected person, the place P is the infection source location, the infected person a is the initial infected person, and the initial transmission time is t.
FIG. 5 is a schematic diagram of a panel data preprocessing module, in which data at time t_m is missing, and data of [ t_0, t_m-1] is non-missing data, as training data and verification data in a forward prediction missing value model; the data of [ t_m+1, t_k ] is non-missing data, and as training data and verification data in a negative predictive missing value model, a prediction algorithm can be used, but is not limited to, a simple exponential smoothing method, a Holt-WINTERS (HOLT) linear trend method, a HOLT-WINTERS seasonal prediction model, an autoregressive moving average model (ARIMA), a naive method, a simple average method, a moving average method and related derivative algorithms, and finally positive and negative predictions and average values are carried out to complement the missing value of the panel data.
Fig. 6 is a precise tracing flowchart, after integrating panel data and complementing missing data on time axes of each place, screening out data sets of locations |m| > ð (ð > 0) and m≡0 based on the data, comparing a plurality of elements in subsets of screening data sets [ [ p_0, p_1], [ p_0, p_1, p_2] … [ p_n-2, p_n-1, p_n ] ], screening out a location P with the largest number of infection at time t_0, selecting a location with the largest number of infection at time t_1 if the location with the largest number of infection at time t_0 cannot be screened out, and so on, screening out an infection source location without repetition, outputting the screening subset, and repeating the spatial geographical analysis and precise tracing steps on the screened data sets if the number of infection sources is > α.
Fig. 7 is a flowchart of an ARIMA algorithm calculation process according to an embodiment of the present invention, mainly including obtaining a specific time sequence of a designated location, in the present invention, indicating a sequence before/after a missing value, drawing a time sequence image, observing the stationarity of the time sequence image, if the image is unstable, obtaining a first derivative of the image, observing a first reciprocal image, if the image is not stable, obtaining a second derivative image, and the like, obtaining a d derivative until the image is stable, obtaining an optimal level p and an order q by obtaining an autocorrelation coefficient ACF and a partial autocorrelation coefficient PACF, if d=0, establishing a model ARMA (p, q), if d+.0, establishing a model ARIMA (d, p, q), thereby predicting a missing value of panel data.
Based on the embodiments described in fig. 1-7, the technical solution of the present invention further proposes the following examples:
the invention combines big data and small data, and traces the epidemic situation from microscopic to macroscopic. From microcosmic (small data), tracing epidemic situation origin places, epidemic situation origin persons and epidemic situation propagation time individually; from macroscopic (big data), accurate traceback source, and travel time.
The primary tracing infection source module is used for tracing epidemic situation origin places, epidemic situation origin persons and epidemic situation propagation time from microcosmic (small data):
coronaviruses are used as examples, which are only used for the experimental description of the present invention. The related study showed that the virus had a incubation period of 14 days, survived in air for 4 days, and beta=14, mu=4, and the collected subjects E (confirmed diagnosis 1 month 15 in 2020) had a visit of R2 route L site in city D area a and R1 route P port in city a for 14 days, and a visit time of 2020.1.5 and 2020.1.10, respectively, and suspected infectious agents of 2020.1.1-2020.1.5 visit R2 route D area L site in city D area a and 2020.1.6-2020.1.10 visit R1 route P port in city a were examined, and it was found that subject F of 2020.1.7 visit R1 route P port in city a had symptoms of infection at 2020.1.5, and citizens of 2020.1.10-2020.1.14 visit R1 route P port in city a and 2020.1.5-2020.1.9 visit R2 route L site in city D area a should pay close attention to, and isolate themselves. And searching suspicious cases of the object F to the visited place, and if the suspicious cases pass the isolation detection, removing the suspicious cases, so that the object F is searched for the finding of the visited place within 14 days, and meanwhile, removing the suspicion of infection by the visiting person, wherein the R1 path P harbor of A city is preliminarily set as the infection source place, the object F is preliminarily determined as the epidemic origin person, and 2020.1.5 is the earliest infection time.
