CN107609682A - Population agglomeration middle or short term method for early warning under a kind of big data environment - Google Patents
Population agglomeration middle or short term method for early warning under a kind of big data environment Download PDFInfo
- Publication number
- CN107609682A CN107609682A CN201710726883.8A CN201710726883A CN107609682A CN 107609682 A CN107609682 A CN 107609682A CN 201710726883 A CN201710726883 A CN 201710726883A CN 107609682 A CN107609682 A CN 107609682A
- Authority
- CN
- China
- Prior art keywords
- mtd
- msubsup
- mrow
- thiessen
- population
- 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
Landscapes
- Mobile Radio Communication Systems (AREA)
- Alarm Systems (AREA)
Abstract
The purpose of the present invention is to utilize the mobile terminal individual at the appointed time activity data collection in scope and spatial dimension (i.e. the communications records of mobile terminal individual and fixed sensor), Thiessen polygons are divided to determine its control range according to the spatial distribution of fixed sensor, excavate the trip Time-space serial data of a large amount of individuals, one step state transition matrix of the individual in each Thiessen polygons is calculated using the method for Markov process, take this by the number of individuals in each Thiessen polygons of immediately monitoring, predict the possibility and mathematic expectaion of individual distribution in its following instant, early warning is carried out to extensive population agglomeration that may be present.In order to achieve the above object, the technical scheme is that providing population agglomeration middle or short term method for early warning under a kind of big data environment.The danger of the invention that potential extensive population agglomeration can be predicted effective and rapidly.
Description
Technical field
The present invention relates to a kind of population agglomeration applying based on magnanimity anonymity encryption times sequence location data and
Method for early warning, the individual trip Time-space serial data of magnanimity are built according to the time of individual and spatial position data, as sample
Originally it is trained, obtains position transfer probability characteristics of the individual in different time sections internal space；Calculated using Markov methods
Population in specified time point different zones predicts each region in future time period in the position of future time point and its probability
Population and its probability of happening, prediction result is taken to different population agglomeration Forewarning Measures by formulating early warning mechanism.
Background technology
With the quickening of urbanization process, increasing people pours in city, city public place crowd gathering event day
It is beneficial frequently, caused by consequence and influence also getting worse.Great or special event generation is often brought greatly in a short time
The passenger flow of scale, and easily trigger and gather, and the public place volume of the flow of passengers overload brought by population agglomeration so that it is various crowded and
Tread event occurs, and brings serious economic loss, causes bad social influence, serious threat social public security, to public affairs
Place crowd's safety guarantee proposes severe challenge altogether.On July 29th, 2008, India horse Harrar Shi Telabang provincial capital Bombay suburb
Morning on the 29th tramples accident, causes 16 people dead, nearly 20 people is injured；On December 31st, 2014, Shanghai City Huangpu District outbeach
Generation massed fall, laminate, and then cause swarm and jostlement event to occur, cause 36 people dead, 49 people injury September 25 in 2015
Day, pilgrim's tread event occurs for Saudi Arabia Meccah, causes at least 2177 people dead.Therefore, for by extensive passenger flow
Space-time characteristic extraction and analysis, middle or short term crowd's aggregation phenomenon is predicted and early warning, for carrying for municipal public safety
It is high most important.
In recent years, as explosive growth is presented in the development of information technology, data message amount, data source is more and more,
Data volume is also more and more huger.Wherein, the data recorded by information sensors such as mobile phone, WIFI, Internet of Things have become big number
According to most important data source in analysis, its more complete individual trip is recorded as big data, especially traffic big data point
Analysis provides good data and supported.By taking mobile phone as an example, to 2015, cellphone subscriber reached 13.06 hundred million, accounts for total population
More than 96%, mobile phone terminal equipment continues caused signal message, forms the volume of data collection of record user's trip, is big
Scale passenger flow produces and the population agglomeration phenomenon thus brought and its evolution Feature provide important data source.
The content of the invention
The purpose of the present invention is to utilize the mobile terminal individual at the appointed time activity data collection in scope and spatial dimension
(i.e. the communications records of mobile terminal individual and fixed sensor), it is more that Thiessen is divided according to the spatial distribution of fixed sensor
Side shape is excavated the trip Time-space serial data of a large amount of individuals, calculated using the method for Markov process to determine its control range
One step state transition matrix of the individual in each Thiessen polygons, takes this polygon by each Thiessen of immediately monitoring
Number of individuals in shape, the possibility and mathematic expectaion of individual distribution in its following instant are predicted, to extensive people that may be present
Mouth gathers carry out early warning.
In order to achieve the above object, the technical scheme is that providing short in population agglomeration under a kind of big data environment
Phase method for early warning, it is characterised in that comprise the following steps：
Step 1, system read the anonymous encryption mobile terminal sensing data obtained from sensor operator, anonymity encryption
Mobile terminal sensing data is continuous in the time and space, and different mobile terminal corresponds to different EPID, extracts each EPID
The communication signaling record at the appointed time triggered in section, form the trip track data collection of the EPD；
The positional information of step 2, all fixed sensors of extraction, carries out Cluster merging processing to it, then calculates
Voronoi diagram, the actual control range of each sensor is obtained, i.e., the Thiessen polygons of each sensor, record is each
The area of Thiessen polygons, set the three-level population carrying threshold value of each Thiessen polygons；
Step 3, trip track data collection of each EPID at the appointed time in section is extracted successively, arranged in chronological order
Sequence；From start time t0, on room and time, row interpolation is entered to trip track data using T as time interval, established out
Row Time-space serial data set；The each point gone on a journey on Time-space serial data set is mapped on Voronoi diagram, assigns each point pair
The numbering for the Thiessen polygons answered；
Step 4, track data that all user goes on a journey are divided into working day, weekend and common red-letter day, great festivals or holidays three
Class, all Thiessen polygons are traveled through, from start time t0, inquire about each Thiessen polygons on the same type date
In the EPID in each period T daily, search the EPID in the position at next moment, statistics t is at certain
EPID in Thiessen polygons goes to the frequency of other Thiessen polygons in subsequent time, and institute is calculated by large sample
There is a step transition probability of EPID states between Thiessen polygons, form all Thiessen polygons in t
Markov Matrix of shifting of a step；
Step 5, the three-level population carrying threshold value formulated according to step 2 set extensive population agglomeration early warning mechanism, in real time
The quantity of EPID in each Thiessen polygons is monitored, and expands sample according to a certain percentage；If certain moment, some Thiessen was more
The density of population in the shape of side reaches the density of population carrying threshold value of lowest level, that is, opens yellow warning, using the moment as starting point,
Predict that the Thiessen polygons and its periphery Thiessen the polygons population in future time section T are total using Markov methods
Measure the mathematic expectaion of size and maximum population gathers the probability of generation；
Step 6, according to Markov methods constantly based on each in the next phase target zone of previous phase prediction of result
The All population capacities and the density of population of Thiessen polygons, decided whether to open the orange of higher level according to the rule pre-established
With red alert and implement necessary evacuation work, or reduce warning level, until releasing warning yellow, stop prediction and calculate,
Recover normal monitored state.
Preferably, the step 1 includes：
The anonymous encryption mobile terminal sensing data that step 1.1, system reading obtain from sensor operator, anonymity add
Close mobile terminal sensing data is continuous in the time and space, and anonymity encryption mobile terminal sensing data includes：With
Moment TIME, great Qu residing for sensor occur for family unique number EPID, communication operation type TYPE, communication operation
REGIONCODE, sensing implement body numbering SENSORID, wherein, great Qu REGIONCODE residing for sensor and sensing implement body are compiled
Number SENSORID constitutes sensor number；
Step 1.2, an anonymous encryption mobile terminal sensing data are that a signaling records, every signaling is recorded into
Row decryption；
Step 1.3, according to EPID, inquire about its at the appointed time signaling record all in section, structure and current EPID phases
Corresponding trip track data collection.
Preferably, the step 2 includes：
The sensor number and its corresponding latitude and longitude coordinates LON-LAT of all fixation sensors of step 2.1, extraction,
Latitude and longitude coordinates are converted into geographical coordinate X-Y；
Step 2.2, sensor record importing GIS software will be fixed, by overlapping fixation on vertical space
Sensor merges into a fixed sensor, carries out cluster analysis to the locus of fixed sensor on this basis, if poly-
Class radius is rds, then fixation sensor of the mutual distance less than rds is merged into a fixed sensor, take and be merged
Fixation sensor locus position of the center of gravity as the fixation sensor after merging, be all fixed sensings after merging
Device renumbers；
Step 2.3, selection create Thiessen polygons, create to fix Voronoi of the sensor as polygon center
Figure, an object is created for each Thiessen polygons, the numbering of i-th of Thiessen polygon is THi；
Step 2.4, will rearrange after the numbering of fixation sensor be associated with Thiessen polygons, if for some
For Thiessen polygons, there is multiple fixed sensors situation overlapping or close on vertical space, then by these quilts
The sensor number of the fixation sensor of merging all assigns the Thiessen polygons；
Step 2.5, the attribute imparting Thiessen polygons by geographical space, to weigh its population bearing capacity PCC, specifically
Including：Natural quality NC, land used attribute LUC, the construction situation CC in plot where current Thiessen polygons, for multiple solid
Determine situation of the sensor merging in a Thiessen polygon, then accordingly increase the population bearing capacity of the Thiessen polygons
PCC, if i-th of Thiessen polygon is made up of multiple plot, plot is divided into road plot, house plot, general plot again
And the population bearing capacity PCC in factory building plot, then i-th of Thiessen polygoniCalculation formula be：
In formula,AndRepresent respectively j-th of road plot, house plot, general plot and
The area in commercial facility plot；AndJ-th road plot, house are represented respectively
The bearing capacity of block, general plot and commercial facility plot；AndRepresent respectively j-th of road plot,
The number of plies in house plot, general plot and commercial facility plot；
Step 2.6, the three-level population carrying threshold value according to each Thiessen polygons of historical experience setting, i-th
The l levels population of Thiessen polygons carries threshold valueThen have：
In formula, alFor l level population agglomeration threshold value of warning.
