CN110426735A - A kind of detection method of the earthquake disaster coverage based on social media - Google Patents
A kind of detection method of the earthquake disaster coverage based on social media Download PDFInfo
- Publication number
- CN110426735A CN110426735A CN201910589007.4A CN201910589007A CN110426735A CN 110426735 A CN110426735 A CN 110426735A CN 201910589007 A CN201910589007 A CN 201910589007A CN 110426735 A CN110426735 A CN 110426735A
- Authority
- CN
- China
- Prior art keywords
- social media
- data
- earthquake
- growth
- transducing signal
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/282—Application of seismic models, synthetic seismograms
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The detection method for the earthquake disaster coverage based on social media that the invention discloses a kind of, first, the time cycle is determined according to the signal-to-noise ratio of setting, social media transducing signal data are extracted from the social media data towards earthquake disaster of acquisition, then, according to the social media transducing signal data extracted, spatial statistics are carried out in conjunction with demographic data, construct data space logic model of growth；Finally, being detected using the data space logic model of growth to earthquake disaster coverage.Social media transducing signal spatial distribution model of growth proposed by the present invention, it can reveal that the mapping mechanism of data space distribution and devastated, solve the problems, such as that the estimation of disaster-stricken range is limited by that social media data volume relies on and the response time is long, thus realize quickly, quantitative, detection devastated.Devastated is understood for manager, guidance is provided, facilitate calamity emergency decision.
Description
Technical field
The present invention relates to social media Text Mining Technology fields, and in particular to a kind of earthquake disaster based on social media
The detection method of coverage.
Background technique
Logic model of growth (Logistic) typically exhibits S type curve, there is long history in terms of statistics and modeling.
It is a kind of to be initially used to the most simple of the Population Size that continuously increases under the conditions of limited environment of description biotic population and time relationship
Single form.The model starts to be mainly used for studying species procreation, and with the sample of investigation every profession and trade, discovery is not only biological
Population growth speed exists from slow to fast, and near slow rule, many things such as economy, business, sciemtifec and technical sphere also comply with life
S curve rule in object developmental process.Logistic model is widely applied in each research.
Social media data also contain location information in addition to the data comprising the forms such as picture or video, text.Earthquake hair
After life, the witness and direct participant of the part common people and media as Disaster Event are more accurate to the assurance of event, in real time
The social media data of publication can be considered as the sensed values for having the condition of a disaster information value.The social media number of victims of the disaster's real-time release
According to discrimination standard is very effective, transducing signal can be counted as, for monitoring the generation and coverage of identification disaster.It is right
For earthquake is this without disaster that is emissary and having outburst center type, the distance apart from disaster center will affect citizen
The wish of perception and publication the condition of a disaster information to disaster intensity, so that the distribution of social media transducing signal spatially is regular
S type curve law is presented.Logic of sets model of growth extracts studying transducing signal and the spatial distribution of data is theoretical and model
Theory support can be provided to perceive devastated using social media.
At least there is following technology in implementing the present invention, it may, the method for finding the prior art in present inventor
Problem:
It is usually indirectization that social media, which contains knowledge, and existing method is limited to data volume dependence, it is difficult to quickly
The defect of the disaster-stricken range of quantitative detection earthquake.
Summary of the invention
In view of this, the detection method of the present invention provides a kind of earthquake disaster coverage based on social media, is used
Data volume dependence is limited to solve or at least partly solve existing method, it is difficult to which fast quantification detects the disaster-stricken range of earthquake
Defect the technical issues of.
The earthquake disaster coverage based on social media that in order to solve the above-mentioned technical problems, the present invention provides a kind of
Detection method, comprising:
Step S1: determining the time cycle according to the signal-to-noise ratio of setting, from the social media number towards earthquake disaster of acquisition
Social media transducing signal data are extracted in, wherein signal-to-noise ratio is to be pushed away in a time cycle by event influence area
The ratio of literary sum is pushed away in literary quantity and the time cycle；
Step S2: according to the social media transducing signal data extracted, spatial statistics, building are carried out in conjunction with demographic data
Data space logic model of growth；
Step S3: earthquake disaster coverage is detected using the data space logic model of growth.
