CN109740957A - A kind of urban traffic network node-classification method - Google Patents
A kind of urban traffic network node-classification method Download PDFInfo
- Publication number
- CN109740957A CN109740957A CN201910025828.5A CN201910025828A CN109740957A CN 109740957 A CN109740957 A CN 109740957A CN 201910025828 A CN201910025828 A CN 201910025828A CN 109740957 A CN109740957 A CN 109740957A
- Authority
- CN
- China
- Prior art keywords
- network node
- data
- flow
- passengers
- volume
- 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
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of urban traffic network node-classification methods, are related to urban planning and urban transportation technical field, firstly, pre-processing to research intra zone traffic network node data.Secondly, being ranked up to the volume of the flow of passengers achievement data between each transportation network node and transportation network node.It recycles Time Series Clustering algorithm to classify transportation network node, and is associated with research intra zone traffic network node data on geographical space.Finally, carrying out map visualization displaying according to classification results to data set P1.The present invention can be according to the passenger flow magnitude relation of each transport node and other transport nodes, rapidly classify to urban transportation node, classification results can reflect out the volume of the flow of passengers distribution characteristics between the volume of the flow of passengers size and transport node and other transport nodes of every class transport node, to provide decision-making foundation for urban planning and traffic administration.
Description
Technical field
It is especially a kind of based on Time Series Clustering and OD visitor the present invention relates to urban planning and urban transportation technical field
The urban traffic network node-classification method of flow data.
Background technique
Currently, with the development of big data technology, urban traffic information data are showing explosive growth trend, special
It is not that particularly evident (general this kind of data are referred to as traffic trip OD number for volume of the flow of passengers data to occur between transport node
According to).For example, the visitor between the volume of the flow of passengers, public bicycles website between travel amount, subway station between city upblic traffic station
Flow etc..These big data sources have highly important practice to understand that city operations feature provides good data basis
Value.A large amount of data more must could quickly and easily help people to excavate most valuable by certain model algorithm
The information of value.For traffic trip OD data, 2 relatively conventional and particularly important information points are respectively: (1) each friendship
The size of passenger flow magnitude between logical node and other transport nodes.(2) passenger flow between each transport node and other transport nodes
The distribution situation of magnitude.Based on this 2 information points, researcher wishes to excavate valuable content, to go to understand that traffic is transported
Capable internal characteristics.For example, for all transport nodes, going out for each transport node and other transport nodes can be counted
Row total amount, to judge which the biggish node of the volume of traffic is according to the sequence of trip total amount value；If to some traffic section
The travel amount of point is paid special attention to, and can be ranked up to the size of itself and other transport node travel amounts, to observe this friendship
Logical node and other which transport nodes are most related.The above method is mainly the operation characteristic for studying local traffic node, is but lacked
The weary research to global feature.
In fact, how to study volume of the flow of passengers relationship characteristic between all websites be always paid special attention in practicing and and its
Important problem！Although current complex network scheduling theory technology provides good channel to study this problem, also deposit
In certain defect: (1) global feature is difficult to take into account with local feature relationship, as complex network moderate is distributed as research entirety
One important tool means of network structure but directly can not interpret each transport node and other transport nodes by degree distribution
Connection feature.(2) similarity feature between transport node is not deep enough, such as typically only by the community in complex network
It divides and the close a kind of transport node of connection is put together, however user is difficult directly to find out wherein every class transport node and phase
What kind of the connection of artis is characterized in, i.e., the OD stream feature that can not be occurred according to each website marks off similitude spy
Sign.
At the same time, some characteristic informations of the feature of traffic OD data are deeply excavated not yet, such as: if by each
Transport node and other each transport nodes are formed by volume of the flow of passengers data, are ranked up, then can see according to volume of the flow of passengers size
At one group of orderly data acquisition system (being denoted as L), and if this data acquisition system is shown in the form of histogram, when just having similar
Between sequence wave spectrum shape feature.In addition it is also possible to be ranked up according to spatial neighborhood relation, Time Series Clustering point is carried out
Analysis can reflect that transport node is constrained generated space connection relationship feature by space length then with emphasis.