Preprocessing panel data: in the experiment, 11 cities in the area B are taken as an example, 2020.1.1-2020.5.1 time series data are randomly generated, data on individual dates are randomly deleted, an ARIMA algorithm is adopted, and the average value of positive prediction values and negative prediction values is calculated and is used as a missing data value to be filled into panel data. The process mainly comprises the following steps: acquiring a specific time sequence of a specified place, in the example, 11 cities in region B, drawing a time sequence image before/after the missing value of each city on the time sequence, observing the stability of the time sequence image, if the image is not stable, obtaining the first derivative of the image, observing the first reciprocal image, if the image is not stable, obtaining the second derivative image, and the like, obtaining the d-order derivative until the image is stable, obtaining the optimal level p and the order q by obtaining the autocorrelation coefficient ACF and the partial autocorrelation coefficient PACF, if d=0, establishing a model ARMA (p, q), if d is not equal to 0, establishing a model ARIMA (d, p, q), and thus predicting the missing value of the panel data. The calculation of a true value is performed by performing ARIMA prediction for 2 times to obtain an average value, wherein a multi-thread multi-process calculation method is adopted, and the multi-process comprises simultaneously calculating a plurality of missing values, preparing the missing values by multi-line Cheng Baokuo positive prediction, preparing the missing values by negative prediction and obtaining the average value of the two missing values.
Spatial and geographic analysis: in combination with the above data, the present example uses local Moran' I as the local correlation parameter, whose calculation formula is as follows, wherein
For the weights of cities i and j, here, if two cities are located adjacently, the sum of the number of separation of 11 cities is 33, the weight is set to (33/1), if two cities are separated by one city, the weight is set to (33/2), and so on. The local correlation parameters between the 11 cities are obtained in n number, and the parameters are normalized to [ -1,1]Within the range.
Accurate tracing module (from macroscopic (big data), accurate tracing source, and propagation time): the parameter alpha=1 is set in the example, and the screening local related parameter is approximately 0 (representing) i city and other cities are independent of each other without any mutual influence, so that i city can be an epidemic origin place, the threshold ð is set to 0.9, if M > ð, the place has a strong forward promotion relationship with surrounding areas, and the place is used as the epidemic origin place; if M < ð indicates that the land has a strong negative promotion relationship with surrounding areas, and may be a mobile cause of an infected population, the land is taken as an epidemic situation origin, and the example does not obtain the 5 seats of the city meeting the condition, so that the spatial geographic analysis is newly realized, the weight is adjusted, and finally, the weight is adjusted until the city meeting the condition is 1. And finally, if the obtained local correlation coefficients |M| are smaller than ð and not approximately equal to 0, taking the place where the |M| maximum value is located as the infection source place.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of one of ordinary skill in the art without departing from the spirit of the present invention.
Claims (7)
1. An epidemic situation tracing method is characterized by comprising the following steps:
s100, corresponding data acquisition is carried out on the places, the stay time and the suspected infected persons visited by a plurality of the diagnosed infected persons within the set time, and corresponding first infected persons and corresponding first infection sources are determined according to the acquired data;
s200, constructing three-dimensional coordinates according to the S100, and forming three-dimensional panel data taking the place, the residence time and the first infected person number as coordinates;
s300, predicting the three-dimensional panel data through a machine learning method to obtain the number of first infectors in one or more places of a definite infected person in the missing time, and completing the completion of the three-dimensional panel data;
s400, performing spatial geographic analysis, specifically, calculating corresponding local autocorrelation coefficients of a plurality of places;
wherein, the step S400 specifically includes:
calculating local autocorrelation coefficients and the number of the local autocorrelation coefficients between adjacent places, and accurately screening infection sources according to the local autocorrelation coefficients and the number of the local autocorrelation coefficients, wherein the local autocorrelation coefficients are calculated through Moran I indexes and Geary C indexes, and weight values of the adjacent places can be set in a self-defining mode;
the accurate screening specifically includes:
screening a data set with a set local positive correlation coefficient, comparing a plurality of elements in a subset of the screened data set, and screening out corresponding places with the largest local autocorrelation coefficient in each time period one by one until the places with the largest local autocorrelation coefficient cannot be screened out, and then skipping to the next time period for searching, wherein the screened places are not repeated;
screening a data set with a set local negative correlation coefficient, comparing a plurality of elements in a subset of the screened data set, and screening out corresponding places with the minimum local autocorrelation coefficient but not 0 in each time period one by one until places with the minimum local autocorrelation coefficient but not 0 cannot be screened out, and then skipping to the next time period for searching, wherein the screened places are not repeated;
screening and setting a data set which is not locally related, selecting all places in the screened data set as a first infection source of the current moment point, and further jumping to the next time period for searching, wherein the screened places are not repeated;
selecting the intersection of a plurality of location sets in the earliest time period as an infection source;
outputting a screening subset if the number of the infection sources is lower than a set value, and repeatedly executing the space geographic analysis and the accurate tracing step on the screened data set if the number of the infection sources is higher than the set value;
s500, accurately screening the first infection sources according to the sites and the corresponding local autocorrelation coefficients until the number of the screened first infection sources is lower than a set threshold value, and visually displaying the screened first infection sources.