In one embodiment, step S1 is specifically included:
Step S1.1: social media data of the acquisition towards earthquake disaster；
Step S1.2: the social media data of acquisition are formatted, the format of internal preset is converted into；
Step S1.3: the social media data after format conversion are filtered based on keyword；
Step S1.4: filtered social media data are pre-processed；
Step S1.5: training machine Study strategies and methods carry out real-time grading to pretreated social media data are carried out,
It extracts and earthquake related data；
Step S1.6: determining the time cycle according to signal-to-noise ratio, from obtaining in step S1.5 and sieve in earthquake related data
Select the social media transducing signal data of corresponding time cycle.
In one embodiment, step S2 is specifically included:
Step S2.1: determining spatial statistics distance interval, calculates the loop buffer apart from seismic centre c different distance interval
Social media transducing signal quantity and the size of population in area；
Step S2.2: the size of population in the calculated buffer circle apart from seismic centre c different distance interval is utilized
Social media signal data is standardized, unit population is obtained and issues transducing signal quantity；
Step S2.3: unit population issues transducing signal number after the standardization within the scope of statistical distance seismic centre distance r
According to quantity MPr and r between numerical relation, using structural simulation S type citizen's sensor number of classical logic Growth Function
According to growth curve, spatial logic model of growth SLGM is constructed, wherein SLGM is defined as follows:
Wherein, MP (r) indicates that population standardizes social media transducing signal cumulative amount within the scope of seismic centre r,
rmFor the range index in earthquake effect region, K is quantity and l after standardization0For maximum space growth rate, e is natural constant.
In one embodiment, step S3 is specifically included:
Using the parameter of maximum likelihood estimate estimation space logic model of growth, solves and obtain rmFor earthquake disaster influence
Range.
In one embodiment, step S1.4 is specifically included:
Filtered social media data are segmented, and delete URL wherein included, number and stop words.
In one embodiment, step S2.1 is specifically included:
Step S2.1.1: centered on earthquake centre, the buffer area apart from earthquake centre different distance interval is generated, wherein buffer area
Each distance interval is 1km；
Step S2.1.2: carrying out erasing analysis to adjacent buffer area, obtains ring buffer, counts in ring buffer
The size of population and social media transducing signal quantity.
Said one or multiple technical solutions in the embodiment of the present application at least have following one or more technology effects
Fruit:
The detection method of a kind of earthquake disaster coverage based on social media provided by the invention, firstly, according to setting
The signal-to-noise ratio set determines the time cycle, and social media sensing is extracted from the social media data towards earthquake disaster of acquisition
Then signal data according to the social media transducing signal data extracted, carries out spatial statistics, building in conjunction with demographic data
Data space logic model of growth；The data space logic model of growth of building is recycled to visit earthquake disaster coverage
It surveys.
Since the present invention can use the transducing signal feature of social media data, in conjunction with collected society after the earthquake
Media transducing signal data and demographic data are handed over, the spatial distribution characteristic of express statistic data constructs spatial distribution model of growth,
And the mapping mechanism of data space distribution and devastated is disclosed, it is disaster-stricken using the detection earthquake of social media data to solve tradition
The method of range is limited by the problem that social media data volume relies on and the response time is long, can be realized and does not need in a short time
Under conditions of priori knowledge, quickly estimates earthquake effect region, reference is provided for Emergency decision, to further detect more
Fine disaster-stricken range.The present invention has Emergency decision certain help.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow diagram of the detection method of the earthquake disaster coverage based on social media of the present invention；
Fig. 2 is the Technology Roadmap of the detection method of earthquake disaster coverage provided by the invention；
Fig. 3 is the result schematic diagram of the first earthquake case detection；
Fig. 4 is the result schematic diagram of second of earthquake case detection；
Fig. 5 is the result and official's comparative evaluation result schematic diagram of the first earthquake case detection；
Fig. 6 is the result and official's comparative evaluation result schematic diagram of second of earthquake case detection.
Specific embodiment
It is an object of the invention to not consider the transduction feature of social media for the prior art, and be limited by data volume according to
Rely, it is difficult to which fast quantification detects the defect of the disaster-stricken range of earthquake, proposes a kind of utilization social media quick detection earthquake effect model
The method enclosed, to reach the technical effect of quick detection earthquake effect range.