Summary of the invention
It is provided the technical problem to be solved by the present invention is to overcome the deficiencies in the prior art a kind of poly- based on time series
The urban traffic network node-classification method of class and OD passenger flow data, the present invention can be according to each transport nodes and other traffic
The passenger flow magnitude relation of node, rapidly classifies to urban transportation node, and classification results can reflect out every class transport node
Volume of the flow of passengers size and transport node and other transport nodes between volume of the flow of passengers distribution characteristics, thus be urban planning and friendship
Siphunculus reason provides decision-making foundation.
The present invention uses following technical scheme to solve above-mentioned technical problem:
A kind of urban traffic network node-classification side based on Time Series Clustering and OD passenger flow data proposed according to the present invention
Method, comprising the following steps:
Step 1 pre-processes research intra zone traffic network node；It is specific as follows:
Step 1.1 carries out unique identifying number setting processing to all transportation network nodes, forms data set P；
Step 1.2 counts the passenger flow figureofmerit number that other transportation network nodes generate in each transportation network node and network
According to；
The volume of the flow of passengers achievement data obtained after the completion of step 1.3, step 1.2 statistics forms the passenger flow connection of all transportation network nodes
It is data set OD；
Step 2 is ranked up the volume of the flow of passengers achievement data of each transportation network node, forms new all transportation network nodes
Passenger flow contact data collection ODN；
Each transportation network node in step 2.1, ergodic data collection OD, and according to the size order of volume of the flow of passengers achievement data or
Spatial neighborhood relation, the passenger flow figureofmerit number that other transportation network nodes in the transportation network node and network in traversal are generated
According to being ranked up；
After the completion of step 2.2, traversal, the passenger flow contact data collection ODN of new all transportation network nodes is formed；
Step 3 classifies to transportation network node using Time Series Clustering algorithm, and by classification results on geographical space
It is associated with research intra zone traffic network node
Being classified using Time Series Clustering algorithm to transportation network node, detailed process is as follows: being defeated with data set ODN
Enter data, is classified using Time Series Clustering algorithm to research intra zone traffic network node.
As a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data point of the present invention
Class method advanced optimizes scheme, in step 3, using data set ODN as input data, using Time Series Clustering algorithm to research
Intra zone traffic network node is classified；Recycle each transportation network node unique identifying number sum number saved in classification results
It according to each transportation network node unique identifying number corresponding relationship in collection P, realizes that data set P is associated with classification results, and will close
Result after connection saves as new data set P1.
As a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data point of the present invention
Class method advanced optimizes scheme, further includes step 4 after step 3, step 4: carrying out map according to classification results to data set P1
It visualizes.
As a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data point of the present invention
Class method advanced optimizes scheme, and the data format of P is the data format suitable for ArcGIS software in step 1.1.
As a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data point of the present invention
Class method advanced optimizes scheme, and volume of the flow of passengers achievement data is train shift number or trip number in step 1.2.
As a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data point of the present invention
Class method advanced optimizes scheme, and there is no the connections of traffic passenger flow occurring between two transportation network nodes in step 1.2
When, volume of the flow of passengers achievement data is denoted as 0.
As a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data point of the present invention
Class method advanced optimizes scheme, according to the size order of volume of the flow of passengers achievement data is according to ascending order or descending in step 2.1
It is ranked up, spatial neighborhood relation refers to be ranked up according to space length is descending.
The invention adopts the above technical scheme compared with prior art, has following technical effect that
(1) the present invention provides a kind of urban traffic network node-classification side based on Time Series Clustering and OD passenger flow data
Method, the passenger flow magnitude relation between website provide a kind of new understanding and Analysis perspective, have taken into account whole and part feature
Content has important reference significance for the planning application of urban transportation node；
(2) final calculation result of the invention is website classification, if in conjunction with the distribution of facilities feature of every class website surrounding area,
Designer can be helped to more fully understand how different type website area should configure the public service facility in city；Cause
This, the present invention can be mentioned in conjunction with the space distribution of facilities feature in transport node area for new transport node surrounding area planning
For scientific guidance foundation.