Preferably, the step 3 includes：
The trip track data collection of step 3.1, all EPID of traversal, arranged by triggering call duration time TIMESTAMP orders,
Trip track data collection is begun stepping through from start time, adjacent every 3 signaling measuring points are fitted a conic section, secondary song
The X-axis of line is the timeline of user's trip track, and Y-axis is the X-Y coordinate of signaling measuring point, if so trip track bag of user
Containing n communications records point, then need to fit 2n-4 bar conic sections altogether；
Step 3.2, from integer start time t0, T calculates X-Y of the user at each time point and sat at timed intervals
Mark, same time X (t0+nT) and Y (one interpolation point of (t0+nT) composition, all interpolation points sort in chronological order, will when
Between the nearest interpolation point of upper distance original measuring point be set to interpolation measuring point, all interpolation points form the trip Time-space serial number of users
According to；
Step 3.3, the X-Y coordinate according to each interpolation point in user's trip Time-space serial data, are carried out with Voronoi diagram
Space correlation, its Thiessen polygon is numbered to each interpolation point assigned in user's trip Time-space serial data.
Preferably, the step 4 includes：
Step 4.1, all Thiessen polygons of traversal, create object, from the time for each Thiessen polygons
Point t0 sets out, and the EPID that Thiessen polygons are in moment t is searched in going on a journey Time-space serial data from user, by the EPID
With interpolation point or interpolation measuring point deposit user's communication list Temp_EPID_LIST of the EPID；
Step 4.2, traversal Temp_EPID_LIST, search each EPID in Thiessen polygons corresponding to the t+1 moment
Numbering, be stored in user's subsequent time where Thiessen polygon lists Temp_Th_List；
Step 4.3, Temp_Th_List is read, it is more to be deposited into Thiessen in the form of dynamic array AppendlList
Side shape TH variable MarMatrix [t] .Freq, if the code T H-ID of some Thiessen polygon in Temp_Th_List
MarMatrix [t] .Freq is present in, then its frequency is added 1, if being not present, this TH-ID is added to MarMatrix
In [t] .Freq, and its frequency is set to 1；
Temp_EPID_LIST is read, counts sum between interpolation point and interpolation measuring point, sample ratio is expanded in deposit
MarMatrix[t].EnlargeProp；
Step 4.4, after having traveled through Temp_Th_List, according to MarMatrix [t] .Freq, moment t is counted at i-th
Thiessen polygons THiEPID, in moment t+1 spatial distribution, user is calculated in moment t at i-th with this
Thiessen polygons THiA step transition probability, i.e., user from moment t to t+1 from i-th of Thiessen polygons THiTransfer
To n-th of Thiessen polygons THnProbabilityBe all EPID from moment t to t+1 from i-th of Thiessen polygon
THiIt is transferred to n-th of Thiessen polygons THnSum divided by be in i-th of Thiessen polygons TH in moment ti's
EPID sum；
Then i-th of Thiessen polygon is in the Markov Matrix of shifting of a step of t：
All Thiessen polygons are in the Markov Matrix of shifting of a step of t：
Preferably, the step 5 includes：
Step 5.1, the three-level density of population threshold value of each Thiessen polygons are set to yellow warning, the orange alert respectively
And red alert, wherein, the three-level density of population threshold value of i-th of Thiessen polygon is respectively
Communication user quantity of each fixed sensor of step 5.2, in real time monitoring in each specified time section, with expansion sample
It is the total of present period fixation sensor place Thiessen polygons that ratio MarMatrix [t] .EnlargeProp, which expands sample,
Number of users, then total amount expands total people that sample ratio EnlargeRadio expands in sample to the present period Thiessen polygons per capita
Number；
If i-th of Thiessen polygons TH in step 5.3, current time tiThe density of populationReach one-level
Density of population threshold value of warningThen open yellow warning；
If step 5.4, i-th of Thiessen polygons THiYellow warning is opened in moment t, then with i-th
Thiessen polygons THiCentered on, the population size in moment t+1 comprising Thiessen polygons adjacent thereto is calculated,
With i-th of Thiessen polygons THiAdjacent Thiessen polygons THjShared K adjacent Thiessen polygons, then
Thiessen polygons THjIt is in moment t+1 population size
In formula,For with Thiessen polygons THjK-th adjacent of Thiessen polygons THkIn moment t people
Mouth size,From Thiessen polygons TH from moment t to t+1kIt is transferred to Thiessen polygons THjProbability；
Step 5.5, with Thiessen polygons THiCentered on, Thiessen polygons TH when calculating moment t+1iPopulation
Density exceedesWithPossibility, comprise the following steps：
Step 5.5.1, to Thiessen polygons THiAround Thiessen polygons within two layers, according to its when
Thiessen polygons TH is transferred between quarter t to t+1iProbability be ranked up from big to small；
Step 5.5.2, with Thiessen polygons THiIt is radix in moment t population, it is assumed that in moment t to t+1,
Thiessen polygons THiPopulation all stay in Thiessen polygons THi, its population isProbability is
Step 5.5.3, the Thiessen polygons after traversal sequence, wherein j-th of Thiessen polygons THjPeople exist
Moment t+1 is completely transferred to Thiessen polygons THiProbability beAssuming that j-th of Thiessen polygons THjNext
Moment is transferred completely into Thiessen polygons THi, then Thiessen polygons TH during moment t+1iMaximum possible population isProbability isCalculate now Thiessen polygons THiThe density of population, if exceedingThen record Thiessen polygons THiExceed in moment t+1Probability be
Step 5.5.4, the Thiessen polygons after traversal sequence are continued, wherein z-th of Thiessen polygons THz's
People is completely transferred to Thiessen polygons TH in moment t+1iProbability beAlso assume that it is all shifted in subsequent time
To Thiessen polygons THi, then Thiessen polygons TH during moment t+1iMaximum possible population isProbability is
Step 5.5.5, using with after the traversed n Thiessen polygons of step 5.5.3 and 5.5.4 identical method,
Thiessen polygons THiMaximum possible population beProbability isUntil
Thiessen polygons THiThe maximum possible density of population be more thanRecord Thiessen polygons THiIn moment t+1
When exceedProbability be
Preferably, the step 6 includes：
Step 6.1, if Thiessen polygons TH is calculatediIn the moment t+1 density of populationIt is more thanOr it is more thanProbability be more than p1, then open yellow warning；
If step 6.2, Thiessen polygons THiIn the moment t+1 density of populationIt is more thanAnd
The density of population that adjacent Thiessen polygons around it be present in moment t+1 is more than D_THR2, or more than D_THR2Probability it is big
In p2, then the orange alert is opened, it is necessary to take the guard and evacuation measure of certain population agglomeration；
If step 6.3, Thiessen polygons THiIn the moment t+1 density of populationIt is more thanThen
The orange alert is directly opened, if the density of population of the adjacent Thiessen polygons in moment t+1 around it on this basis be present
It is more thanOr it is more thanProbability be more than p3, then open red alert, evacuation measure should be taken immediately；
If Thiessen polygons TH in step 6.4, calculating processiThe adjacent Thiessen polygons TH of surroundingjReach
Alarm threshold is higher than Thiessen polygons TH on the contraryi, then by Thiessen polygons THj, will for the central point of calculating
Thiessen polygons THiIt is reduced to Thiessen polygons THjAdjoining Thiessen polygons；
If step 6.5, in calculating process, Thiessen polygons THiIn the moment t+n density of populationIt is small
InAnd its density of population of adjacent Thiessen polygons in moment t+n is also both less thanThen release
Warning yellow.
The present invention is handled and screened for mobile terminal big data, is held by individual between mobile terminal and sensor
Communications records construct the Time-space serial data of individual trip, pass through the unified user of mathematical interpolation completion time interval and go on a journey
Time-space serial data, geographical background is divided into Thiessen polygons according to the locus of fixed sensor, passes through Markov
Method is trained to big-sample data, and calculating individual is transferred to another within each period from a Thiessen polygon
The probability of individual Thiessen polygons, the population of the following each Thiessen polygons sometime put of prediction based on this
Density；By three-level early warning mechanism, the population agglomeration situation of designated area is monitored in real time, for different warning levels, is taken
Corresponding evacuation measure.
It is an advantage of the invention that：The communication leveraged fully between mobile terminal and sensor that existing user holds counts greatly
, can be inexpensive, automatic using the lasting encryption position information of existing magnanimity anonymity mobile terminal in communication network according to resource
Change, the trip Time-space serial for easily obtaining a large amount of populations in the range of specified time, it is different as sample training different location
Individual space migrating probability in period, so as to predict the danger of potential extensive population agglomeration effective and rapidly.
Brief description of the drawings
Fig. 1 is the Voronoi diagram of this example generation.
Embodiment
To become apparent the present invention, hereby with preferred embodiment, and accompanying drawing is coordinated to be described in detail below.
