CN107908636A - A kind of method that mankind's activity spatiotemporal mode is excavated using social media - Google Patents
A kind of method that mankind's activity spatiotemporal mode is excavated using social media Download PDFInfo
- Publication number
- CN107908636A CN107908636A CN201710883260.1A CN201710883260A CN107908636A CN 107908636 A CN107908636 A CN 107908636A CN 201710883260 A CN201710883260 A CN 201710883260A CN 107908636 A CN107908636 A CN 107908636A
- Authority
- CN
- China
- Prior art keywords
- space
- activity
- cluster
- social media
- time path
- 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.)
- Withdrawn
Links
- 230000000694 effects Effects 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000005484 gravity Effects 0.000 claims abstract description 12
- 230000002123 temporal effect Effects 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000013075 data extraction Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 description 5
- 230000007774 longterm Effects 0.000 description 5
- 244000097202 Rathbunia alamosensis Species 0.000 description 3
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of method that mankind's activity spatiotemporal mode is excavated using social media, social media data extraction is carried out including user oriented individual, an activity is used as using every social media data, activity is divided into by the different periods according to the temporal information of social media data, the activity to each period clusters respectively;The moving position point quantity included according to cluster, calculates the rate of specific gravity of each cluster in each period;According to the rate of specific gravity of each cluster, the representative clusters of each period are extracted;A plurality of space-time path is generated based on representative clusters, confirms main space-time path;According to the point of safes in the daytime and night point of safes of main space-time path extraction user;And determine main space-time path, user is divided into according to main space-time path different classes of.The time and spatial homing that the present invention can go on a journey the mankind are combined, and obtain the urban population in different time, space and assemble situation, flowing law, support carries out dynamic role management symmetrically.
Description
Technical field
The present invention relates to mankind's movement law digging technology field, more particularly to one kind to excavate the mankind using social media and live
The method of dynamic spatiotemporal mode.
Background technology
Time suboptimal control be it is a kind of study under various restriction conditions the space-time characteristic of the behavior of people research method, with when
The mode of vacant lot reason frame is shown, framework integration time (t) and three, space (x, y) dimension.Spatial Dimension is shown
The change of mankind's movement in position, time dimension illustrate the sequentiality of mankind's movement in time.
The space-time path concepts being contained in time geography frame are to connect the active sequences point of the mankind in a manner of line segment
Pick up and, generate a path in three dimensions.Each moving point represents an activity, movable positional information by
Spatial Dimension mark in time geography frame, the temporal information that activity occurs are identified by time dimension.Space-time path is clearly
Illustrate User Activity to change with time rule, include the time interval of adjacent activities, activity changed time point,
Carry out the information such as same movable frequency.The change of the activity that the moving point connection table of mankind's short time is leted others have a look in a short time
Rule, when moving point is the custom sexuality of people, the space-time path connected by moving point represents the activity of people substantially
Pattern.The custom sexuality of the mankind's each period can be extracted according to the motion frequency of people, generation space-time path, obtains the mankind
Movable main spatiotemporal mode.
Social media is virtualization community and the network platform that people are used for creating, sharing, exchanging.With the popularization of mobile phone
With the development of location technology, identification and record of the mobile phone to geographical location are more and more careful, accurate, and geographical location slowly becomes
The popular sharing contents of social media user.Although people log in the time of social media daily and frequency is not consolidated very much
It is fixed, but life record of the social media to people is long-term, this long-term record is formd towards the huge of individual
Data source, can extract the space-time path of user from these huge data sources, obtain the long-term activity pattern of the mankind.
From space-time path, point of safes, night point of safes can obtain the position of Subscriber Unit and family in the daytime.Space-time path
Shape depend in the daytime point of safes occur and duration, in the daytime positional fluctuation situation, and in the daytime, night point of safes
The distance between (Commuting Distance).It can investigate and be classified using these features to user's space-time path.