Detailed description of the invention
Fig. 1 is overall flow schematic diagram of the invention.
Fig. 2 is transport node spatial distribution schematic diagram.
Fig. 3 is guest flow statistics schematic diagram between transport node.
Fig. 4 is the histogram of volume of the flow of passengers data between single transport node and other transport nodes；Wherein, (a) be P1 with
The histogram of volume of the flow of passengers data between other transport nodes, (b) between P2 and other transport nodes volume of the flow of passengers data histogram
Figure, (c) between P3 and other transport nodes volume of the flow of passengers data histogram, (d) passenger flow between P4 and other transport nodes
Measure the histogram of data, (e) for P5 and other transport nodes between volume of the flow of passengers data histogram, be (f) P6 and other traffic
The histogram of volume of the flow of passengers data between node.
Fig. 5 is transport node classification results spatial visualization schematic diagram.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawing:
Therefore, the present invention is to gather the data of spatial relationship between this kind of characterization transport node of similar OD passenger flow by time series
The method of class is classified.That is, the present invention, which changes and expanded Time Series Clustering algorithm, generally can be only applied to list
The scene of a transport node time moving law enables Time Series Clustering algorithm to carry out sequence point to entity space relationship
Class, so that the policymaker such as traffic, urban planning preferably be helped to observe the operation interactive relation of traffic flow spatially.Time sequence
Column clustering algorithm
Wherein, exactissima diligentia is needed: the relation data (such as trip number) of each node and other nodes, it is necessary to first
Certain sorting operation is carried out, otherwise Time Series Clustering algorithm can not directly be used for analyzing, and the result obtained is also difficult
To be applied in practice explanation, the reason is that the requirement format that data are analyzed in Time Series Clustering under normal circumstances is: pressing
According to the time, the sequencing of trip is recorded, so that people are when parsing cluster result, it can be suitable according to time point
Sequence carries out Phenomenon, and there is the subway station of the identical trip size of population can be divided into a kind of website at such as early high late peak.If
Which the volume of the flow of passengers between transport node and other transport nodes is ranked up, then it can be seen that each transport node and traffic
Node is most related (to contain much information: the volume of the flow of passengers size between the most quantity of relevant traffic node and most relevant traffic node
Deng).Therefore, the result of Time Series Clustering then can directly help people to know that certain class transport node is and other how many traffic
There is correlativity between node and be easy to judge the size (such as volume of the flow of passengers) of correlation, and then analyzes friendship on the whole
Spatial relationship distribution characteristics between logical node.
Step 1) is referring to attached drawing 1, it is necessary first to pre-process to research intra zone traffic network node.
Step 1.1) possesses 6 transportation network nodes referring to attached drawing 2 in area to be studied, geographical coordinate be respectively (x1,
), y1 (x2, y2), (x3, y3), (x4, y4), (x5, y5), (x6, y6).It is raw according to this 6 coordinate pairs in arcgis software
At the point data collection of shape format；
Step 1.2) again to all transportation network nodes of data set carry out unique identifying number setting processing, such as to above-mentioned 6 points according to
Secondary label is, P2, P3, P4, P5, P6, and acquired results are denoted as data set P；
Step 1.3) counts the passenger flow figureofmerit number that other transportation network nodes generate in each transportation network node and network
According to being the volume of the flow of passengers of 20, P1 to P5 if the volume of the flow of passengers that the volume of the flow of passengers of P1 to P2 is 20, P1 to P3 is the volume of the flow of passengers of 20, P1 to P4
The volume of the flow of passengers that the volume of the flow of passengers for 22, P1 to P6 is 23, P2 to P1 is that the volume of the flow of passengers of 7, P2 to P5 is the volume of the flow of passengers of 30, P2 to P6
The volume of the flow of passengers that the volume of the flow of passengers for 8, P3 to P6 is 5, P4 to P5 is that the volume of the flow of passengers of 30, P5 to P6 is the volume of the flow of passengers of 5, P6 to P1
The volume of the flow of passengers that the volume of the flow of passengers for 40, P6 to P2 is 38, P6 to P3 is that the volume of the flow of passengers of 10, P6 to P4 is the passenger flow of 38, P6 to P5
Amount is 10.When occurring contacting between two transportation network nodes there is no traffic passenger flow among the above, volume of the flow of passengers achievement data note
It is 0.