Step 1, system read the anonymous encryption mobile terminal sensing data obtained from sensor operator, anonymity encryption
Mobile terminal sensing data is continuous in the time and space in theory, and different mobile terminal corresponds to different EPID, and extraction is every
The communication signaling record that individual EPID is at the appointed time triggered in section, form the trip data collection of the EPID.
Anonymity encryption mobile terminal sensing data is operator from mobile communications network, fixed broadband network, wireless
WIFI and location-based service correlation APP etc. are obtained in real time and the encrypted location for the anonymous cellphone subscriber's time series after encrypting that desensitizes
Information, content include：EPID, TYPE, TIME, REGIONCODE, SENSORID, referring to Application No. 201610273693.0
Chinese patent.It is specifically described as follows：
EPID (anonymous One-Way Encryption whole world unique mobile terminal identification code, EncryPtion international
Mobile subscriber IDentity), it is that unidirectional irreversible encryption is carried out to each mobile terminal user, so as to uniquely mark
Know each mobile terminal user, and do not expose Subscriber Number privacy information, it is desirable to the EPID after each mobile terminal user's encryption
Uniqueness is kept, i.e. the EPID of any time each cellphone subscriber keeps constant and do not repeated with other cellphone subscribers.
TYPE, it is the communication operation type involved by current record, e.g., online, call, calling and called, transmitting-receiving short message, GPS
Positioning, the switching of sensor cell, sensor switching, switching on and shutting down etc..
TIME, it is that the moment occurs for the communication operation involved by current record, unit is millisecond.
REGIONCODE, SENSORID are the sensor encrypted bits confidences that the communication operation involved by current record occurs
Breath.The numbering of REGIONCODE, SENSORID sensor, great Qu, SENSORID wherein residing for REGIONCODE representative sensors
It is the numbering of specific sensor.
Step 1.1, system read from sensor operator and obtain anonymous encryption mobile terminal sensing data, hide in theory
Name encryption mobile terminal sensing data all should be continuous in the time and space, including：User's unique number EPID, lead to
Believe type of action TYPE, communication operation moment TIME occurs, great Qu REGIONCODE, sensing implement body numbering residing for sensor
SENSORID；Wherein, great Qu REGIONCODE residing for sensor and sensing implement body numbering SENSORID constitute sensor volume
Number；
Step 1.2, an anonymous encryption mobile terminal sensing data are that a signaling records, every signaling is recorded into
Row decryption；
Step 1.3, according to Customs Assigned Number EPID, inquire about its at the appointed time signaling record all in section, build user
Trip data；
In this example, the real-time signaling record data for extracting obtained user and sensor is：
Table 1：The real-time signaling record data newly received after decryption
| RECORDID | EPID | TYPE | TIMESTAMP | REGIONCODE | SENSORID |
| …… | …… | …… | …… | …… | …… |
| R101 | E1 | T1 | 2017-04-12 13:05:24 | 9540 | 9784 |
| R102 | E1 | T2 | 2017-04-12 11:01:26 | 9540 | 5781 |
| R103 | E1 | T1 | 2017-04-12 11:01:48 | 9540 | 7675 |
| R104 | E1 | T2 | 2017-04-12 11:01:48 | 9540 | 2746 |
| …… | …… | …… | …… | …… | …… |
| R301 | E1 | T1 | 2017-04-12 11:15:09 | 10408 | 8641 |
| R302 | E1 | T1 | 2017-04-12 11:16:45 | 10408 | 8642 |
| R303 | E1 | T1 | 2017-04-12 11:18:20 | 10408 | 8644 |
| R304 | E1 | T1 | 2017-04-12 11:18:48 | 10408 | 8513 |
| R305 | E1 | T1 | 2017-04-12 11:19:26 | 10408 | 8092 |
| …… | …… | …… | …… | …… | …… |
| R441 | E1 | T2 | 2017-04-12 11:35:21 | 9874 | 3325 |
| R442 | E1 | T2 | 2017-04-12 11:35:30 | 9874 | 2144 |
| R443 | E1 | T4 | 2017-04-12 11:35:59 | 9881 | 5744 |
| R444 | E1 | T1 | 2017-04-12 11:36:04 | 9875 | 7121 |
| …… | …… | …… | …… | …… | …… |
The positional information of step 2, all fixed sensors of extraction, carries out Cluster merging processing to it, then calculates it
Voronoi diagram, the actual control range (i.e. its Thiessen polygon) of each sensor is obtained, it is more to record each Thiessen
The area of side shape, the three-level population bearing capacity of each Thiessen polygons is set, is comprised the following steps：
Step 2.1, all fixation sensor number REGIONCODE-SENSORID of extraction and its corresponding longitude and latitude are sat
LON-LAT is marked, latitude and longitude coordinates are converted into geographical coordinate X-Y；
In this example, the numbering of fixed sensor and geographical coordinate are shown in Table 2：
Fixation sensors X-Y-coordinate after the conversion of the longitude and latitude of table 2
| REGIONCODE | SENSORID | X | Y |
| …… | …… | …… | …… |
| 9878 | 4796 | 64948.9426 | 120901.1132 |
| 9879 | 9721 | 68860.6841 | 132947.0579 |
| 9646 | 2716 | 65657.4389 | 120328.1643 |
| 9421 | 4523 | 72559.6835 | 118194.8941 |
| 9880 | 8095 | 68948.2975 | 114069.1227 |
| 9421 | 4041 | 72556.7439 | 118391.5958 |
| 9878 | 4339 | 63132.7352 | 120466.3362 |
| 10407 | 2086 | 61696.4767 | 113860.7929 |
| …… | …… | …… | …… |
Step 2.2, sensor record importing GIS software will be fixed, for multiple sensors in vertical space
Upper overlapping special circumstances, as each floor of commercial center has a sensor, then these sensors are merged into one；
Cluster analysis is carried out to the locus of fixed sensor on the basis of this, it is assumed that cluster radius rds, will be between each other apart from small
One is merged into rds fixation sensor, takes the center of gravity of locus for the sensor being merged as the sensing after merging
The position of device, is renumberd after merging for all the sensors；
The fixation sensor that table 3 renumbers after merging
Step 2.3, selection create Thiessen polygons, create to fix sensor as Thiessen polygons center
Voronoi diagram, an object is created for each Thiessen polygons, the numbering of i-th of Thiessen polygon is THi；
In this example, Thiessen polygons class includes following variable：
Polygon code T H-ID；
Population bearing capacity CAPACITY；
Density of population carrying threshold value D_THR；
Any instant t Markov transfer matrix class MarMatrix [t]；
Wherein, Markov transfer matrixes class includes following variable：
Moment t to t+1 user shifts the frequency MarMatrix [t] .Freq；
Moment t to t+1 user's transition probability MarMatrix [t] .P；
Moment t interpolation point and fitting measuring point ratio MarMatrix [t] .EnlargeProp；
Moment t measuring point and All population capacities ratio MarMatrix [t] .EnlargeRadio；
The Voronoi diagram of this example generation is as shown in Figure 1.