To reach above-mentioned technical effect, central scope of the invention is as follows:
A kind of method of reasonable utilization social media quick detection earthquake disaster coverage provided by the invention, including
For the spatial analysis of social media transducing signal data after the earthquake, the space growth trend and biological species of data are found
Group's logic growth trend is similar, a social media transducing signal spatial logic model of growth, and the space to describe data increases
Long pattern；Secondly, the model based on proposition, constructs one using the one of social media data quick detection earthquake effect range
A frame, by estimating earthquake effect range in conjunction with social media data and other auxiliary datas.Social activity proposed by the present invention
Media transducing signal spatial distribution model of growth can reveal that the mapping mechanism of data space distribution and devastated, solve
Disaster-stricken range is estimated to be limited by the problem that social media data volume relies on and the response time is long, to realize quick, quantitative, detection
Devastated.Devastated is understood for manager, guidance is provided, facilitate calamity emergency decision.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Embodiment one
A kind of detection method of earthquake disaster coverage based on social media is present embodiments provided, referring to Figure 1,
This method comprises:
Step S1: determining the time cycle according to the signal-to-noise ratio of setting, from the social media number towards earthquake disaster of acquisition
Social media transducing signal data are extracted in, wherein signal-to-noise ratio is to be pushed away in a time cycle by event influence area
The ratio of literary sum is pushed away in literary quantity and the time cycle.
Specifically, the embodiment of the present invention can carry out the acquisition of data to push away special and Sina weibo as data source.
Wherein, step S1 is specifically included:
Step S1.1: social media data of the acquisition towards earthquake disaster；
Step S1.2: the social media data of acquisition are formatted, the format of internal preset is converted into；
Step S1.3: the social media data after format conversion are filtered based on keyword；
Step S1.4: filtered social media data are pre-processed；
Step S1.5: training machine Study strategies and methods carry out real-time grading to pretreated social media data are carried out,
It extracts and earthquake related data；
Step S1.6: determining the time cycle according to signal-to-noise ratio, from obtaining in step S1.5 and sieve in earthquake related data
Select the social media transducing signal data of corresponding time cycle.
Specifically, step S1.1 can be searched for using social media and be applied by the given radius of given lat/lon
Routine interface (API) collects the accordingly social media data with geographical coordinate.
In step S1.2, the internal data structure being pre-designed is converted to every collected social media data, is wrapped
ID number containing user identifier, timestamp t, geographical location (x, y) and text message text form anonymous social media data
IDn (t, x, y, text).Social media data with accurate latitude and longitude coordinates are sent out by personal use mobile device application program
Cloth geo-location.
Step S1.3 can carry out the social media data being collected into using keyword " earthquake " and " earthquake "
Filtering.
Step S1.4 is specifically included:
Filtered social media data are segmented, and delete URL wherein included, number and stop words.
By being pre-processed original social media text to reduce statistical noise, segmented, and delete and wherein wrap
The URL contained, number and stop words.Such as use Natural Language Toolkit (NLTK；http://
Www.nltk.org/ stop words is deleted in the predefined list of the standard) provided.
Step S1.5 training machine Study strategies and methods carry out real-time grading to the social media data of acquisition, extract and ground
Shake related data.Support vector machines (SVM) can be used and carry out structural classification device, use LIBSVM as machine learning algorithm.Most
Classify eventually for the social media data of each acquisition: 1 is related to event, and 0 is uncorrelated to event.Sorting algorithm SVM
For the prior art, reference can be made to pertinent literature: Zhang, D. , &Lee, W.S.2003.Question classification
using support vector machines.In Proceedings of the 26th annual international
ACM SIGIR conference on Research and development in information retrieval
(pp.26-32).ACM.This will not be detailed here.
Step S1.6 can define a signal-to-noise ratio (SNR for earthquake disaster in a period of time TT), according to
Signal-to-noise ratio come determine data acquisition period of time T.Signal-to-noise ratio is defined as follows:
Wherein, high SNRTValue can guarantee more effective zone of action.