After the completion of step 1.4) statistics, the passenger flow contact data collection OD of all transportation network nodes, this example statistics are formed
Result out is referring to attached drawing 3.
Step 2 is ranked up the volume of the flow of passengers achievement data of each transportation network node.
The each transportation network node of step 2.1) ergodic data collection OD, and it is suitable from big to small according to volume of the flow of passengers achievement data
Sequence arranges the volume of the flow of passengers achievement data generated with the transportation network node in traversal with transportation network nodes other in network
Sequence.Such as the ranking results of transport node P1 are as follows: { 23,22,20,20,20 }；The ranking results of transport node P2 are as follows: 30,8,
7,0,0 }；The ranking results of transport node P3 are as follows: { 5,0,0,0,0 }；The ranking results of transport node P4 are as follows: 30,0,0,0,
0}；The ranking results of transport node P5 are as follows: { 5,0,0,0,0 }；The ranking results of transport node P6 are as follows: 40,38,38,10,
10}。
After the completion of step 2.2) traversal, the passenger flow contact data collection ODN of new all transportation network nodes is formed.
Step 3) Time Series Clustering algorithm, can a series of time moving law feature to research objects divide
Class.So, the data acquisition system that will study all transport nodes in area, classifies according to Time Series Clustering algorithm, then can be with
Find out every class transport node with other transport node relationships.Therefore, next using Time Series Clustering algorithm to the network of communication lines
Network node is classified, and research intra zone traffic network node data is associated on geographical space；
Step 3.1) is using data set ODN as input data, using Time Series Clustering algorithm to research intra zone traffic network node
Classify；
Step 3.2) is after determining reasonable classification results, it can be seen that this classification results is that P1 is one kind, is denoted as classification a；
P2 is one kind, is denoted as classification b；P3 and P5 is one kind, is denoted as classification c；P4 is 1 class, is denoted as classification d；P6 is 1 class, is denoted as classification
e。
Referring to attached drawing 4, Fig. 4 is the histogram of volume of the flow of passengers data between single transport node and other transport nodes；Wherein,
(a) in Fig. 4 between P1 and other transport nodes volume of the flow of passengers data histogram, (b) in Fig. 4 is P2 and other traffic sections
The histogram of volume of the flow of passengers data between point, (c) in Fig. 4 between P3 and other transport nodes volume of the flow of passengers data histogram,
(d) in Fig. 4 between P4 and other transport nodes volume of the flow of passengers data histogram, (e) in Fig. 4 is P5 and other traffic sections
The histogram of volume of the flow of passengers data between point, (f) in Fig. 4 between P6 and other transport nodes volume of the flow of passengers data histogram.
In the form of histogram, P1, P2, P3, P4, P5 and P6 and other transport node volumes of the flow of passengers are visualized respectively.
Combining classification result is as it can be seen that P3 is similar with the histogram distribution of P5.And the histogram of P1, P2, P4 and P6 respectively have a feature, therefore by
It is divided into different classifications.
Recycle each traffic in each transportation network node unique identifying number and data set P saved in classification results
Network node unique identifying number corresponding relationship realizes that data set P is associated with classification results, and saves as new data set P1(i.e.
Data set P new field describes the classification results of Time Series Clustering).