Step 2.4, the numbering of the sensor after rearranging is associated with Thiessen polygons, if there is step 2.2
In multiple sensors situation overlapping or close on vertical space, then by the numbering of these sensors being merged
REGIONCODE-SENSORID assigns the Thiessen polygons；
The Thiessen polygons of table 4 associate with fixed sensor
Step 2.5, the attribute imparting Thiessen polygons by geographical space, to weigh its population bearing capacity PCC；Specifically
Including：Natural quality NC (soil, river, lake), land used attribute LUC (road, the business in plot where the Thiessen polygons
Industry facility, residential land, general land used), construction situation CC (road grade, architecture storey number, population intake's ability)；For
Multiple sensors in step 2.2 merge the situation in a Thiessen polygon, then it is polygon accordingly to increase the Thiessen
The population bearing capacity PCC of shape；
In this example, the population bearing capacity of each Thiessen polygons is：
The population bearing capacity (people/square metre) of the Thiessen polygons of table 5
Step 2.6, three-level population carrying threshold value D_THR is set according to historical experience,alFor l levels
Population agglomeration threshold value of warning, the density of population just open early warning more than D_THR；
In this example, a is setl、al、alThe three-level threshold value of warning of respectively 0.9,1.1 and 1.3, then Thiessen polygons
For：
The three-level threshold value of warning of the Thiessen polygons of table 6
Step 3, trip track data collection of each EPID at the appointed time in section is extracted successively, it is entered in chronological order
Row sequence；From start time t0, on room and time, row interpolation is entered to trip data using T time as interval, established out
Row Time-space serial data set；The each point gone on a journey on Time-space serial data set is mapped on Voronoi diagram, assigns each point pair
The Thiessen polygons numbering answered, comprises the following steps：
User's trip track data that step 3.1, traversal step 1.3 obtain, by it by triggering call duration time TIMESTAMP
Order is arranged, and trip data is begun stepping through from start time, and adjacent every 3 communications records point is fitted a conic section, and two
The x-axis of secondary curve is the timeline of user's trip track, and y-axis is the X-Y coordinate of communications records point, if so trip rail of user
Mark includes n communications records point, then needs to fit 2n-4 bar conic sections altogether
In this example, the original trip data of user is：
Table 7 is associated with the original trip record of user of X-Y coordinate
| RECORDID | EPID | TYPE | TIMESTAMP | REGIONCODE | SENSORID | X | Y |
| …… | …… | …… | …… | …… | …… | …… | …… |
| R1 | E1 | T1 | 2017-04-30 07:58:17 | 9881 | 8835 | 66906.63 | 114996.29 |
| R2 | E1 | T4 | 2017-04-30 08:02:55 | 9881 | 8835 | 66906.63 | 114996.29 |
| R3 | E1 | T4 | 2017-04-30 08:04:57 | 9881 | 8835 | 66906.63 | 114996.29 |
| R4 | E1 | T3 | 2017-04-30 08:07:15 | 9881 | 8835 | 66906.63 | 114996.29 |
| R5 | E1 | T4 | 2017-04-30 08:12:15 | 9881 | 8813 | 67695.63 | 115742.55 |
| R6 | E1 | T1 | 2017-04-30 08:17:03 | 9881 | 8548 | 67895.97 | 115699.61 |
| R7 | E1 | T2 | 2017-04-30 08:21:04 | 9881 | 2101 | 68141.16 | 115533.00 |
| R8 | E1 | T2 | 2017-04-30 08:56:17 | 9881 | 8855 | 68450.68 | 115118.71 |
| R9 | E1 | T2 | 2017-04-30 09:26:18 | 9881 | 8855 | 68450.68 | 115118.71 |
| R10 | E1 | T4 | 2017-04-30 09:56:23 | 9881 | 6130 | 68366.52 | 114560.06 |
| R11 | E1 | T1 | 2017-04-30 10:56:28 | 9881 | 6130 | 68366.52 | 114560.06 |
| R12 | E1 | T1 | 2017-04-30 11:10:14 | 9881 | 6135 | 68899.23 | 114451.70 |
| R13 | E1 | T1 | 2017-04-30 11:33:28 | 9881 | 2849 | 68931.60 | 114652.72 |
| R14 | E1 | T1 | 2017-04-30 11:37:45 | 9881 | 2101 | 68939.49 | 114927.09 |
| R15 | E1 | T2 | 2017-04-30 11:44:09 | 9877 | 1857 | 68811.01 | 115143.33 |
| R16 | E1 | T1 | 2017-04-30 11:49:45 | 9877 | 5331 | 68818.71 | 115568.92 |
| R17 | E1 | T3 | 2017-04-30 12:00:30 | 9881 | 9457 | 68900.19 | 115793.66 |
| …… | …… | …… | …… | …… | …… | …… | …… |
Step 3.2, from integer start time t0, T calculates X-Y of the user at each time point and sat at timed intervals
Mark, same time X (t0+nT) and Y (one interpolation point of (t0+nT) composition, all interpolation points sort in chronological order, will when
Between the nearest interpolation point of upper distance original measuring point be set to interpolation measuring point, all interpolation points form the trip Time-space serial number of users
According to；
In this example, it is 15 minutes to make T, from 8:00 starts interpolation, then the interpolated data obtained is：
The interpolated data of table 8 and record data
| RECORDID | EPID | TYPE | TIMESTAMP | REGIONCODE | SENSORID | X | Y |
| …… | …… | …… | …… | …… | …… | …… | …… |
| R1 | E1 | T1 | 2017-04-30 07:58:17 | 9881 | 8835 | 66906.63 | 114996.29 |
| INS1 | 2017-04-30 08:00:00 | 66906.63 | 114996.29 | ||||
| R2 | E1 | T4 | 2017-04-30 08:02:55 | 9881 | 8835 | 66906.63 | 114996.29 |
| R3 | E1 | T4 | 2017-04-30 08:04:57 | 9881 | 8835 | 66906.63 | 114996.29 |
| R4 | E1 | T3 | 2017-04-30 08:07:15 | 9881 | 8835 | 66906.63 | 114996.29 |
| R5 | E1 | T4 | 2017-04-30 08:12:15 | 9881 | 8813 | 67695.63 | 115742.55 |
| INS2 | 2017-04-30 08:15:00 | 67797.82 | 115720.34 | ||||
| R6 | E1 | T1 | 2017-04-30 08:17:03 | 9881 | 8548 | 67895.97 | 115699.61 |
| R7 | E1 | T2 | 2017-04-30 08:21:04 | 9881 | 2101 | 68141.16 | 115533.00 |
| INS3 | 2017-04-30 08:30:00 | 68235.34 | 115436.54 | ||||
| INS4 | 2017-04-30 08:45:00 | 68364.56 | 115231.63 | ||||
| R8 | E1 | T2 | 2017-04-30 08:56:17 | 9881 | 8855 | 68450.68 | 115118.71 |
| INS5 | 2017-04-30 09:00:00 | 68450.68 | 115118.71 | ||||
| INS6 | 2017-04-30 09:15:00 | 68450.68 | 115118.71 | ||||
| R9 | E1 | T2 | 2017-04-30 09:26:18 | 9881 | 8855 | 68450.68 | 115118.71 |
| INS7 | 2017-04-30 09:30:00 | 68434.43 | 115012.52 | ||||
| INS8 | 2017-04-30 09:45:00 | 68382.57 | 114653.31 | ||||
| R10 | E1 | T4 | 2017-04-30 09:56:23 | 9881 | 6130 | 68366.52 | 114560.06 |
| INS9 | 2017-04-30 10:00:00 | 68366.52 | 114560.06 | ||||
| INS10 | 2017-04-30 10:15:00 | 68366.52 | 114560.06 | ||||
| INS11 | 2017-04-30 10:30:00 | 68366.52 | 114560.06 | ||||
| INS12 | 2017-04-30 10:45:00 | 68366.52 | 114560.06 | ||||
| R11 | E1 | T1 | 2017-04-30 10:56:28 | 9881 | 6130 | 68366.52 | 114560.06 |
| INS13 | 2017-04-30 11:00:00 | 68533.88 | 114523.91 | ||||
| R12 | E1 | T1 | 2017-04-30 11:10:14 | 9881 | 6135 | 68899.23 | 114451.70 |
| INS14 | 2017-04-30 11:15:00 | 68902.24 | 114487.71 | ||||
| INS15 | 2017-04-30 11:30:00 | 68926.88 | 114612.35 | ||||
| R13 | E1 | T1 | 2017-04-30 11:33:28 | 9881 | 2849 | 68931.60 | 114652.72 |
| R14 | E1 | T1 | 2017-04-30 11:37:45 | 9881 | 2101 | 68939.49 | 114927.09 |
| R15 | E1 | T2 | 2017-04-30 11:44:09 | 9877 | 1857 | 68811.01 | 115143.33 |
| INS16 | 2017-04-30 11:45:00 | 68812.86 | 115234.12 | ||||
| R16 | E1 | T1 | 2017-04-30 11:49:45 | 9877 | 5331 | 68818.71 | 115568.92 |
| INS17 | 2017-04-30 12:00:00 | 68894.23 | 115786.84 | ||||
| R17 | E1 | T3 | 2017-04-30 12:00:30 | 9881 | 9457 | 68900.19 | 115793.66 |
| …… | …… | …… | …… | …… | …… | …… | …… |
Step 3.3, the X-Y coordinate according to each interpolation point in user's trip Time-space serial data, are generated with step 2.3
The Voronoi diagram being made up of sensor distribution carries out space correlation, when its Thiessen polygon is numbered into imparting user's trip
Each interpolation point in null sequence data；
In this example, the association of the interpolation point of user and Thiessen polygons spatially is shown as：
The interpolation point of table 9 associates with Thiessen polygons
| RECORDID | TIMESTAMP | X | Y | TH-ID |
| …… | …… | …… | …… | …… |
| INS1 | 2017-04-30 08:00:00 | 66906.63 | 114996.29 | 162 |
| INS2 | 2017-04-30 08:15:00 | 67797.82 | 115720.34 | 117 |
| INS3 | 2017-04-30 08:30:00 | 68235.34 | 115436.54 | 97 |
| INS4 | 2017-04-30 08:45:00 | 68364.56 | 115231.63 | 67 |
| INS5 | 2017-04-30 09:00:00 | 68450.68 | 115118.71 | 61 |
| INS6 | 2017-04-30 09:15:00 | 68450.68 | 115118.71 | 61 |
| INS7 | 2017-04-30 09:30:00 | 68434.43 | 115012.52 | 61 |
| INS8 | 2017-04-30 09:45:00 | 68382.57 | 114653.31 | 72 |
| INS9 | 2017-04-30 10:00:00 | 68366.52 | 114560.06 | 91 |
| INSI0 | 2017-04-30 10:15:00 | 68366.52 | 114560.06 | 91 |
| INS11 | 2017-04-30 10:30:00 | 68366.52 | 114560.06 | 91 |
| INS12 | 2017-04-30 10:45:00 | 68366.52 | 114560.06 | 91 |
| INS13 | 2017-04-30 11:00:00 | 68533.88 | 114523.91 | 85 |
| INS14 | 2017-04-30 11:15:00 | 68902.24 | 114487.71 | 82 |
| INS15 | 2017-04-30 11:30:00 | 68926.88 | 114612.35 | 56 |
| INS16 | 2017-04-30 11:45:00 | 68812.86 | 115234.12 | 46 |
| INS17 | 2017-04-30 12:00:00 | 68894.23 | 115786.84 | 34 |
| …… | …… | …… | …… | …… |
Step 4, all user's trip datas are divided into working day, weekend and common red-letter day, the class of great festivals or holidays three, time
All Thiessen polygons are gone through, from start time t0, it is every in the same type date to inquire about each Thiessen polygons
EPID in its each period T, the EPID is searched in the position at next moment, it is more that the statistics some time is engraved in certain Thiessen
EPID in the shape of side, the frequency of other Thiessen polygons is gone in subsequent time, existed by large sample using EPID is calculated
A step transition probability of state between Thiessen polygons；
Step 4.1, traversal Thiessen polygons, create object, from start time t0 for each Thiessen polygons
Set out, searched in going on a journey Time-space serial data set from user and be in Thiessen polygons TH in moment tiUser EPID (i.e.
