CN111695048A - Epidemic situation tracing method and medium - Google Patents
Epidemic situation tracing method and medium Download PDFInfo
- Publication number
- CN111695048A CN111695048A CN202010387822.5A CN202010387822A CN111695048A CN 111695048 A CN111695048 A CN 111695048A CN 202010387822 A CN202010387822 A CN 202010387822A CN 111695048 A CN111695048 A CN 111695048A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- places
- screened
- screening
- 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.)
- Granted
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an epidemic situation tracing method and a medium, wherein the method comprises the following steps: collecting data of a confirmed infected person, namely an initial infected person and an infection source; 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 spatial geographic analysis, and calculating corresponding local autocorrelation coefficients of a plurality of places; and accurately screening the initial infection source according to the location and the corresponding local autocorrelation coefficient until the screened initial infection source is lower than a set threshold, and visually displaying the screened initial infection source. The invention has the beneficial effects that: based on the technical means of space geographic analysis and machine learning, big data and little data are combined, and the epidemic situation is traced from the micro to the macro.
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
From 2003 to the present, epidemic situations are always rough and impatient, and in the beginning of 2020, national leaders stress that "new technologies such as artificial intelligence and big data are used to carry out epidemiology and traceability investigation, and to find out where the disease source comes and goes, so as to improve the accuracy and the screening efficiency. "
The epidemic situation tracing of the prior art is analyzed by collecting images, videos, human body temperature and other data through collecting equipment, sensors and other equipment, the limitation of the technical scheme is very large, the epidemic situation tracing can only be collected and analyzed through a place provided with the device, and the tracing can not be carried out according to the action track of an epidemic disease carrier.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art, and provides an epidemic situation tracing method and medium, which realize accurate tracing of an epidemic situation by a technical means based on space 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 places visited by a plurality of confirmed infected persons within a set time or longer, the staying time and suspected infected persons, 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 with the location, the residence time and the number of the first infected persons as coordinates; s300, predicting the three-dimensional panel data by a machine learning method to obtain the first infected person number of one or more places of confirmed infected persons 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 places and the corresponding local autocorrelation coefficients until the number of the screened first infection sources is lower than a set threshold, and visually displaying the screened first infection sources.
According to the epidemic situation tracing method, the S100 further includes: according to the position visited by the confirmed infected person within the set time, the stay time and the suspected infected person, identifying the suspected infected person at the corresponding position; specifically, if the suspected infected person is diagnosed, repeating the step S100 to complete data acquisition when the diagnosed suspected infected person is regarded as a diagnosed infected person; if the suspected infected person is not diagnosed, the infected person diagnosed in the step S100 is used as a first infected person, and the place is used as a first infection source.
According to the epidemic situation tracing method, the set time and the stay time are set according to the characteristics of the epidemic disease, specifically, the characteristics of the epidemic disease comprise 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.
According to the epidemic situation tracing method, the S200 specifically comprises the following steps: s210, dividing the residence time corresponding to a plurality of confirmed infected persons into a plurality of time periods with the same size, and counting the number of first infected persons at the corresponding position of each time period of the confirmed infected persons; s220, establishing three-dimensional panel data by taking the stay time as an X axis, taking the time period as an X axis scale, taking the place as a Y axis and taking the number of the first infected persons as a Z axis.
According to the epidemic situation tracing method, the S300 specifically comprises the following steps: predicting the three-dimensional panel missing by using a simple exponential smoothing method, a Holt linear trend method, a HOLT-WINTERS seasonal prediction model, an autoregressive moving average model, a naive method, a simple average method, a moving average method and a time series machine learning algorithm, and predicting first infectious sources and the corresponding number of first infected persons at different places of the missing time point.
According to the epidemic situation tracing method, the prediction specifically comprises positive prediction and negative prediction; the forward prediction is to sort the data in the forward direction of the time sequence, take the data continuously existing before the missing value data time point as training and verification data and predict the missing value time point data; the negative prediction is to sort the data in the negative direction along a time sequence, take the continuously existing data after the missing value data time point as training and verification data, predict the missing value time point data, and finally obtain the average value of the positive and negative prediction values as the missing value.
According to the epidemic situation tracing method, the S400 specifically comprises the following steps: 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 an I index of Moran and a C index of Geary, and weight values of the adjacent places can be set in a self-defined mode.