And how different, the different space-time path of latitude and longitude coordinates is mapped to two dimension from three dimensions (x, y, t)
Plane space (Commuting Distance, t), and the division for carrying out classification is a major challenge of current this area.
The content of the invention
For prior art defect, the present invention proposes a kind of side that mankind's activity spatiotemporal mode is excavated using social media
Method.
Technical solution of the present invention provides a kind of method that mankind's activity spatiotemporal mode is excavated using social media, including following
Step:
Step 1, user oriented individual extraction space-time path, and determine main space-time path, including following sub-step,
Step 1.1, user oriented individual carries out social media data extraction;
Step 1.2, using every social media data as an activity, work is used as using the positional information of social media data
Dynamic position;
Step 1.3, activity is divided into by the different periods according to the temporal information of social media data, during equipped with n
Between section;
Step 1.4, the activity to each period clusters respectively;
Step 1.5, the moving position point quantity included according to cluster, calculates the rate of specific gravity of each cluster in each period;
Step 1.6, according to the rate of specific gravity of each cluster, the representative clusters of each period are extracted;
Step 1.7, a plurality of space-time path is generated based on representative clusters, generating mode is, in each period from representativeness
A cluster is selected in cluster, by one space-time path of selection result connection generation of all periods;
Step 1.8, the probability of occurrence in every space-time path of the gained of calculation procedure 1.7, confirms main space-time path;
Step 1.9, according to the point of safes in the daytime and night point of safes of main space-time path extraction user;
Step 2, user is divided into different classes of, including following sub-step according to main space-time path,
Step 2.1, the main space-time path of each user is mapped to two-dimensional space from three dimensions, dead circuit during to any bar
The Mapping implementation in footpath is as follows,
It is external using each clustering using the center each clustered that space-time path includes as cluster position, cluster centre
The round heart;
The latitude and longitude coordinates of cluster position within a predetermined period of time are averaged, as origin position;
Calculate cluster position and the Commuting Distance of origin position for the day part that space-time path includes;
Using transverse axis as the time, the longitudinal axis is Commuting Distance by space-time path drawing to two dimensional surface;
Step 2.2, it is as an object for possessing n dimension, each dimension using every space-time path for participating in cluster
The Commuting Distance of corresponding period, classifies space-time path;
Step 2.3, temporal mode feature and spatial model of all categories are obtained by the Commuting Distance of different classes of user
Feature.
Moreover, in step 1.4,
Clustered respectively using activity of the DBSCAN clustering methods based on density to each period.
Moreover, in step 1.3, if the length of each period is 1 small, n=24.
Moreover, in step 1.5, the rate of specific gravity of each cluster in each period, including the activity bit included with cluster are calculated
To put points amount and calculate each cluster proportion, calculation formula is as follows,
Wherein, P (j)tRefer to t-th of period, j-th of cluster proportion, njRefer to what t-th of period, j-th of class was included
Moving position is counted, and N refers to the period all moving position points.
Moreover, in step 1.8, calculating per paths probability of occurrence, formula is as follows,
Wherein,Represent the probability of occurrence in the user's individual kth bar space-time path, p (j)tRepresent t-th of time window
The shared proportion of j-th interior of cluster.
Moreover, in step 2.1, predetermined amount of time 1:00-6:00.
Moreover, in step 2.2, classified in n-dimensional space using K-Means methods to space-time path.
Moreover, the positional information of the social media data is point data of registering, sign-in desk data include GPS information.
The present invention have recorded the advantage of mankind's long term activity of earthquake space time information, the sign-in desk long-term from user using social media
The extracting data main life pattern of one day.According to default time window, multiple periods were divided into by one day of the mankind,
Obtain that each period user is most stable of position occurs in a manner of cluster, and calculate its probability of occurrence.When acquisition user is a plurality of
Dead circuit footpath, and user is divided into by the classification with different space-time characteristics according to main space-time path.The present invention is for understanding
The activity pattern of the mankind has certain application value.The activity pattern of the mankind influence the operation management in city, commercial planning,
The every aspects such as infrastructure construction.Can by the mankind go on a journey time and spatial homing be combined, obtain different time,
The urban population aggregation situation in space, flowing law, support carry out dynamic role management symmetrically.