Moment, t was in THiHave the EPID of interpolation point), the attribute (interpolation point or interpolation measuring point) of its EPID and point deposit user is led to
Believe list Temp_EPID_LIST；
In this example, Thiessen polygons TH100On weekdays at the time of t Temp_EPID_LIST be：
The TH of table 10100In moment t user's communication list Temp_EPID_LIST
| TH-ID | EPID | TYPE |
| …… | …… | …… |
| 100 | E0441 | INS |
| 100 | E0087 | R |
| 100 | E0087 | INS |
| 100 | E0087 | R |
| 100 | E4002 | INS |
| 100 | E9875 | INS |
| 100 | E1931 | INS |
| 100 | E7638 | INS |
| 100 | E2836 | INS |
| 100 | E2836 | R |
| 100 | E1837 | INS |
| 100 | E5938 | INS |
| 100 | E5938 | INS |
| 100 | E2891 | INS |
| 100 | E6829 | INS |
| 100 | E2881 | R |
| 100 | E7892 | R |
| 100 | E1983 | INS |
| 100 | E1983 | INS |
| 100 | E1983 | INS |
| 100 | E1983 | INS |
| 100 | E1983 | INS |
| 100 | E5438 | INS |
| 100 | E0192 | INS |
| 100 | E9103 | INS |
| 100 | E8701 | INS |
| 100 | E4289 | R |
| 100 | E3429 | INS |
| 100 | E5431 | INS |
| 100 | E4366 | INS |
| …… | …… | …… |
Step 4.2, traversal Temp_EPID_LIST, it is corresponding in next moment t+1 to search each EPID
Thiessen polygons are numbered, the Thiessen polygon list Temp_Th_List being stored in where user's subsequent time, will
Temp_EPID_LIST and Temp_Th_List returns to Thiessen polygons THi；
In this example, TH100The list of locations Temp_Th_List of EPID at the time of on weekdays in t in moment t+1
For：
The TH of table 11100In moment t Temp_Th_List lists
| EPID | TH-ID |
| …… | …… |
| E0441 | 100 |
| E0087 | 98 |
| E0087 | 98 |
| E0087 | 99 |
| E4002 | 96 |
| E9875 | 90 |
| E1931 | 104 |
| E7638 | 100 |
| E2836 | 101 |
| E2836 | 103 |
| E1837 | 103 |
| E5938 | 103 |
| E5938 | 105 |
| E2891 | 99 |
| E6829 | 101 |
| E2881 | 87 |
| E7892 | 99 |
| E1983 | 103 |
| E1983 | 103 |
| E1983 | 103 |
| E1983 | 100 |
| E1983 | 103 |
| E5438 | 112 |
| E0192 | 96 |
| E9103 | 99 |
| E8701 | 100 |
| E4289 | 103 |
| E3429 | 103 |
| E5431 | 99 |
| E4366 | 100 |
| …… | …… |
Step 4.3, Temp_Th_List is read, it is more to be deposited into Thiessen in the form of dynamic array AppendlList
Side shape TH variable MarMatrix [t] .Freq, if some Thiessen polygon code T H-ID in Temp_Th_List is
It is present in MarMatrix [t] .Freq, then its frequency is added 1, if being not present, this TH-ID is added to MarMatrix [t]
.Freq in, and its frequency is set to 1；Temp_EPID_LIST is read, sum between interpolation point and interpolation measuring point is counted, deposits
Enter to expand sample ratio MarMatrix [t] .EnlargeProp；
In this example, TH100T MarMatrix [t] .EnlargeProp is 0.2158 at the time of on weekdays,
MarMatrix [t] .Freq is：
The TH of table 12100In moment t frequency statistics MarMatrix [t] .Freq
| TH-ID | Frequency |
| 103 | 1431 |
| 98 | 1034 |
| 100 | 783 |
| 99 | 204 |
| 96 | 134 |
| 104 | 32 |
| 102 | 13 |
| …… | …… |
Step 4.4, after having traveled through Temp_Th_List, according to MarMatrix [t] .Freq, count moment t and exist
Thiessen polygons THiUser EPID, in moment t+1 spatial distribution, user is calculated in moment t with this,
Thiessen polygons THiA step transition probability, i.e., user from moment t to t+1 from THiIt is transferred to THnProbability be all
EPID is from moment t to t+1 from THiIt is transferred to THnSum divided by be in TH in moment tiEPID sum；
In this example, TH100The step transition probability from moment t to t+1 is on weekdays：
The TH of table 13100Step transition probability MarMatrix [t] .P from moment t to t+1
Step 5, the three-level population carrying threshold value formulated according to step 2 set extensive population agglomeration early warning mechanism, in real time
The quantity of EPID in each Thiessen polygons is monitored, and expands sample according to a certain percentage；If certain moment, some Thiessen was more
The density of population in the shape of side reaches the density of population carrying threshold value of lowest level, that is, opens yellow warning, using the moment as starting point,
Predict that the Thiessen polygons and its periphery Thiessen the polygons population in future time section T are total using Markov methods
Measure the mathematic expectaion of size and maximum population gathers the probability of generation；
Step 5.1, foundation step 2.5, by the three-level density of population threshold value of each Thiessen polygonsIt is set to yellow warning, the orange alert and red alert respectively according to degree of danger；
In this example, Thiessen polygons TH100Population bearing capacity for 6.5378 people/square metre, the three-level density of population
Threshold value is respectively 5.8840,7.1916,8.4991.
Communication user quantity of each fixed sensor of step 5.2, in real time monitoring in each specified time section, with expansion sample
It is present period fixation sensor place Thiessen polygons TH that ratio MarMatrix [t] .EnlargeProp, which expands sample,i's
Total number of users, then total amount expands sample ratio EnlargeRadio expansion samples to the present period TH per capitaiInterior total number of persons；
In this example, Thiessen polygons TH100Moment t MarMatrix [t] .EnlargeProp is on weekdays
0.2158, it is 0.8732, TH that the total population that outside obtains, which expands sample ratio MarMatrix [t] .EnlargeRadio,100At the moment
The number of users of t records be 6529 people, then the number of users that full user expands after sample is 36784 people, the people after All population capacities expansion sample
Mouth is 42125 people；
If TH in step 5.3, current time tiThe density of populationReach THiOne-level density of population early warning threshold
ValueThen open yellow warning；
In this example, TH100Area be 7056 square metres, the moment t density of population reach 5.97 people/square metre, exceed
One-level density of population threshold value of warning, open yellow warning；
If step 5.4, Thiessen polygons THiYellow warning is opened in moment t, then with THiCentered on, calculate bag
Containing Thiessen polygons adjacent thereto moment t+1 population size；
In this example, TH is calculated100In moment t population TH is still remained in moment t+1100For 10995 people, from
The population that surrounding Thiessen polygons flow into is 42562 people, TH100It is 53557 people in moment t+1 population；
Step 5.5, with THiCentered on, TH when calculating moment t+1iThe density of population exceedWith's
Possibility, concretely comprise the following steps：
Step 5.5.1, to THiAround Thiessen polygons within two layers, shifted according to it between moment t to t+1
To THiProbability be ranked up from big to small；
Step 5.5.2, with THiIt is radix in moment t population, it is assumed that in moment t to t+1, THiPopulation all stay in
THi, its population isProbability is
Step 5.5.3, the Thiessen polygons after traversal sequence, Thiessen polygons j people shift completely in t+1
To THiProbability beAssuming that it is transferred completely into TH in subsequent timei, then TH during t+1iMaximum possible population isProbability isCalculate now THiThe density of population, if exceedingThen record THi
Exceed during t+1Probability be
Step 5.5.4, the Thiessen polygons after traversal sequence, Thiessen polygons TH are continuedzPeople it is complete in t+1
Total transfer is to THiProbability beAlso assume that it is transferred completely into TH in subsequent timei, then TH during t+1iMaximum possible population
ForProbability is
Step 5.5.5, after traversed n Thiessen polygons, THiMaximum possible population beProbability isUntil THiThe maximum possible density of population be more thanNote
Record THiExceed in t+1Probability be
In this example, TH is calculated100The density of population exceed in moment t+1Probability be 0.2154,
ExceedProbability be 0.1548；
Step 6, according to Markov methods constantly based on each in the next phase target zone of previous phase prediction of result
The All population capacities and the density of population of Thiessen polygons, decided whether to open the orange of higher level according to the rule pre-established
With red alert and implement necessary evacuation work, or reduce warning level, until releasing warning yellow, stop prediction and calculate,
Recover normal monitored state.