2. The epidemic situation tracing method according to claim 1, wherein said S100 further comprises:
identifying suspected infected persons at corresponding places according to the places where the infected persons are visited in the set time or more, the stay time and the suspected infected persons;
specifically, if the suspected infected person is diagnosed, taking the diagnosed suspected infected person as the diagnosed infected person, and repeating the step S100 to acquire data; if the suspected infected person is not diagnosed, the diagnosed infected person in S100 is taken as a first infected person, and the site is taken as a first infection source.
3. The epidemic situation tracing method according to claim 1, wherein the set time and the stay time are set according to epidemic characteristics, specifically, the epidemic characteristics include a latency period and an in vitro survival period, the set time is set according to the latency period, and the stay time is set according to the in vitro survival period.
4. The epidemic situation tracing method according to claim 1, wherein the S200 specifically comprises:
s210, dividing the residence time corresponding to a plurality of diagnosed infecting persons into a plurality of equal-size time periods, and counting the number of first infecting persons at the corresponding place of each time period of the diagnosed infecting persons;
s220, constructing three-dimensional panel data by taking the residence time as an X axis, taking a time period as an X axis scale, taking a place as a Y axis and taking the number of first infected persons as a Z axis.
5. The epidemic situation tracing method according to claim 1, wherein the S300 specifically comprises:
predicting the three-dimensional panel deletion by using a model comprising, but not limited to, a simple exponential smoothing method, a Holt-WINTERS seasonal predictive model, an autoregressive moving average model, a naive method, a simple averaging method, a moving average method and a time sequence machine learning algorithm, and predicting to obtain first infection sources and corresponding first infection numbers at different positions of a deletion time point.
6. The epidemic situation tracing method according to claim 5, wherein the prediction specifically comprises positive prediction and negative prediction;
the forward prediction is to forward sequence the data along a time sequence, take the data continuously existing before the time point of the missing value data as training and verification data, and predict the data of the missing value time point;
the negative prediction is to sort the data along the time sequence in the negative direction, take the data continuously existing after the time point of the missing value data as training and verification data, predict the time point data of the missing value, and finally obtain the average value of the positive and negative prediction values as the missing value.
7. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, is adapted to perform the epidemic situation tracing method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010387822.5A CN111695048B (en) | 2020-05-09 | 2020-05-09 | Epidemic situation tracing method and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010387822.5A CN111695048B (en) | 2020-05-09 | 2020-05-09 | Epidemic situation tracing method and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695048A CN111695048A (en) | 2020-09-22 |
| CN111695048B true CN111695048B (en) | 2023-06-02 |
Family
ID=72477403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010387822.5A Active CN111695048B (en) | 2020-05-09 | 2020-05-09 | Epidemic situation tracing method and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695048B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113132912B (en) * | 2021-04-12 | 2022-11-29 | 东南大学 | Double tracing method and system for infectious disease close contact based on human-ground digital portrait |
| CN113299401B (en) * | 2021-05-28 | 2023-04-07 | 平安科技（深圳）有限公司 | Infectious disease data transmission monitoring method and device, computer equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015127065A1 (en) * | 2014-02-19 | 2015-08-27 | Hrl Laboratories, Llc | Disease prediction system using open source data |
| CN105740615A (en) * | 2016-01-28 | 2016-07-06 | 中山大学 | Method for tracking infection sources and predicting trends of infectious diseases by utilizing mobile phone tracks |
| CN107767954A (en) * | 2017-10-16 | 2018-03-06 | 中国科学院地理科学与资源研究所 | A kind of Environmental Health Risk Monitoring early warning system and method based on space Bayesian network |