Brief description of the drawings
Fig. 1 is the flow chart of the embodiment of the present invention.
Embodiment
Below in conjunction with the drawings and examples embodiment that the present invention will be described in detail.
The present invention utilizes social media data, based on the space-time path theory in space-time-geography frame, proposes to calculate the mankind
The method in space-time path and the scheme that space-time path category division is carried out using clustering method.Used with Beijing's Sina weibo
Exemplified by family, a plurality of space-time path of user is obtained, and user is divided into according to main space-time path by different classes of, these classifications
With different space-time characteristics.
Crucial improvement of the invention is to be to propose:
(1) the center longitude coordinate of the cluster included using space-time path as the cluster latitude and longitude coordinates, in cluster
The heart uses the circumscribed circle center of circle each clustered.
(2) 1:00-6:The latitude and longitude coordinates of cluster position in 00 period are averaged, as origin position.
(3) the cluster position of 24 periods and the distance of origin position that space-time path includes are calculated.
(4) using transverse axis as the time, the longitudinal axis is distance by space-time path drawing to two dimensional surface.
And classification is carried out to path using 24 time dimensions that space-time path includes as parameter according to K-Means clustering algorithms
Division.
Referring to Fig. 1, the embodiment of the present invention carries out following processing using Sina weibo as data source:
Step 1, user oriented individual extraction space-time path, and determine main space-time path, including following sub-step:
(1.1) user oriented individual carries out social media data extraction, obtains id of all users in microblog, carries
Take all Sina weibo data of each id issues.
(1.2) using every microblog data as an activity, work is used as using the point data of registering (GPS information) of microblog data
Dynamic position.
(1.3) according to default time window, microblogging is divided into the different periods according to temporal information, equipped with n
A period:Embodiment with 1h (hour) for time window, according to the temporal information of microblog data by activity be divided into it is different
Period, then n=24.
(1.4) activity to each period is clustered using the DBSCAN clustering methods based on density;Based on density
DBSCAN clustering methods be the prior art, reference can be made to pertinent literature:Huang Q,Wong D W S.2015.Modeling
and Visualizing Regular Human Mobility Patterns with Uncertainty:An Example
Using Twitter Data[J]. Annals of the Association of American Geographers,105
(6):1-19。
(1.5) from the spatial distribution of user's microblogging point, it can be seen that the user then may there are multiple movable hot spots
There are multiple activity clusters.Calculate multiple cluster rates of specific gravity of each period, including the moving position points gauge included with cluster
Each cluster proportion is calculated, under calculation formula such as formula:
Wherein, P (j)tRefer to t-th of period, j-th of cluster proportion, njRefer to what t-th of period, j-th of class was included
Moving position count, N refer to the period it is all moving position points, t=1,2 ... 24.
(1.6) arrange parameter controls, and with the rate of specific gravity according to each cluster, extracts the representative clusters of each period:
It is proposed to set multiple limitation parameters in embodiment, to obtain the representative clusters of each period.In 1.5 parts,
The rate of specific gravity shared by multiple clusters of same period is obtained, in order to extract the main movement law of user, the present embodiment is set
Three parameters therefrom extract main cluster (representative clusters), and three parameters are respectively:The accumulative threshold of DBSCAN parameters, cluster
Value, secondary cluster account for main cluster proportion, realize state modulator.DBSCAN is used for adjusting the size of cluster, produces of cluster
Number, cluster accumulation threshold are used to obtain main and a cluster using the mode of accumulative cluster proportion, and secondary cluster accounts for main poly-
Analogy is reused to prevent from by force retaining smaller cluster to reach the accumulative threshold value of cluster.