Step 6.1, if Thiessen polygons TH is calculatediIn the moment t+1 density of populationIt is more thanOr more than D_THR1Probability be more than p1, then open yellow warning；
If step 6.2, THiIn the moment t+1 density of populationIt is more thanAnd exist around it adjacent
The density of population of the Thiessen polygons in moment t+1 is more than D_THR2, or more than D_THR2Probability be more than p2, then open orange
Color is guarded against, it is necessary to take the guard and evacuation measure of certain population agglomeration；
If step 6.3, THiIn the moment t+1 density of populationIt is more thanThen directly open orange police
Guard against, if the density of population that adjacent Thiessen polygons around it on this basis be present in moment t+1 is more than D_THR3, or greatly
In D_THR3Probability be more than p3, then open red alert, evacuation measure should be taken immediately；
If TH in step 6.4, calculating processiThe adjacent Thiessen polygons TH of surroundingjThe alarm threshold reached on the contrary will
Higher than THi, then by THjIt is set to the central point of calculating, by THiIt is reduced to THjAdjoining Thiessen polygons；
If step 6.5, in calculating process, THiIn the moment t+n density of populationIt is less thanAnd
The density of population of its adjacent Thiessen polygon in moment t+n is also both less than D_THR1, then warning yellow is released；
In this example, it is respectively 0.6,0.4 and 0.25 to set probability threshold value p1, p2 and p3, and TH is calculated100Population
Density is desired for 7.5902 moment t+1's, exceedesMoment t+1 is not present in its adjacent Thiessen polygon
The density of population be more than D_THR2Situation, do not meet open orange warning standard, keep yellow warning；
Moment t+1, TH100The density of population be desired for 8.5245 people/square metre, exceedDirectly open orange
Warning, its adjacent Thiessen polygon density of population reach D_THR2, reach D_THR3Probability be respectively less than 0.1353, not
Reach p, open the orange alert；
Moment t+2, TH100The density of population be desired for 8.8342 people/square metre, exceedExist adjacent
The Thiessen polygon density of population is more than D_THR2, not up to D_THR3, but reach D_THR3Maximum probability be 0.2613,
More than p3, red alert is opened；
……
Moment t+n, TH100The density of population be desired for 5.6458, less than D_THR1, and its adjacent Thiessen is polygon
The shape density of population is respectively less than D_THR1, then warning yellow is released.
Claims (7)
1. population agglomeration middle or short term method for early warning under a kind of big data environment, it is characterised in that comprise the following steps：
Step 1, system read the anonymous encryption mobile terminal sensing data obtained from sensor operator, anonymity encryption movement
Terminal sensor data is continuous in the time and space, and different mobile terminal corresponds to different EPID, extracts each EPID and is referring to
The communication signaling record triggered in section of fixing time, form the trip track data collection of the EPID；
The positional information of step 2, all fixed sensors of extraction, carries out Cluster merging processing to it, then calculates Voronoi
Figure, the actual control range of each sensor is obtained, i.e., the Thiessen polygons of each sensor, records each Thiessen
The area of polygon, set the three-level population carrying threshold value of each Thiessen polygons；
Step 3, trip track data collection of each EPID at the appointed time in section is extracted successively, be ranked up in chronological order；
From start time t0, on room and time, row interpolation is entered to trip track data using T as time interval, establishes trip
Time-space serial data set；The each point gone on a journey on Time-space serial data set is mapped on Voronoi diagram, it is corresponding to assign each point
Thiessen polygons numbering；
Step 4, track data that all user goes on a journey are divided into working day, weekend and common red-letter day, the class of great festivals or holidays three, time
All Thiessen polygons are gone through, from start time t0, it is every in the same type date to inquire about each Thiessen polygons
EPID in its each period T, it is more in certain Thiessen in the position at next moment, statistics t to search the EPID
EPID in the shape of side goes to the frequency of other Thiessen polygons in subsequent time, and calculating all EPID by large sample exists
A step transition probability of state between Thiessen polygons, forms Markov of all Thiessen polygons in t
Matrix of shifting of a step；
Step 5, the three-level population carrying threshold value formulated according to step 2 set extensive population agglomeration early warning mechanism, monitoring in real time
EPID quantity in each Thiessen polygons, and expand sample according to a certain percentage；If some Thiessen polygon of certain moment
In the density of population reach lowest level the density of population carrying threshold value, that is, open yellow warning, using the moment as starting point, use
Markov methods predict that the Thiessen polygons and its periphery Thiessen the polygons All population capacities in future time section T are big
Small mathematic expectaion and maximum population gathers the probability of generation；
It is step 6, more constantly based on each Thiessen in the next phase target zone of previous phase prediction of result according to Markov methods
The All population capacities and the density of population of side shape, decided whether to open the orange and red alert of higher level according to the rule pre-established
And implement necessary evacuation work, or warning level is reduced, until releasing warning yellow, stop prediction and calculate, recover normal
Monitored state.
2. population agglomeration middle or short term method for early warning under a kind of big data environment as claimed in claim 1, it is characterised in that described
Step 1 includes：
Step 1.1, system read the anonymous encryption mobile terminal sensing data obtained from sensor operator, and anonymity encryption moves
Dynamic terminal sensor data is continuous in the time and space, and anonymity encryption mobile terminal sensing data includes：User is only
One numbering EPID, communication operation type TYPE, communication operation occur moment TIME, great Qu REGIONCODE residing for sensor, passed
The specific numbering SENSORID of sensor, wherein, great Qu REGIONCODE residing for sensor and sensing implement body numbering SENSORID structures
Into sensor number；
Step 1.2, an anonymous encryption mobile terminal sensing data are that a signaling records, and every signaling record is solved
It is close；
Step 1.3, according to EPID, inquire about its at the appointed time signaling record all in section, structure is corresponding with current EPID
Trip track data collection.
3. population agglomeration middle or short term method for early warning under a kind of big data environment as claimed in claim 2, it is characterised in that described
Step 2 includes：
Step 2.1, the sensor number of all fixation sensor of extraction and its corresponding latitude and longitude coordinates LON-LAT, will be through
Latitude coordinate is converted to geographical coordinate X-Y；
Step 2.2, sensor record importing GIS software will be fixed, by overlapping fixed sensing on vertical space
Device merges into a fixed sensor, carries out cluster analysis to the locus of fixed sensor on this basis, if cluster half
Footpath is rds, then fixation sensor of the mutual distance less than rds is merged into a fixed sensor, take what is be merged to consolidate
Determine position of the center of gravity of the locus of sensor as the fixation sensor after merging, be that all fixed sensings are thought highly of after merging
New numbering；
Step 2.3, selection create Thiessen polygons, create to fix Voronoi diagram of the sensor as polygon center, are
Each Thiessen polygons create an object, and the numbering of i-th of Thiessen polygon is THi；
Step 2.4, will rearrange after the numbering of fixation sensor be associated with Thiessen polygons, if for some
For Thiessen polygons, there is multiple fixed sensors situation overlapping or close on vertical space, then by these quilts
The sensor number of the fixation sensor of merging all assigns the Thiessen polygons；
Step 2.5, the attribute imparting Thiessen polygons by geographical space, to weigh its population bearing capacity PCC, specific bag
Include：Natural quality NC, land used attribute LUC, the construction situation CC in plot where current Thiessen polygons, for multiple fixations
Sensor merges the situation in a Thiessen polygon, then accordingly increases the population bearing capacity of the Thiessen polygons
PCC, if i-th of Thiessen polygon is made up of multiple plot, plot is divided into road plot, house plot, general plot again
And the population bearing capacity PCC in factory building plot, then i-th of Thiessen polygoniCalculation formula be：
<mrow>
<msub>
<mi>PCC</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munder>
<mo>&Sigma;</mo>
<mi>j</mi>
</munder>
<msubsup>
<mi>A</mi>
<mi>j</mi>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>a</mi>
<mi>d</mi>
</mrow>
</msubsup>
<msubsup>
<mi>PC</mi>
<mi>j</mi>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>a</mi>
<mi>d</mi>
</mrow>
</msubsup>
<mo>+</mo>
<munder>
<mo>&Sigma;</mo>
<mi>j</mi>
</munder>
<msubsup>
<mi>A</mi>
<mi>j</mi>
<mrow>
<mi>h</mi>
<mi>o</mi>
<mi>u</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</msubsup>
<msubsup>
<mi>PC</mi>
<mi>j</mi>
<mrow>
<mi>h</mi>
<mi>o</mi>
<mi>u</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</msubsup>
<msub>
<mi>L</mi>
<mi>j</mi>
</msub>
<mo>+</mo>
<munder>
<mo>&Sigma;</mo>
<mi>j</mi>
</munder>
<msubsup>
<mi>A</mi>
<mi>j</mi>
<mrow>
<mi>c</mi>
<mi>o</mi>
<mi>m</mi>
<mi>m</mi>
</mrow>
</msubsup>
<msubsup>
<mi>PC</mi>
<mi>j</mi>
<mrow>
<mi>c</mi>
<mi>o</mi>
<mi>m</mi>
<mi>m</mi>
<mi>e</mi>
</mrow>
</msubsup>
<msub>
<mi>L</mi>
<mi>j</mi>
</msub>
<mo>+</mo>
<munder>
<mo>&Sigma;</mo>
<mi>j</mi>
</munder>
<msubsup>
<mi>A</mi>
<mi>j</mi>
<mrow>
<mi>f</mi>
<mi>a</mi>
<mi>c</mi>
</mrow>
</msubsup>
<msubsup>
<mi>PC</mi>
<mi>j</mi>
<mrow>
<mi>f</mi>
<mi>a</mi>
<mi>c</mi>
</mrow>
</msubsup>
<msub>
<mi>L</mi>
<mi>j</mi>
</msub>
</mrow>
<msub>
<mi>A</mi>
<mi>i</mi>
</msub>
</mfrac>
</mrow>
In formula,AndJ-th of road plot, house plot, general plot and business are represented respectively
The area in facility plot；AndJ-th of road plot, house plot are represented respectively, are led to
With the bearing capacity in plot and commercial facility plot；AndJ-th road plot, house are represented respectively
The number of plies in plot, general plot and commercial facility plot；
Step 2.6, the three-level population carrying threshold value according to each Thiessen polygons of historical experience setting, i-th
The l levels population of Thiessen polygons carries threshold valueThen have：
<mrow>
<mi>D</mi>
<mo>_</mo>
<msubsup>
<mi>THR</mi>
<mi>i</mi>
<mi>l</mi>
</msubsup>
<mo>=</mo>
<msub>
<mi>a</mi>
<mi>l</mi>
</msub>
<msub>
<mi>PCC</mi>
<mi>i</mi>
</msub>
</mrow>
In formula, alFor l level population agglomeration threshold value of warning.