According to the epidemic situation tracing method, the accurate 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, screening out a corresponding place with the maximum local autocorrelation coefficient in each time period one by one until the place with the maximum local autocorrelation coefficient cannot be screened out, and then jumping 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, screening corresponding places with the minimum local autocorrelation coefficient but not 0 in each time period one by one until the places with the minimum local autocorrelation coefficient but not 0 can not be screened, and then jumping to the next time period for searching, wherein the screened places are not repeated; screening and setting a local irrelevant data set, selecting all places in the data set as a first infection source place of the moment point, and then skipping to the next time period for searching, wherein the screened places are not repeated; selecting the intersection of a plurality of site sets in the earliest time period as an infection source; if the number of the infection sources is lower than a set value, outputting the screening subset, and if the number of the infection sources is higher than the set value, repeatedly executing the spatial geographic analysis and the accurate source tracing steps on the screened data set.
The technical solution of the present invention further includes a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed when being executed by a processor, and is used to execute any one of the epidemic situation tracing methods.
The invention has the beneficial effects that: based on the technical means of space geographic analysis and machine learning, big data and little data are combined, and the epidemic situation is traced from the micro to the macro. From the microcosmic (small data), the personalized tracing epidemic situation source, epidemic situation source person and epidemic situation propagation time; from the macro (big data), accurate tracing to the origin place and the propagation time of tracing back realizes the accurate tracing to the epidemic situation to through visual show, the source of more audio-visual demonstration epidemic situation.
Drawings
The invention is further described below with reference to the accompanying drawings and examples;
FIG. 1 is a general flow diagram according to the present invention;
FIG. 2 is a flow diagram of a method according to an embodiment of the invention;
FIG. 3 is a big data environment building block diagram according to an embodiment of the invention;
FIG. 4 is a flow diagram of a preliminary traceability 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 invention;
FIG. 6 is a flow chart of accurate tracing according to an embodiment of the present invention;
fig. 7 is a flow chart of an ARIMA algorithm calculation process according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood 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 otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
Fig. 1 shows a general flow chart according to the invention. S100, corresponding data acquisition is carried out on places visited by a plurality of confirmed infected persons within a set time or longer, the staying time and suspected infected persons, and corresponding first infected persons and corresponding first infection sources are determined according to the acquired data; s200, constructing a three-dimensional coordinate according to the S100 to form three-dimensional panel data with the location, the stay time and the first infected person as coordinates; s300, predicting the three-dimensional panel data by a machine learning method to obtain the first infected person number of one or more places of the confirmed 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 source according to the location and the corresponding local autocorrelation coefficient until the screened first infection source is lower than a set threshold, and visually displaying the screened first infection source.
Fig. 2 is a flowchart of the whole method and system, which specifically includes: and first establishing
The big data calculation and display system and the development platform based on 'hive + spark + python + mysql + Java + spring' enter a data acquisition module to realize the initial tracing infection source module, a panel data preprocessing module, a geographic space analysis module, an accurate tracing module and finally enter the Java + spring + mysql front end result visual display.
Fig. 3 is a structural diagram of a 'hive + spark + Python + mysql + Java + spring' big data environment construction, wherein the hive reads data in formats such as json and log, and serves as a read data source for storing data and a Python model, the spark serves as the whole computing environment, subsequent Python algorithms calculate and store by calling pyspark, pyhive, pymysql and other related modules, the Python serves as a main computing and algorithm programming language, and performs operations such as parallel computing development, data preprocessing, panel data completion and the like, the calculated and processed data are stored in the hive and mysql, the mysql serves as a backup of a computing result and an input of front-end data, and a Java programming language ssm front-end construction system is adopted to realize visualization of data analysis and facilitate viewing of a user.
Fig. 4 is a flowchart of a module for preliminarily tracing the infection source, which shows the steps of preliminarily determining the location of the infection source, the infection source (the patient is initially diagnosed at the infection source), and the initial infection time, that is, based on the collected data, if the suspected infected person B is diagnosed as the infected person, the data collection step is continued by "the suspected infected person B is the confirmed infected person a", and if the suspected infected person B is not diagnosed, the location P is the infection source, 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 [ t _0, t _ m-1] is non-missing data, and is used 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 is used as training data and verification data in a negative prediction missing value model, and the prediction algorithm can use but is not limited to a simple exponential smoothing method, a Holt (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 are carried out and averaged to complete the missing value of the panel data.