(1.7) a plurality of space-time path is obtained according to the representative clusters of selection, the method in generation space-time path is:In three-dimensional
In space (x, y, t), from arbitrarily one cluster of selection of each period, so as to obtain 24 clusters, 24 clusters are used into line segment
Connection, then generate a space-time path.Because the representative clusters of some periods are more than one, therefore travel through every kind of combination, can
Obtain a plurality of space-time path..
(1.8) probability of occurrence in every space-time path of the gained of calculation procedure 1.7, confirms main space-time path.The present invention into
One step designs every space-time path probability of occurrence computational methods, the probable value occurred according to every space-time path, when confirming main
Dead circuit footpath, 2-4 bar space-times path is the main space-time path of user before general selection.Formula is as follows:
Wherein,Represent the probability of occurrence in the user's individual kth bar space-time path, p (j)tRepresent t-th of time window
The shared proportion of j-th interior of cluster.N is time window number, the value that n is 24, t in the present embodiment is 1,2 ... n.
(1.9) according to the point of safes in the daytime (unit) and night point of safes (family) of main space-time path extraction user.In the daytime
Stablize
Point and night point of safes are respectively user in the darg period (10:00-17:And the rest period (1 00):00-
6:00) it is steady
Existing position is made, the average value for being appeared in all positions of the period during research using user respectively is obtained
.Extracting
Using the position got home with unit during user's space activity pattern, in addition house is used when carrying out route classification
Position make
To draw the origin position in space-time path.
Step 2, user is divided into different classes of, including following sub-step according to main space-time path:
(2.1) in the cluster preparation stage, design space-time path that to be mapped to two-dimensional space from three dimensions (x, y, t) (logical
Diligent distance, t) method, mainly include the following steps that;
A) using the center each clustered that space-time path includes as cluster position, the cluster that can be included with space-time path
Latitude and longitude coordinates of the center longitude coordinate as the cluster, cluster centre use the circumscribed circle center of circle each clustered.
B) 1:00-6:The latitude and longitude coordinates of cluster position in 00 period are averaged, and obtain night point of safes
(family), and using night point of safes as origin position.
C) the cluster position of 24 periods and the distance of origin position that space-time path includes are calculated, as Commuting Distance.
D) using transverse axis as the time, the longitudinal axis is Commuting Distance by space-time path drawing to two dimensional surface.
(2.2) the space-time Path Clustering flow based on K-Means methods is designed, is mainly comprised the steps of:
A) according to the proportion in a plurality of space-time path of each user obtained in step (8), user's proportion maximum is chosen
Space-time path participates in cluster.The space-time path is also rate of specific gravity is maximum in representative space-time path one.
B) every space-time path for participating in cluster is led to as an object for possessing 24 dimensions, each dimension to be corresponding
Diligent distance, that is, the cluster position and the distance of origin that the preparation stage of classifying calculates.
C) classified in 24 dimension spaces using K-Means methods to space-time path.
When it is implemented, different classification numbers can be attempted, classification number should not be advisable, classified too much or very little with 4-6 classes
Effect should accomplish that difference is obvious between tiring out, i.e., embody significant difference on space-time characteristic.According to Clustering Effect, suitable point of selection
Class number, i.e. K values.