Case theory influence area needs to be determined in advance.Since seismic wave is propagated outward by focus, earthquake is not
It takes place at the same instant on all regions being affected by it, US Geological Survey provides earthquake and theoretically reaches distance
The time Estimate function (angular distance is sphere centre angle) in the place of earthquake centre difference angular distance, as follows:
WhereinWithIndicate that the latitude of hair push position and earthquake centre, Δ λ refer to its difference of longitude.It so can use seismic wave to exist
The range influenced in seismic theory is estimated in the position that different time reaches, to carry out correction data.For different weeks time
For phase T, Signal to Noise Ratio (SNR)THigher, the data of acquisition can more be considered as transducing signal.For data volume, period of time T
Longer, the data volume of acquisition is bigger, is more advantageous to experimental detection.Need the Signal to Noise Ratio (SNR) to different period of time TTIt carries out
It calculates, the time threshold of appropriate events is selected according to result, carry out the extraction of social media transducing signal.The present invention is according to history number
According to be calculated signal-to-noise ratio after 10min after the earthquake for highest when.
Step S2: according to the social media transducing signal data extracted, spatial statistics, building are carried out in conjunction with demographic data
Data space logic model of growth.
Fig. 2 is referred to, is the Technology Roadmap of the detection method of earthquake disaster coverage provided by the invention, it is main to wrap
Transducing signal is included to extract and space distribution rule two processes of modeling.Wherein, transducing signal extraction process, with social media data
As input, data prediction is carried out, obtains transducing signal using classifier and time threshold.Space distribution rule modeled
Journey carries out space statistical analysis in conjunction with demographic data and the transducing signal extracted, reflects to model parameter and disaster-stricken range
It penetrates, so that constructing space increases logical model, and then logical model is increased to space and carries out parameter Estimation, obtain final detection
As a result.
Wherein, step S2 is specifically included:
Step S2.1: determining spatial statistics distance interval, calculates the loop buffer apart from seismic centre c different distance interval
Social media transducing signal quantity and the size of population in area；
Step S2.2: the size of population in the calculated buffer circle apart from seismic centre c different distance interval is utilized
Social media signal data is standardized, unit population is obtained and issues transducing signal quantity；
Step S2.3: unit population issues transducing signal number after the standardization within the scope of statistical distance seismic centre distance r
According to quantity MPr and r between numerical relation, using structural simulation S type citizen's sensor number of classical logic Growth Function
According to growth curve, spatial logic model of growth SLGM is constructed, wherein SLGM is defined as follows:
Wherein, MP (r) indicates that population standardizes social media transducing signal cumulative amount within the scope of seismic centre r,
rmFor the range index in earthquake effect region, K is quantity and l after standardization0For maximum space growth rate, e is natural constant.
Specifically, the present invention determines that spatial statistics distance interval is 1km by largely practice and research.Then, it counts
Calculate the buffer circle (c apart from seismic centre c different distance interval；ri,ri+1) in social media transducing signal quantityAnd the size of populationAnd period of time T is set to 10min in step 1.6.
Wherein, step S2.1 is specifically included:
Step S2.2.1: centered on earthquake centre, the buffer area apart from earthquake centre different distance interval is generated, wherein buffer area
Each distance interval is 1km；
Step S2.2.2: carrying out erasing analysis to adjacent buffer area, obtains ring buffer, counts in ring buffer
The size of population and social media transducing signal quantity.
In step S2.2, social media signal data is standardized using the size of population.Obtain the publication of unit population
Transducing signal quantityWherein, the population for the 1km*1km that demographic data uses U.S. LandScan in 2012 to provide
According to.LandScan population in the world dynamic statistics analytical database be the whole world it is the most accurate, it is reliable, there is distributed model and best point
The population in the world dynamic statistics of resolution analyze data, specifically may refer to network address (http://web.ornl.gov/sci/ landscan/)。
In the spatial logic model of growth SLGM of step S2.3 building, r is not reached apart from seismic centre positionmWhen, number
Increase according to spatial growth rate；R is reached apart from seismic centre positionmAfterwards, spatial growth rate is begun to decline, and data cumulant MP is not
It is disconnected to increase, until reaching K.Earthquake, which causes casualties, is located at r with the region of property lossmLeft side, safety zone are located at rmIt is right
Side.
In building spatial logic model of growth SLGM, S3 is thened follow the steps: utilizing the data space logic model of growth
Earthquake disaster coverage is detected.
Crucial improvement of the invention is to be to propose:
(1) it adopts and the analysis method of time-based theory is introduced into spatial analysis, construct citizen's sensor after earthquake
The spatial logic model of growth of data, carrys out the ability of rich space data mining.Use the simple of classical logic Growth Function
Structure simulates S type citizen's sensing data growth curve.