FIG. 6 is a flow chart of accurate traceability, which is to integrate panel data and fill up missing data on each local time axis, and then screen the missing data based on the data
And M ≈ 0 location data set, and filters the data set [ [ P _0, P _ 1]],[P_0,P_1,P_2]…[P_n-2，P_n-1,P_n]]The plurality of elements in the subset in (1) are compared, and a place P with the largest number of initial infected people at the time point of t _0 is screened out, and if the time point of t _0 isIf the site with the largest number of infected persons cannot be screened out, selecting a t _1 time point, and so on, wherein the screened infection source sites have no repetition, and if the number of the infection source sites is large<α, the selected subset is output, if the number of infection sources>α, the spatial geography analysis and the accurate source tracing steps are repeated on the screened data set.
Fig. 7 is a flowchart of a calculation process of ARIMA algorithm according to an embodiment of the present invention, which mainly includes acquiring a specific time sequence of a designated location, referring to a missing value forward/backward sequence in the present invention, drawing a time sequence image, observing stationarity of the time sequence image, if the image is not stationary, obtaining a first derivative of the image, observing a first reciprocal image, if the image is still not stationary, obtaining a second derivative image, and so on obtaining a d-order derivative until the image is stationary, obtaining an optimal level p and an optimal level q by obtaining an autocorrelation coefficient ACF and an autocorrelation coefficient PACF, if d ≠ 0, establishing a model ARMA (p, q), and 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 to trace the epidemic situation from micro to macro. From the microcosmic (small data), the individual tracing epidemic situation source, the epidemic situation source person and the epidemic situation propagation time; from a macroscopic (big data) perspective, the origin is accurately traced back, and the propagation time is also accurately traced.
The infection source module is preliminarily traced, and the individual tracing epidemic situation source area, the epidemic situation source person and the epidemic situation propagation time are as follows from the microcosmic (small data):
the examples are given by way of example only and are intended to be illustrative of the present invention. Relevant researches show that the virus has a latency period of 14 days and can survive in the air for 4 days, beta is 14, mu is 4, the sites visited within 14 days of Huang-Zhi (confirmed by 1/15 days in 2020) are respectively R2L site in D area of A and R1P harbor in A, the visiting times are 2020.1.5 and 2020.1.10, suspicious infected persons visiting 2020.1.1-2020.1.5R 2D area L site in D area of A and 2020.1.6-2020.1.10R 1P harbor in A are examined, and the suspected infected persons visiting 2020.1.7 to Liu R1P harbor in B area of A and 2020.1.5 show infection symptoms, and meanwhile 2020.1.10-2020.1.14A R1P harbor and 2020.1.5-2020.1.9 to R2L site in D area of A should pay close attention and be isolated. Then, the place 2020. of Liu and suspicious cases are searched, and the suspicious cases are detected by isolation and all the suspicious cases are eliminated, so that the places visited within 14 days of Liu are searched for finding, meanwhile, the visitors all eliminate infection suspicions, therefore, R1 harbor in A city is initially set as the infection source, Liu is initially identified as the epidemic initiator, and 2020.1.5 is the earliest infection time.
Panel data preprocessing: in the experiment, 11 cities in a certain area are taken as an example, 2020.1.1-2020.5.1 time sequence data are randomly generated, data of individual dates are randomly deleted, and an ARIMA algorithm is adopted to obtain the average value of positive prediction values and negative prediction values to be used as missing data values to be filled in panel data. The process mainly comprises the following steps: the method comprises the steps of obtaining a specified location specific time sequence, in the example, 11 cities in a certain area, obtaining a data sequence before/after a missing value of each city on the time sequence, drawing a time sequence image, observing stationarity of the time sequence image, obtaining a first derivative of the image and a first reciprocal image if the image is not stationary, obtaining a second derivative image if the image is not stationary, obtaining a d-order derivative by the analogy until the image is stationary, obtaining an optimal level p and an order q by obtaining an autocorrelation coefficient ACF and a partial autocorrelation coefficient PACF, establishing a model ARMA (p, q) if d is 0, and establishing a model ARIMA (d, p, q) if d is not 0, thereby predicting a missing value of panel data. The calculation of one actual value needs 2 ARIMA predictions and the average value is obtained, wherein a multithreading multiprocess obtaining method is adopted, wherein the multiprocess comprises the simultaneous obtaining of a plurality of missing values, and the multithreading comprises the positive prediction of making the missing value, the negative prediction of making the missing value and the average value of the two.