4. population agglomeration middle or short term method for early warning under a kind of big data environment as claimed in claim 1, it is characterised in that described
Step 3 includes：
The trip track data collection of step 3.1, all EPID of traversal, arranged by triggering call duration time TIMESTAMP orders, from when
Between starting point begin stepping through trip track data collection, adjacent every 3 signaling measuring points be fitted a conic section, conic section
X-axis is the timeline of user's trip track, and Y-axis is the X-Y coordinate of signaling measuring point, if so the trip track of user includes n
Individual communications records point, then need to fit 2n-4 bar conic sections altogether；
Step 3.2, from integer start time t0, T calculates user in the X-Y coordinate at each time point, phase at timed intervals
With time X (t0+nT) and Y ((t0+nT) forms an interpolation point, and all interpolation points sort in chronological order, will in time away from
The interpolation point nearest from former measuring point is set to interpolation measuring point, and all interpolation points form the trip Time-space serial data of user；
Step 3.3, the X-Y coordinate according to each interpolation point in user's trip Time-space serial data, space is carried out with Voronoi diagram
Association, its Thiessen polygon is numbered to each interpolation point assigned in user's trip Time-space serial data.
5. population agglomeration middle or short term method for early warning under a kind of big data environment as claimed in claim 4, it is characterised in that described
Step 4 includes：
Step 4.1, all Thiessen polygons of traversal, create object, from start time t0 for each Thiessen polygons
Set out, the EPID that Thiessen polygons are in moment t is searched in going on a journey Time-space serial data from user, by the EPID and is somebody's turn to do
EPID interpolation point or interpolation measuring point deposit user's communication list Temp_EPID_LIST；
Step 4.2, traversal Temp_EPID_LIST, search volumes of each EPID in Thiessen polygons corresponding to the t+1 moment
Number, the Thiessen polygon lists Temp_Th_List being stored in where user's subsequent time；
Step 4.3, Temp_Th_List is read, Thiessen polygons are deposited into the form of dynamic array AppendlList
TH variable MarMatrix [t] .Freq, if the code T H-ID of some Thiessen polygon in Temp_Th_List has been deposited
It is MarMatrix [t] .Freq, then its frequency is added 1, if being not present, this TH-ID is added to MarMatrix [t]
.Freq in, and its frequency is set to 1；
Temp_EPID_LIST is read, counts sum between interpolation point and interpolation measuring point, sample ratio MarMatrix is expanded in deposit
[t].EnlargeProp；
Step 4.4, after having traveled through Temp_Th_List, according to MarMatrix [t] .Freq, moment t is counted at i-th
Thiessen polygons THiEPID, in moment t+1 spatial distribution, user is calculated in moment t at i-th with this
Thiessen polygons THiA step transition probability, i.e., user from moment t to t+1 from i-th of Thiessen polygons THiTransfer
To n-th of Thiessen polygons THnProbabilityBe all EPID from moment t to t+1 from i-th of Thiessen polygon
THiIt is transferred to n-th of Thiessen polygons THnSum divided by be in i-th of Thiessen polygons TH in moment ti's
EPID sum；
Then i-th of Thiessen polygon is in the Markov Matrix of shifting of a step of t：
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mrow>
<mi>n</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mi>n</mi>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mrow>
<mi>n</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
All Thiessen polygons are in the Markov Matrix of shifting of a step of t：
<mrow>
<msub>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msubsup>
<mi>p</mi>
<mn>1</mn>
<mn>1</mn>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mn>1</mn>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mn>1</mn>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mn>1</mn>
<mi>n</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mn>1</mn>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mi>n</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mn>1</mn>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>i</mi>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mn>1</mn>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>p</mi>
<mi>n</mi>
<mn>1</mn>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>n</mi>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>n</mi>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msubsup>
<mi>p</mi>
<mi>n</mi>
<mi>n</mi>
</msubsup>
</mtd>
</mtr>
</mtable>
</mfenced>
<mi>t</mi>
</msub>
<mo>.</mo>
</mrow>
6. population agglomeration middle or short term method for early warning under a kind of big data environment as claimed in claim 5, it is characterised in that described
Step 5 includes：
Step 5.1, the three-level density of population threshold value of each Thiessen polygons are set to yellow warning, the orange alert and red respectively
Color is guarded against, wherein, the three-level density of population threshold value of i-th of Thiessen polygon is respectively
Communication user quantity of each fixed sensor of step 5.2, in real time monitoring in each specified time section, with expansion sample ratio
MarMatrix [t] .EnlargeProp expands total user that sample is present period fixation sensor place Thiessen polygons
Number, then total amount expands the total number of persons that sample ratio EnlargeRadio expands in sample to the present period Thiessen polygons per capita；
If i-th of Thiessen polygons TH in step 5.3, current time tiThe density of populationReach one-level population
Density threshold value of warningThen open yellow warning；
If step 5.4, i-th of Thiessen polygons THiOpen yellow warning in moment t, then it is more with i-th of Thiessen
Side shape THiCentered on, the population size in moment t+1 comprising Thiessen polygons adjacent thereto is calculated, with i-th
Thiessen polygons THiAdjacent Thiessen polygons THjShared K adjacent Thiessen polygons, then Thiessen is more
Side shape THjIt is in moment t+1 population size
<mrow>
<msubsup>
<mi>Pop</mi>
<mi>j</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</munderover>
<msubsup>
<mi>p</mi>
<mi>k</mi>
<mi>j</mi>
</msubsup>
<msubsup>
<mi>Pop</mi>
<mi>k</mi>
<mi>t</mi>
</msubsup>
</mrow>
In formula,For with Thiessen polygons THjK-th adjacent of Thiessen polygons THkIt is big in moment t population
It is small,From Thiessen polygons TH from moment t to t+1kIt is transferred to Thiessen polygons THjProbability；
Step 5.5, with Thiessen polygons THiCentered on, Thiessen polygons TH when calculating moment t+1iThe density of population
ExceedWithPossibility, comprise the following steps：
Step 5.5.1, to Thiessen polygons THiAround Thiessen polygons within two layers, according to it in moment t to t
Thiessen polygons TH is transferred between+1iProbability be ranked up from big to small；
Step 5.5.2, with Thiessen polygons THiIt is radix in moment t population, it is assumed that in moment t to t+1, Thiessen
Polygon THiPopulation all stay in Thiessen polygons THi, its population isProbability is
Step 5.5.3, the Thiessen polygons after traversal sequence, wherein j-th of Thiessen polygons THjPeople in moment t
+ 1 is completely transferred to Thiessen polygons THiProbability beAssuming that j-th of Thiessen polygons THjIt is complete in subsequent time
Portion is transferred to Thiessen polygons THi, then Thiessen polygons TH during moment t+1iMaximum possible population isProbability isCalculate now Thiessen polygons THiThe density of population, if exceedingThen record Thiessen polygons THiExceed in moment t+1Probability be
Step 5.5.4, the Thiessen polygons after traversal sequence are continued, wherein z-th of Thiessen polygons THz people exists
Moment t+1 is completely transferred to Thiessen polygons THiProbability beAlso assume that it is transferred completely into subsequent time
Thiessen polygons THi, then Thiessen polygons TH during moment t+1iMaximum possible population isProbability is
Step 5.5.5, using with after the traversed n Thiessen polygons of step 5.5.3 and 5.5.4 identical method,
Thiessen polygons THiMaximum possible population beProbability isUntil
Thiessen polygons THiThe maximum possible density of population be more thanRecord Thiessen polygons THiIn moment t+1
When exceedProbability be
7. population agglomeration middle or short term method for early warning under a kind of big data environment as claimed in claim 6, it is characterised in that described
Step 6 includes：
Step 6.1, if Thiessen polygons TH is calculatediIn the moment t+1 density of populationIt is more thanOr it is more thanProbability be more than p1, then open yellow warning；
If step 6.2, Thiessen polygons THiIn the moment t+1 density of populationIt is more thanAnd its week
Enclose and the density of population of the adjacent Thiessen polygons in moment t+1 be present and be more than D_THR2, or more than D_THR2Probability be more than
P2, then the orange alert is opened, it is necessary to take the guard and evacuation measure of certain population agglomeration；
If step 6.3, Thiessen polygons THiIn the moment t+1 density of populationIt is more thanIt is then direct
The orange alert is opened, is more than if adjacent Thiessen polygons around it on this basis be present in the moment t+1 density of populationOr it is more thanProbability be more than p3, then open red alert, evacuation measure should be taken immediately；
If Thiessen polygons TH in step 6.4, calculating processiThe adjacent Thiessen polygons TH of surroundingjThe warning reached