(2) the social media data relevant to earthquake selected and corresponded in the time cycle after the earthquake are deleted according to signal-to-noise ratio
For social media transducing signal data, to guarantee more effective zone of action.
(3) spatial statistics distance interval is calculated according to the resolution ratio of demographic data apart from seismic centre different distance interval
Demographic data and social media transducing signal data, provide basis for the building of model.
(4) using horizontal axis as epicentral distance, the longitudinal axis is that accumulation normalizated unit population social media transducing signal data draw number
According to space growth curve.It is fitted using the spatial logic model of growth of proposition, and parameter is solved according to maximum likelihood method, from
And reach the quick detection to earthquake coverage.
Specifically, step S3 is specifically included:
Using the parameter of maximum likelihood estimate estimation space logic model of growth, solves and obtain rmFor earthquake disaster influence
Range.
Specifically, the present invention also utilize US Geological Survey USGS issue shakeMap (http: //
Earthquake.usgs.gov/shakemap) official's data construct three indexs, carry out to method proposed by the present invention
Verifying.Specific evaluation index is as follows:
X, detection result accurate rate
Y, detection result recall rate
Z-measure, detection result and official's data degree of agreement
Testing result is more accurate, and Z-measure value is closer to 1.
Wherein, detection result region area, which refers to, is damaged using calculated cause casualties of method of the invention with property
The earthquake disaster coverage of mistake.The region ShakeMap earthquake intensity >=V, detecting for official can cause casualties damages with property
The range of mistake.Detection result region and ShakeMap earthquake intensity are to be shipped using the calculated range of the present invention and asking for official range
It calculates, the region area of obtained intersection is equivalent to the accurate of a detection result divided by the area of the calculated range of the present invention
It spends (similar to the accurate rate and recall rate of text classification).
The present invention utilizes the transducing signal feature of social media data, and logic-based model of growth proposes a kind of earthquake
Social media social media transducing signal spatial logic model of growth after generation, and it is a kind of using social based on this model construction
The scheme of media quick detection earthquake effect range.By taking Nepal's earthquake in 2014 and Jiu Zhaigou earthquake in 2017 as an example, use
Social media data be respectively to push away special and microblogging, the side proposed is proved using different earthquakes and different social medias
The unbiasedness of method.
Fig. 3~Fig. 6 is referred to, by studying two earthquake cases, it is found that model proposed by the present invention can have
Effect, the space propagation process for quantitatively expressing social media transducing signal data after earthquake, and effectively quickly estimate earthquake shadow
Ring range.Fig. 3 and Fig. 4 illustrates the result of two earthquake cases detection.Fig. 5 and Fig. 6 be respectively and official's comparative evaluation result.
For Nepal's earthquake, the Z-measure of detection is 71.74%.52.37% region detected using SLGM is corresponding
Earthquake intensity is greater than or equal to the region (X=52.37% of V in ShakeMap；Earthquake intensity is big in 91.11% ShakeMap
(Y=91.11%) is detected by SLGM in or equal to the region of V.For Jiu Zhaigou earthquake, as shown in figure 4, in ShakeMap
Region very identical (X=98.81%, Y=87.36%, the Z- that region of the shake intensity more than or equal to V and SLGM are detected
Measure=93.11%).
On the whole, technical solution of the present invention compared with prior art, is had the following advantages and beneficial effects:
The present invention utilizes the transducing signal feature of social media data, passes in conjunction with collected social media after the earthquake
Feel signal data and demographic data, the spatial distribution characteristic of express statistic data constructs spatial distribution model of growth, and discloses number
According to the mapping mechanism of spatial distribution and devastated, solves tradition using the side of the social media data detection disaster-stricken range of earthquake
Method is limited by the problem that social media data volume relies on and the response time is long, can not need the item of priori knowledge in a short time
Under part, quickly estimates earthquake effect region, reference is provided for Emergency decision, to further detect finer disaster-stricken model
It encloses.The present invention has Emergency decision certain help.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, those skilled in the art can carry out various modification and variations without departing from this hair to the embodiment of the present invention
The spirit and scope of bright embodiment.In this way, if these modifications and variations of the embodiment of the present invention belong to the claims in the present invention
And its within the scope of equivalent technologies, then the present invention is also intended to include these modifications and variations.