Spatial geographic analysis: in combination with the above data, the present example uses local Moran' I as the local correlation parameter, which is calculated as follows, where wijThe weights for cities i and j are set to (33/1) where two cities are Dongguan and Foshan, respectively, adjacent to each other, and the total of the number of 11 cities apart is 33, and where two cities are Dongguan and Guangzhou, respectively, separated by oneFor each city, the weight is set to (33/2), and so on. Thus, n local correlation parameters between every two of the 11 cities are obtained, and the parameters are standardized to [ -1, 1]Within the range.
The parameter α is set to be 1, the local related parameter is screened to be approximately 0 (representing that the city i and other cities are independent and have no mutual influence, so the city i can be an epidemic situation origin, and a threshold value is set at the place
Is set to 0.9, if
The situation shows that the place has strong forward promotion relation with the surrounding area and serves as an epidemic situation origin place; if it is
The situation shows that the place has a strong negative promotion relationship with surrounding areas and may be a cause of infected population mobility, the place is taken as an epidemic situation origin, and the example does not obtain 5 eligible cities, so that the space geographic analysis is newly realized, the weight is adjusted, and finally the eligible city is 1. Finally, if the obtained local correlation coefficients | M | are all smaller than
And is not equal to 0, and the location of the maximum value of M is taken as the infection source.
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 those skilled in the art without departing from the gist of the present invention.
Claims (9)
1. An epidemic situation tracing method is characterized by comprising the following steps:
s100, corresponding data acquisition is carried out on places visited by a plurality of confirmed infected persons within a set time or longer, the staying time and suspected infected persons, 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 with the location, the residence time and the number of the first infected persons as coordinates;
s300, predicting the three-dimensional panel data by a machine learning method to obtain the first infected person number of one or more places of confirmed infected persons 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 places and the corresponding local autocorrelation coefficients until the number of the screened first infection sources is lower than a set threshold, and visually displaying the screened first infection sources.
2. The epidemic tracing method according to claim 1, wherein the S100 further comprises:
according to the position visited by the confirmed infected person within the set time, the stay time and the suspected infected person, identifying the suspected infected person at the corresponding position;
specifically, if the suspected infected person is diagnosed, repeating the step S100 to complete data acquisition when the diagnosed suspected infected person is regarded as a diagnosed infected person; if the suspected infected person is not diagnosed, the infected person diagnosed in the step S100 is used as a first infected person, and the place is used as a first infection source.
3. The epidemic 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 confirmed infected persons into a plurality of time periods with the same size, and counting the number of first infected persons at the corresponding position of each time period of the confirmed infected persons;
s220, establishing three-dimensional panel data by taking the stay time as an X axis, taking the time period as an X axis scale, taking the place as a Y axis and taking the number of the first infected persons as a Z axis.
5. The epidemic situation tracing method according to claim 1, wherein said S300 specifically comprises:
predicting the three-dimensional panel missing by using a simple exponential smoothing method, a Holt linear trend method, a HOLT-WINTERS seasonal prediction model, an autoregressive moving average model, a naive method, a simple average method, a moving average method and a time series machine learning algorithm, and predicting first infectious sources and the corresponding number of first infected persons at different places of the missing time point.
6. The epidemic tracing method according to claim 5, wherein the prediction specifically comprises a positive prediction and a negative prediction;
the forward prediction is to sort the data in the forward direction of the time sequence, take the data continuously existing before the missing value data time point as training and verification data and predict the missing value time point data;
the negative prediction is to sort the data in the negative direction along a time sequence, take the continuously existing data after the missing value data time point as training and verification data, predict the missing value time point data, and finally obtain the average value of the positive and negative prediction values as the missing value.
7. The epidemic situation tracing method according to claim 1, wherein said S400 specifically comprises:
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 an I index of Moran and a C index of Geary, and weight values of the adjacent places can be set in a self-defined mode.