(2.3) the temporal mode feature and spatial model feature of classification are obtained by the Commuting Distance of different classes of user:
The temporal mode feature of classification is obtained by the Commuting Distance of different classes of user.The temporal mode of classification, which refers to, to be belonged to
For same category of user since habits and customs are similar, some special time periods in one day embody similar active degree, and lead to
Issuing microblog quantity is crossed to show in social media.As some users get used in the morning 6:00-9:The 00 a large amount of microbloggings of issue,
It may be left home farther out due to this kind of user job unit, on a vehicle caused by the waste plenty of time.It can show 1,2,3 classes
The temporal mode of (occupying 84% user) user's issuing microblog, transverse axis are 24 time divisions when small, and the longitudinal axis is each period
The standardization result of each classification issuing microblog total amount.It can be seen that change three classes user's issuing microblog with Commuting Distance
Peak also change correspondingly;
The spatial model feature of classification is obtained by the Commuting Distance of different classes of user.The spatial model feature of classification refers to
The point of safes in the daytime (work unit) of fellow users and the distribution characteristics of night point of safes (family) and the distance between.As led to
Diligent distant user, family is distributed in remote locations more, and work unit is distributed in urban district more, this may be due to Beijing's height
Caused by the room rate of volume.It can show the spatial distribution of the 6th class and the 2nd class user man and unit, wherein green point is the distribution of family, it is red
Point is the distribution of unit.It can be seen that user family and unit random distribution of the Commuting Distance at 5 kilometers or so, Commuting Distance exist
25 kilometers or so of user family is distributed in Beijing periphery more and unit Relatively centralized is distributed in urban district.Which reflects Beijing
High housing price and migrant in Beijing's phenomenon.
When it is implemented, flow of the present invention can realize automatic running using software technology.
Above-mentioned is presently preferred embodiments of the present invention, however it is not limited to the present embodiment, all spirit and principle in the present embodiment
Within modification, replacement, the improvement etc. made, should be included within the protection domain of this patent.
Claims (9)
- A kind of 1. method that mankind's activity spatiotemporal mode is excavated using social media, it is characterised in that comprise the following steps:Step 1, user oriented individual extraction space-time path, and determine main space-time path, including following sub-step,Step 1.1, user oriented individual carries out social media data extraction;Step 1.2, using every social media data as an activity, activity bit is used as using the positional information of social media data Put;Step 1.3, activity is divided into by the different periods according to the temporal information of social media data, equipped with n period;Step 1.4, the activity to each period clusters respectively;Step 1.5, the moving position point quantity included according to cluster, calculates the rate of specific gravity of each cluster in each period;Step 1.6, according to the rate of specific gravity of each cluster, the representative clusters of each period are extracted;Step 1.7, a plurality of space-time path is generated based on representative clusters, generating mode is, in each period from representative clusters Middle one cluster of selection, by one space-time path of selection result connection generation of all periods;Step 1.8, the probability of occurrence in every space-time path of the gained of calculation procedure 1.7, confirms main space-time path;Step 1.9, according to the point of safes in the daytime and night point of safes of main space-time path extraction user;Step 2, user is divided into different classes of, including following sub-step according to main space-time path,Step 2.1, the main space-time path of each user is mapped to two-dimensional space from three dimensions, to any bar space-time path Mapping implementation is as follows,It is external round using each clustering using the center each clustered that space-time path includes as cluster position, cluster centre The heart;The latitude and longitude coordinates of cluster position within a predetermined period of time are averaged, as origin position;Calculate cluster position and the Commuting Distance of origin position for the day part that space-time path includes;Using transverse axis as the time, the longitudinal axis is Commuting Distance by space-time path drawing to two dimensional surface;Step 2.2, it is corresponding using every space-time path for participating in clustering as an object for possessing n dimension, each dimension The Commuting Distance of period, classifies space-time path;Step 2.3, temporal mode feature and spatial model feature of all categories are obtained by the Commuting Distance of different classes of user.
- 2. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 1, it is characterised in that:Step In 1.4, clustered respectively using activity of the DBSCAN clustering methods based on density to each period.
- 3. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 1, it is characterised in that:Step In 1.3, if the length of each period is 1 small, n=24.