Claims (6)
1. a kind of detection method of the earthquake disaster coverage based on social media characterized by comprising
Step S1: determining the time cycle according to the signal-to-noise ratio of setting, from the social media data towards earthquake disaster of acquisition
Extract social media transducing signal data, wherein signal-to-noise ratio is to be pushed away literary number by event influence area in a time cycle
Amount and the ratio that literary sum is pushed away in the time cycle；
Step S2: according to the social media transducing signal data extracted, spatial statistics is carried out in conjunction with demographic data, construct data
Spatial logic model of growth；
Step S3: earthquake disaster coverage is detected using the data space logic model of growth.
2. the method as described in claim 1, which is characterized in that step S1 is specifically included:
Step S1.1: social media data of the acquisition towards earthquake disaster；
Step S1.2: the social media data of acquisition are formatted, the format of internal preset is converted into；
Step S1.3: the social media data after format conversion are filtered based on keyword；
Step S1.4: filtered social media data are pre-processed；
Step S1.5: training machine Study strategies and methods carry out real-time grading to pretreated social media data are carried out, extract
Out with earthquake related data；
Step S1.6: determining the time cycle according to signal-to-noise ratio, from obtaining in step S1.5 and filter out in earthquake related data
The social media transducing signal data of corresponding time cycle.
3. the method as described in claim 1, which is characterized in that step S2 is specifically included:
Step S2.1: determining spatial statistics distance interval, calculates in the buffer circle apart from seismic centre c different distance interval
Social media transducing signal quantity and the size of population；
Step S2.2: using the size of population in the calculated buffer circle apart from seismic centre c different distance interval to society
It hands over media signal data to be standardized, obtains unit population and issue transducing signal quantity；
Step S2.3: unit population publication transducing signal data after the standardization within the scope of statistical distance seismic centre distance r
Numerical relation between quantity MPr and r is increased using structural simulation S type citizen's sensing data of classical logic Growth Function
Long curve constructs spatial logic model of growth SLGM, and wherein SLGM is defined as follows:
Wherein, MP (r) indicates that population standardizes social media transducing signal cumulative amount, r within the scope of seismic centre rmFor ground
The range index of influence area is shaken, K is quantity and l after standardization0For maximum space growth rate, e is natural constant.
4. the method as described in claim 1, which is characterized in that step S3 is specifically included:
Using the parameter of maximum likelihood estimate estimation space logic model of growth, solves and obtain rmFor earthquake disaster coverage.
5. method according to claim 2, which is characterized in that step S1.4 is specifically included:
Filtered social media data are segmented, and delete URL wherein included, number and stop words.
6. method as claimed in claim 3, which is characterized in that step S2.1 is specifically included:
Step S2.1.1: centered on earthquake centre, the buffer area apart from earthquake centre different distance interval is generated, wherein buffer area is each
Distance interval is 1km；
Step S2.1.2: carrying out erasing analysis to adjacent buffer area, obtains ring buffer, counts the population in ring buffer
Quantity and social media transducing signal quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910589007.4A CN110426735A (en) | 2019-07-02 | 2019-07-02 | A kind of detection method of the earthquake disaster coverage based on social media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910589007.4A CN110426735A (en) | 2019-07-02 | 2019-07-02 | A kind of detection method of the earthquake disaster coverage based on social media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110426735A true CN110426735A (en) | 2019-11-08 |
Family
ID=68410004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910589007.4A Pending CN110426735A (en) | 2019-07-02 | 2019-07-02 | A kind of detection method of the earthquake disaster coverage based on social media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110426735A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767219A (en) * | 2021-02-03 | 2021-05-07 | 上海交通大学 | Post-earthquake disaster population rapid space assessment method and system based on machine learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021508A (en) * | 2016-05-23 | 2016-10-12 | 武汉大学 | Sudden event emergency information mining method based on social media |