8. The epidemic situation tracing method of claim 7, wherein the precise screening specifically comprises:
screening a data set with a set local positive correlation coefficient, comparing a plurality of elements in a subset of the screened data set, screening out a corresponding place with the maximum local autocorrelation coefficient in each time period one by one until the place with the maximum local autocorrelation coefficient cannot be screened out, and then jumping 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, screening corresponding places with the minimum local autocorrelation coefficient but not 0 in each time period one by one until the places with the minimum local autocorrelation coefficient but not 0 can not be screened, and then jumping to the next time period for searching, wherein the screened places are not repeated;
screening and setting a local irrelevant data set, selecting all places in the data set as a first infection source place of the moment point, and then skipping to the next time period for searching, wherein the screened places are not repeated;
selecting the intersection of a plurality of site sets in the earliest time period as an infection source;
if the number of the infection sources is lower than a set value, outputting the screening subset, and if the number of the infection sources is higher than the set value, repeatedly executing the spatial geographic analysis and the accurate source tracing steps on the screened data set.
9. A computer-readable storage medium having stored thereon a computer program for execution by a processor when the computer program is executed, for performing the epidemic tracing method according to any one of claims 1 to 8.
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 true CN111695048A (en) | 2020-09-22 |
| CN111695048B 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) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113132912A (en) * | 2021-04-12 | 2021-07-16 | 东南大学 | Double tracing method and system for infectious disease close-up recipient based on human-ground digital portrait |
| CN113299401A (en) * | 2021-05-28 | 2021-08-24 | 平安科技（深圳）有限公司 | Infectious disease data transmission monitoring method and device, computer equipment and medium |
Citations (7)
| 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 |
| US20190148023A1 (en) * | 2017-11-16 | 2019-05-16 | Google Llc | Machine-Learned Epidemiology |
| 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 |
-
2020
- 2020-05-09 CN CN202010387822.5A patent/CN111695048B/en active Active
Patent Citations (7)
| 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 |
| US20190148023A1 (en) * | 2017-11-16 | 2019-05-16 | Google Llc | Machine-Learned Epidemiology |
| 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" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113132912A (en) * | 2021-04-12 | 2021-07-16 | 东南大学 | Double tracing method and system for infectious disease close-up recipient based on human-ground digital portrait |
| CN113299401A (en) * | 2021-05-28 | 2021-08-24 | 平安科技（深圳）有限公司 | Infectious disease data transmission monitoring method and device, computer equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695048B (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271888A (en) | Personal identification method, device, electronic equipment based on gait | |
| KR20200005987A (en) | System and method for diagnosing cognitive impairment using touch input | |
| RU2012133279A (en) | COMPUTER SYSTEM FOR FORECASTING TREATMENT RESULTS | |
| CN111695048A (en) | Epidemic situation tracing method and medium | |
| CN111597990B (en) | RSVP (resource reservation protocol) model-based brain-computer combined target detection method and system | |
| Thian et al. | Deep learning systems for pneumothorax detection on chest radiographs: a multicenter external validation study | |
| CN113111767A (en) | Fall detection method based on deep learning 3D posture assessment | |
| CN109871762B (en) | Face recognition model evaluation method and device | |
| CN113496781A (en) | Urban internal infectious disease diffusion simulation method and system and electronic equipment | |
| JP2022530868A (en) | Target object attribute prediction method based on machine learning, related equipment and computer programs | |
| CN116611546B (en) | Knowledge-graph-based landslide prediction method and system for target research area | |
| JP3995424B2 (en) | Infectious disease transmission analysis system and its transmission simulation system | |
| CN108446594B (en) | Emergency response capability evaluation method based on action recognition | |
| CN110717461A (en) | Fatigue state identification method, device and equipment | |
| CN116807447B (en) | Brain age prediction modeling method, cognition improving method and system of dynamic brain network | |
| CN111523593A (en) | Method and apparatus for analyzing medical images | |
| CN110716998A (en) | Method for spatializing fine-scale population data | |
| CN113436295B (en) | Living body culture monitoring track drawing method, device, equipment and storage medium | |
| CN113869599A (en) | Fish epidemic disease development prediction method, system, equipment and medium | |
| RU2740708C1 (en) | Radio monitoring results processing method | |
| CN116186561B (en) | Running gesture recognition and correction method and system based on high-dimensional time sequence diagram network | |
| CN115375500A (en) | Risk map generation method, device, equipment and storage medium | |
| CN110610766A (en) | Apparatus and storage medium for deriving probability of disease based on symptom feature weight | |
| CN114882580A (en) | Measuring method for motion action consistency based on deep learning | |
| CN113255462A (en) | Gait scoring method, system, computer program product and readable storage medium |
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 |