- 4. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 1, it is characterised in that:Step In 1.5, the rate of specific gravity of each cluster in each period is calculated, including the moving position points amount included with cluster calculates each cluster Proportion, calculation formula is as follows,<mrow> <mi>P</mi> <msub> <mrow> <mo>(</mo> <mi>j</mi> <mo>)</mo> </mrow> <mi>t</mi> </msub> <mo>=</mo> <mfrac> <msub> <mi>n</mi> <mi>j</mi> </msub> <mi>N</mi> </mfrac> </mrow>Wherein, P (j)tRefer to t-th of period, j-th of cluster proportion, njRefer to the activity that t-th of period, j-th of class is included Position is counted, and N refers to the period all moving position points.
- 5. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 1, it is characterised in that:Step In 1.8, calculating per paths probability of occurrence, formula is as follows,<msub> <mi>P</mi> <mrow> <msub> <mi>stp</mi> <mi>k</mi> </msub> <mo>=</mo> <msubsup> <mi>&Pi;</mi> <mrow> <mi>t</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </msubsup> <mi>p</mi> <msub> <mrow> <mo>(</mo> <mi>j</mi> <mo>)</mo> </mrow> <mi>t</mi> </msub> </mrow> </msub>Wherein,Represent the probability of occurrence in the user's individual kth bar space-time path, p (j)tRepresent in t-th of time window The shared proportion of j-th of cluster.
- 6. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 1, it is characterised in that:Step In 2.1, predetermined amount of time 1:00-6:00.
- 7. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 1, it is characterised in that:Step In 2.2, classified in n-dimensional space using K-Means methods to space-time path.
- 8. according to the side that mankind's activity spatiotemporal mode is excavated using social media of claim 1 or 2 or 3 or 4 or 5 or 6 or 7 Method, it is characterised in that:The social media data are microblog data.
- 9. the method for mankind's activity spatiotemporal mode is excavated using social media according to claim 8, it is characterised in that:It is described The positional information of social media data is point data of registering, and sign-in desk data include GPS information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710883260.1A CN107908636A (en) | 2017-09-26 | 2017-09-26 | A kind of method that mankind's activity spatiotemporal mode is excavated using social media |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710883260.1A CN107908636A (en) | 2017-09-26 | 2017-09-26 | A kind of method that mankind's activity spatiotemporal mode is excavated using social media |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107908636A true CN107908636A (en) | 2018-04-13 |
Family
ID=61840256
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710883260.1A Withdrawn CN107908636A (en) | 2017-09-26 | 2017-09-26 | A kind of method that mankind's activity spatiotemporal mode is excavated using social media |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107908636A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255080A (en) * | 2018-07-31 | 2019-01-22 | 平安科技(深圳)有限公司 | A kind of information processing method and device |
CN109522374A (en) * | 2018-09-14 | 2019-03-26 | 北京三快在线科技有限公司 | A kind of localization method, device, electronic equipment and readable storage medium storing program for executing |
CN110046174A (en) * | 2019-03-07 | 2019-07-23 | 特斯联(北京)科技有限公司 | A kind of population migration analysis method and system based on big data |
CN110426735A (en) * | 2019-07-02 | 2019-11-08 | 武汉大学 | A kind of detection method of the earthquake disaster coverage based on social media |
CN113420067A (en) * | 2021-06-22 | 2021-09-21 | 北京房江湖科技有限公司 | Method and device for evaluating position credibility of target location |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104731795A (en) * | 2013-12-19 | 2015-06-24 | 日本电气株式会社 | Mining apparatus and method of activity patterns of individuals |
CN105183870A (en) * | 2015-09-17 | 2015-12-23 | 武汉大学 | Urban functional domain detection method and system by means of microblog position information |
CN106021508A (en) * | 2016-05-23 | 2016-10-12 | 武汉大学 | Sudden event emergency information mining method based on social media |
-
2017
- 2017-09-26 CN CN201710883260.1A patent/CN107908636A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104731795A (en) * | 2013-12-19 | 2015-06-24 | 日本电气株式会社 | Mining apparatus and method of activity patterns of individuals |