| CN106897400A (en) * | 2017-02-10 | 2017-06-27 | 中国农业大学 | The method for visualizing and system of earthquake information in a kind of network social intercourse media |
| CN107908636A (en) * | 2017-09-26 | 2018-04-13 | 武汉大学 | A kind of method that mankind's activity spatiotemporal mode is excavated using social media |
| CN108829806A (en) * | 2018-06-07 | 2018-11-16 | 中南大学 | Across the evental news text emotion analysis methods of one kind |
| CN108960481A (en) * | 2018-05-22 | 2018-12-07 | 北京师范大学 | Earthquake disaster injures and deaths population estimation method and computer-readable medium |
| CN109063983A (en) * | 2018-07-18 | 2018-12-21 | 北京航空航天大学 | A kind of natural calamity loss real time evaluating method based on social media data |
-
2019
- 2019-07-02 CN CN201910589007.4A patent/CN110426735A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021508A (en) * | 2016-05-23 | 2016-10-12 | 武汉大学 | Sudden event emergency information mining method based on social media |
| CN106897400A (en) * | 2017-02-10 | 2017-06-27 | 中国农业大学 | The method for visualizing and system of earthquake information in a kind of network social intercourse media |
| CN107908636A (en) * | 2017-09-26 | 2018-04-13 | 武汉大学 | A kind of method that mankind's activity spatiotemporal mode is excavated using social media |
| CN108960481A (en) * | 2018-05-22 | 2018-12-07 | 北京师范大学 | Earthquake disaster injures and deaths population estimation method and computer-readable medium |
| CN108829806A (en) * | 2018-06-07 | 2018-11-16 | 中南大学 | Across the evental news text emotion analysis methods of one kind |
| CN109063983A (en) * | 2018-07-18 | 2018-12-21 | 北京航空航天大学 | A kind of natural calamity loss real time evaluating method based on social media data |
Non-Patent Citations (3)
| Title |
|---|
| ANDREW CROOKS等: ""#Earthquake: Twitter as a Distributed Sensor System"", 《TRANSACTIONS IN GIS》 * |
| YANDONG WANG 等: ""Rapid estimation of an earthquake impact area using a spatial logistic growth model based on social media data"", 《INTERNATIONAL JOURNAL OF DIGITAL EARTH》 * |
| 王艳东 等: ""基于社交媒体的突发事件应急信息挖掘与分析"", 《武汉大学学报(信息科学版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767219A (en) * | 2021-02-03 | 2021-05-07 | 上海交通大学 | Post-earthquake disaster population rapid space assessment method and system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106716382B (en) | The method and system of aggregation multiple utility program behavioural analysis for mobile device behavior | |
| Fortin et al. | On the role of spatial stochastic models in understanding landscape indices in ecology | |
| CN105740615B (en) | Utilize the method for the mobile phone trajectory track infection sources and prediction disease transmission trend | |
| Li et al. | Using user generated online photos to estimate and monitor air pollution in major cities | |
| CN107749859B (en) | Malicious mobile application detection method for network encryption traffic | |
| TWI776309B (en) | Recurrent artificial neural network, method implemented by a recurrent artificial neural network system, and neural network device | |
| Li et al. | Introduction to social sensing and big data computing for disaster management | |
| CN107209818A (en) | The method and system protected for improved Malware is interacted with the fictitious users of mobile device for detecting | |
| WO2017003593A1 (en) | Customized network traffic models to detect application anomalies | |
| CN104915944B (en) | A kind of method and apparatus for determining the black surround location information of video | |
| DE202016006038U1 (en) | Detect the location of a mobile device based on semantic indicators | |
| EP3274871A1 (en) | Area modeling by geographic photo label analysis | |
| Liu et al. | Modeling the effect of scale on clustering of spatial points | |
| KR101919098B1 (en) | Earthquake detection system and method | |
| CN110426735A (en) | A kind of detection method of the earthquake disaster coverage based on social media | |
| Vijay et al. | Seismicity analysis using space-time density peak clustering method | |
| CN110197375A (en) | A kind of similar users recognition methods, device, similar users identification equipment and medium | |
| CN116401311B (en) | Three-dimensional visual data management system and method based on GIS | |
| WO2018210039A1 (en) | Data processing method, data processing device, and storage medium | |
| Yang et al. | Anomaly behaviour detection based on the meta-Morisita index for large scale spatio-temporal data set | |
| CN111753587B (en) | Ground falling detection method and device | |
| Menafoglio et al. | O2S2: a new venue for computational geostatistics | |
| CN111915378A (en) | User attribute prediction method, device, computer equipment and storage medium | |
| KR101744776B1 (en) | Apparatus for estimating a floating population using records of search maps and method thereof | |
| Chamikara et al. | SL-SecureNet: intelligent policing using data mining techniques |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191108 |
|
| RJ01 | Rejection of invention patent application after publication |