| CN109545386A (en) * | 2018-11-02 | 2019-03-29 | 深圳先进技术研究院 | A kind of influenza spatio-temporal prediction method and device based on deep learning |
| CN110993118A (en) * | 2020-02-29 | 2020-04-10 | 同盾控股有限公司 | Epidemic situation prediction method, device, equipment and medium based on ensemble learning model |
| CN111027525A (en) * | 2020-03-09 | 2020-04-17 | 中国民用航空总局第二研究所 | Method, device and system for tracking potential infected persons in public places during epidemic situation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190148023A1 (en) * | 2017-11-16 | 2019-05-16 | Google Llc | Machine-Learned Epidemiology |
-
2020
- 2020-05-09 CN CN202010387822.5A patent/CN111695048B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015127065A1 (en) * | 2014-02-19 | 2015-08-27 | Hrl Laboratories, Llc | Disease prediction system using open source data |
| CN105740615A (en) * | 2016-01-28 | 2016-07-06 | 中山大学 | Method for tracking infection sources and predicting trends of infectious diseases by utilizing mobile phone tracks |
| CN107767954A (en) * | 2017-10-16 | 2018-03-06 | 中国科学院地理科学与资源研究所 | A kind of Environmental Health Risk Monitoring early warning system and method based on space Bayesian network |
| CN109545386A (en) * | 2018-11-02 | 2019-03-29 | 深圳先进技术研究院 | A kind of influenza spatio-temporal prediction method and device based on deep learning |
| CN110993118A (en) * | 2020-02-29 | 2020-04-10 | 同盾控股有限公司 | Epidemic situation prediction method, device, equipment and medium based on ensemble learning model |
| CN111027525A (en) * | 2020-03-09 | 2020-04-17 | 中国民用航空总局第二研究所 | Method, device and system for tracking potential infected persons in public places during epidemic situation |
Non-Patent Citations (1)
| Title |
|---|
| 王劲峰,孟斌,郑晓瑛,刘纪远,韩卫国,武继磊,刘旭华,李小文,宋新明.北京市2003年SARS疫情的多维分布及其影响因素分析.中华流行病学杂志.2005,(03),第164-168页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695048A (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Reinhart | A review of self-exciting spatio-temporal point processes and their applications | |
| CN111695048B (en) | Epidemic situation tracing method and medium | |
| CN111738044B (en) | Campus violence assessment method based on deep learning behavior recognition | |
| CN109166630B (en) | Infectious disease data monitoring and processing method and system | |
| CN111597990B (en) | RSVP (resource reservation protocol) model-based brain-computer combined target detection method and system | |
| CN114638292B (en) | Artificial intelligence pathology auxiliary diagnosis system based on multi-scale analysis | |
| CN108446594B (en) | Emergency response capability evaluation method based on action recognition | |
| CN114240874A (en) | Bone age assessment method and device based on deep convolutional neural network and feature fusion and computer readable storage medium | |
| CN116611546A (en) | Knowledge-graph-based landslide prediction method and system for target research area | |
| CN116110597A (en) | Digital twinning-based intelligent analysis method and device for patient disease categories | |
| Bao et al. | Covid-gan+: Estimating human mobility responses to covid-19 through spatio-temporal generative adversarial networks with enhanced features | |
| Dong et al. | Non-stationary spatio-temporal point process modeling for high-resolution COVID-19 data | |
| CN117351440B (en) | Semi-supervised ship detection method and system based on open text detection | |
| Xu et al. | An automated cell tracking approach with multi-Bernoulli filtering and ant colony labor division | |
| RU2740708C1 (en) | Radio monitoring results processing method | |
| CN116363494B (en) | Fish quantity monitoring and migration tracking method and system | |
| CN109670541B (en) | Mosquito-borne infectious disease fever crowd range marking method based on space aggregation | |
| Hopkins et al. | Gap analysis and the geographical distribution of parasites | |
| Hui | A Bayesian solution to the modifiable areal unit problem | |
| Pérez et al. | Model testing and assessment: perspectives from a swarm intelligence, agent-based model of forest insect infestations | |
| Kapusta et al. | Holt's Linear Model of COVID-19 Morbidity Forecasting in Ukraine. | |
| CN112331342A (en) | Disease risk grade evaluation method based on gridding covariate factors | |
| CN117557789B (en) | Intelligent detection method and system for offshore targets | |
| Zheng et al. | Predicting the distribution of COVID-19 through CGAN—Taking Macau as an example | |
| CN117423476B (en) | Echinococcosis epidemic rate prediction method based on downscaling and Bayesian model |
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 |