CN105183870A (en) * | 2015-09-17 | 2015-12-23 | 武汉大学 | Urban functional domain detection method and system by means of microblog position information |
CN106021508A (en) * | 2016-05-23 | 2016-10-12 | 武汉大学 | Sudden event emergency information mining method based on social media |
Non-Patent Citations (2)
Title |
---|
KUMAR D等: "Understanding Urban Mobility via Taxi Trip Clustering", 《IEEE INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT》 * |
高露妹: "基于社交媒体的人类移动时空规律研究", 《中国优秀硕士论文电子期刊网》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255080A (en) * | 2018-07-31 | 2019-01-22 | 平安科技(深圳)有限公司 | A kind of information processing method and device |
CN109522374A (en) * | 2018-09-14 | 2019-03-26 | 北京三快在线科技有限公司 | A kind of localization method, device, electronic equipment and readable storage medium storing program for executing |
WO2020052312A1 (en) * | 2018-09-14 | 2020-03-19 | 北京三快在线科技有限公司 | Positioning method and apparatus, electronic device, and readable storage medium |
CN110046174A (en) * | 2019-03-07 | 2019-07-23 | 特斯联(北京)科技有限公司 | A kind of population migration analysis method and system based on big data |
CN110426735A (en) * | 2019-07-02 | 2019-11-08 | 武汉大学 | A kind of detection method of the earthquake disaster coverage based on social media |
CN113420067A (en) * | 2021-06-22 | 2021-09-21 | 北京房江湖科技有限公司 | Method and device for evaluating position credibility of target location |
CN113420067B (en) * | 2021-06-22 | 2024-01-19 | 贝壳找房(北京)科技有限公司 | Method and device for evaluating position credibility of target site |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107908636A (en) | A kind of method that mankind's activity spatiotemporal mode is excavated using social media | |
CN106096631B (en) | A kind of floating population's Classification and Identification analysis method based on mobile phone big data | |
CN106570184B (en) | Method for extracting recreation-living contact data set from mobile phone signaling data | |
Wang et al. | PGT: Measuring mobility relationship using personal, global and temporal factors | |
CN106912015B (en) | Personnel trip chain identification method based on mobile network data | |
Shi et al. | Human mobility patterns in different communities: a mobile phone data-based social network approach | |
Xu et al. | How friends share urban space: An exploratory spatiotemporal analysis using mobile phone data | |
CN105741486B (en) | Urban Public Space based on mobile phone location data tramples accident real time early warning method | |
Gao et al. | Detecting origin-destination mobility flows from geotagged tweets in greater Los Angeles area | |
Kim | Identifying the structure of cities by clustering using a new similarity measure based on smart card data | |
CN103116696B (en) | Personnel based on the mobile phone location data of sparse sampling reside place recognition methods | |
CN103729478B (en) | LBS interest point discovery method based on MapReduce | |
Asgari et al. | A survey on human mobility and its applications | |
CN103942310B (en) | User behavior similarity mining method based on spatiotemporal mode | |
Jin et al. | Location-based social networking data: exploration into use of doubly constrained gravity model for origin–destination estimation | |
Kurkcu et al. | Evaluating the usability of geo-located twitter as a tool for human activity and mobility patterns: A case study for nyc | |
Tanahashi et al. | Inferring human mobility patterns from anonymized mobile communication usage | |
Sun et al. | Identifying tourists and locals by K-means clustering method from mobile phone signaling data | |
Yuan et al. | Recognition of functional areas based on call detail records and point of interest data | |
Melià-Seguí et al. | Activity duration analysis for context-aware services using foursquare check-ins | |
Liao et al. | A mobility model for synthetic travel demand from sparse traces | |
CN104850657A (en) | Holographic position map superposing method | |
CN105654137B (en) | A kind of mass remote sensing data taxonomic organization method | |
Kheiri et al. | Intra-urban movement flow estimation using location based social networking data | |
Kurilkin et al. | Evaluation of urban mobility using surveillance cameras |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180413 |