Threshold value is higher than Thiessen polygons TH on the contraryi, then by Thiessen polygons THjFor the central point of calculating, by Thiessen
Polygon THiIt is reduced to Thiessen polygons THjAdjoining Thiessen polygons；
If step 6.5, in calculating process, Thiessen polygons THiIn the moment t+n density of populationIt is less thanAnd its density of population of adjacent Thiessen polygons in moment t+n is also both less thanThen release yellow
Color alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710726883.8A CN107609682B (en) | 2017-08-22 | 2017-08-22 | Medium-short term early warning method for population aggregation in big data environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710726883.8A CN107609682B (en) | 2017-08-22 | 2017-08-22 | Medium-short term early warning method for population aggregation in big data environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107609682A true CN107609682A (en) | 2018-01-19 |
| CN107609682B CN107609682B (en) | 2020-09-11 |
Family
ID=61065492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710726883.8A Active CN107609682B (en) | 2017-08-22 | 2017-08-22 | Medium-short term early warning method for population aggregation in big data environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609682B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133298A (en) * | 2018-03-08 | 2018-06-08 | 河南工业大学 | It is a kind of that the multivariate regression models whole nation grain consumption Forecasting Methodology for sliding center of gravity is grouped based on interpolation |
| CN109520499A (en) * | 2018-10-08 | 2019-03-26 | 浙江浙大中控信息技术有限公司 | Region isochronal method in real time is realized based on vehicle GPS track data |
| CN109711447A (en) * | 2018-12-19 | 2019-05-03 | 武大吉奥信息技术有限公司 | A kind of special population event early warning and monitoring method and device |
| CN109831774A (en) * | 2019-01-08 | 2019-05-31 | 中国联合网络通信集团有限公司 | A kind of big data expands quadrat method and device |
| CN110139221A (en) * | 2019-05-09 | 2019-08-16 | 特斯联（北京）科技有限公司 | A kind of population cluster dynamic monitoring method and system based on mobile phone signal microcaloire mouth |
| CN110992233A (en) * | 2019-12-13 | 2020-04-10 | 中国科学院深圳先进技术研究院 | Emergency evacuation method and system for urban gathering event |
| CN111669710A (en) * | 2020-04-21 | 2020-09-15 | 上海因势智能科技有限公司 | Demographic deduplication method |
| CN111680830A (en) * | 2020-05-25 | 2020-09-18 | 广州衡昊数据科技有限公司 | Epidemic situation prevention method and device based on aggregation risk early warning |
| CN112367608A (en) * | 2020-10-27 | 2021-02-12 | 上海世脉信息科技有限公司 | Method for mining spatial position of fixed sensor in big data environment |
| CN112418508A (en) * | 2020-11-19 | 2021-02-26 | 中国科学院地理科学与资源研究所 | Population distribution prediction method based on interaction between physical space and social network space |
| CN115865988A (en) * | 2023-02-21 | 2023-03-28 | 武汉理工大学三亚科教创新园 | Passenger ship passenger treading event monitoring system and method utilizing mobile phone sensor network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488120A (en) * | 2015-11-23 | 2016-04-13 | 上海川昱信息科技有限公司 | Method for collecting spatial population distribution in real time on basis of mobile phone big data and realizing large passenger flow early warning |
| CN105760454A (en) * | 2016-02-04 | 2016-07-13 | 东南大学 | Method for dynamically measuring distribution density of city population in real time |
| CN106792517A (en) * | 2016-12-05 | 2017-05-31 | 武汉大学 | Base station service number time sequence forecasting method based on mobile phone location Time-spatial diversion probability |
-
2017
- 2017-08-22 CN CN201710726883.8A patent/CN107609682B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488120A (en) * | 2015-11-23 | 2016-04-13 | 上海川昱信息科技有限公司 | Method for collecting spatial population distribution in real time on basis of mobile phone big data and realizing large passenger flow early warning |
| CN105760454A (en) * | 2016-02-04 | 2016-07-13 | 东南大学 | Method for dynamically measuring distribution density of city population in real time |
| CN106792517A (en) * | 2016-12-05 | 2017-05-31 | 武汉大学 | Base station service number time sequence forecasting method based on mobile phone location Time-spatial diversion probability |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133298A (en) * | 2018-03-08 | 2018-06-08 | 河南工业大学 | It is a kind of that the multivariate regression models whole nation grain consumption Forecasting Methodology for sliding center of gravity is grouped based on interpolation |
| CN108133298B (en) * | 2018-03-08 | 2022-04-19 | 河南工业大学 | National grain consumption prediction method based on multiple regression model |
| CN109520499A (en) * | 2018-10-08 | 2019-03-26 | 浙江浙大中控信息技术有限公司 | Region isochronal method in real time is realized based on vehicle GPS track data |
| CN109520499B (en) * | 2018-10-08 | 2020-06-26 | 浙江浙大中控信息技术有限公司 | Method for realizing regional real-time isochrones based on vehicle GPS track data |
| CN109711447A (en) * | 2018-12-19 | 2019-05-03 | 武大吉奥信息技术有限公司 | A kind of special population event early warning and monitoring method and device |
| CN109831774B (en) * | 2019-01-08 | 2021-08-10 | 中国联合网络通信集团有限公司 | Big data sample expansion method and device |
| CN109831774A (en) * | 2019-01-08 | 2019-05-31 | 中国联合网络通信集团有限公司 | A kind of big data expands quadrat method and device |
| CN110139221A (en) * | 2019-05-09 | 2019-08-16 | 特斯联（北京）科技有限公司 | A kind of population cluster dynamic monitoring method and system based on mobile phone signal microcaloire mouth |
| CN110139221B (en) * | 2019-05-09 | 2020-02-14 | 特斯联（北京）科技有限公司 | Population cluster dynamic monitoring method and system based on mobile phone signal micro-card port |
| CN110992233A (en) * | 2019-12-13 | 2020-04-10 | 中国科学院深圳先进技术研究院 | Emergency evacuation method and system for urban gathering event |
| CN110992233B (en) * | 2019-12-13 | 2024-04-23 | 中国科学院深圳先进技术研究院 | Emergency evacuation method and system for urban gathering event |
| CN111669710A (en) * | 2020-04-21 | 2020-09-15 | 上海因势智能科技有限公司 | Demographic deduplication method |
| CN111669710B (en) * | 2020-04-21 | 2021-07-06 | 上海因势智能科技有限公司 | Demographic deduplication method |
| CN111680830B (en) * | 2020-05-25 | 2024-01-26 | 广州衡昊数据科技有限公司 | Epidemic situation prevention method and device based on aggregation risk early warning |
| CN111680830A (en) * | 2020-05-25 | 2020-09-18 | 广州衡昊数据科技有限公司 | Epidemic situation prevention method and device based on aggregation risk early warning |
| CN112367608A (en) * | 2020-10-27 | 2021-02-12 | 上海世脉信息科技有限公司 | Method for mining spatial position of fixed sensor in big data environment |
| CN112418508A (en) * | 2020-11-19 | 2021-02-26 | 中国科学院地理科学与资源研究所 | Population distribution prediction method based on interaction between physical space and social network space |
| CN115865988A (en) * | 2023-02-21 | 2023-03-28 | 武汉理工大学三亚科教创新园 | Passenger ship passenger treading event monitoring system and method utilizing mobile phone sensor network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107609682B (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609682A (en) | Population agglomeration middle or short term method for early warning under a kind of big data environment | |
| CN106096631B (en) | A kind of floating population's Classification and Identification analysis method based on mobile phone big data | |
| Zhao et al. | Urban human mobility data mining: An overview | |
| Janzen et al. | Closer to the total? Long-distance travel of French mobile phone users | |
| CN106488405B (en) | A kind of position predicting method of fusion individual and neighbour's movement law | |
| CN111354472A (en) | Infectious disease transmission monitoring and early warning system and method | |
| US8185131B2 (en) | Method of providing location-based information from portable devices | |
| Wang et al. | Estimating dynamic origin-destination data and travel demand using cell phone network data | |
| Ghurye et al. | A framework to model human behavior at large scale during natural disasters | |
| CN105142106A (en) | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data | |
| CN104573859A (en) | Human traffic prediction method based on Wifi positioning and cloud data processing technology | |
| CN106304015A (en) | The determination method and device of subscriber equipment | |
| Guo et al. | Enhanced least square based dynamic OD matrix estimation using Radio Frequency Identification data | |
| CN115034524A (en) | Method, system and storage medium for predicting working population based on mobile phone signaling | |
| Cao et al. | Understanding metropolitan crowd mobility via mobile cellular accessing data | |
| Chen et al. | Data‐Driven Prediction System of Dynamic People‐Flow in Large Urban Network Using Cellular Probe Data | |
| Vidović et al. | Estimation of urban mobility using public mobile network | |
| Yabe et al. | Estimating Evacuation Hotspots using GPS data: What happened after the large earthquakes in Kumamoto, Japan | |
| Alhasoun et al. | The city browser: Utilizing massive call data to infer city mobility dynamics | |
| Duan et al. | MobilePulse: Dynamic profiling of land use pattern and OD matrix estimation from 10 million individual cell phone records in Shanghai | |
| Kurilkin et al. | Evaluation of urban mobility using surveillance cameras | |
| Jundee et al. | Inferring commuting flows using CDR data: A case study of Lisbon, Portugal | |
| Lwin et al. | Identification of various transport modes and rail transit behaviors from mobile CDR data: A case of Yangon City | |
| Platos et al. | Population data mobility retrieval at territory of Czechia in pandemic COVID‐19 period | |
| Al-Assady et al. | A proposed model for human securing using GPS |
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 |