Step 4) carries out map visualization displaying according to classification results referring to attached drawing 5, to data set P1, both in ArcGIS
According to classification results in figure, every class transport node is shown with different pattern identifications number.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, several simple deductions or substitution can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (7)
1. a kind of urban traffic network node-classification method based on Time Series Clustering and OD passenger flow data, which is characterized in that
The following steps are included:
Step 1 pre-processes research intra zone traffic network node；It is specific as follows:
Step 1.1 carries out unique identifying number setting processing to all transportation network nodes, forms data set P；
Step 1.2 counts the passenger flow figureofmerit number that other transportation network nodes generate in each transportation network node and network
According to；
The volume of the flow of passengers achievement data obtained after the completion of step 1.3, step 1.2 statistics forms the passenger flow connection of all transportation network nodes
It is data set OD；
Step 2 is ranked up the volume of the flow of passengers achievement data of each transportation network node, forms new all transportation network nodes
Passenger flow contact data collection ODN；
Each transportation network node in step 2.1, ergodic data collection OD, and according to the size order of volume of the flow of passengers achievement data or
Spatial neighborhood relation, the passenger flow figureofmerit number that other transportation network nodes in the transportation network node and network in traversal are generated
According to being ranked up；
After the completion of step 2.2, traversal, the passenger flow contact data collection ODN of new all transportation network nodes is formed；
Step 3 classifies to transportation network node using Time Series Clustering algorithm, and by classification results on geographical space
It is associated with research intra zone traffic network node
Being classified using Time Series Clustering algorithm to transportation network node, detailed process is as follows: being defeated with data set ODN
Enter data, is classified using Time Series Clustering algorithm to research intra zone traffic network node.
2. a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data according to claim 1 point
Class method, which is characterized in that in step 3, using data set ODN as input data, using Time Series Clustering algorithm to research area
Interior transportation network node is classified；Recycle each transportation network node unique identifying number saved in classification results and data
Collect each transportation network node unique identifying number corresponding relationship in P, realize that data set P is associated with classification results, and will association
Result afterwards saves as new data set P1.
3. a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data according to claim 2 point
Class method, which is characterized in that further include step 4 after step 3, step 4: visual according to classification results progress map to data set P1
Change and shows.
4. a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data according to claim 1 point
Class method, which is characterized in that the data format of P is the data format suitable for ArcGIS software in step 1.1.
5. a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data according to claim 1 point
Class method, which is characterized in that volume of the flow of passengers achievement data is train shift number or trip number in step 1.2.
6. a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data according to claim 1 point
Class method, which is characterized in that in step 1.2 when occurring contacting between two transportation network nodes there is no traffic passenger flow,
Volume of the flow of passengers achievement data is denoted as 0.
7. a kind of urban traffic network node based on Time Series Clustering and OD passenger flow data according to claim 1 point
Class method, which is characterized in that according to the size order of volume of the flow of passengers achievement data carried out according to ascending order or descending in step 2.1
Sequence, spatial neighborhood relation refers to be ranked up according to space length is descending.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910025828.5A CN109740957B (en) | 2019-01-11 | 2019-01-11 | Urban traffic network node classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910025828.5A CN109740957B (en) | 2019-01-11 | 2019-01-11 | Urban traffic network node classification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109740957A true CN109740957A (en) | 2019-05-10 |
| CN109740957B CN109740957B (en) | 2020-12-15 |
Family
ID=66364496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910025828.5A Active CN109740957B (en) | 2019-01-11 | 2019-01-11 | Urban traffic network node classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740957B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458459A (en) * | 2019-08-13 | 2019-11-15 | 深圳前海微众银行股份有限公司 | Visual analysis method, device, equipment and the readable storage medium storing program for executing of traffic data |
| CN112784423A (en) * | 2021-01-28 | 2021-05-11 | 河北师范大学 | Urban area feature analysis method based on complex network |
| WO2021120817A1 (en) * | 2019-12-19 | 2021-06-24 | 广州新科佳都科技有限公司 | Node control-based method and device for subway station passenger flow control |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294679A (en) * | 2016-08-08 | 2017-01-04 | 大连理工大学 | A kind of method for visualizing carrying out website cluster based on subway data |
| CN106408939A (en) * | 2016-10-29 | 2017-02-15 | 浙江大学 | Traffic flow sequence classification method based on density peak value clustering |
| CN106844624A (en) * | 2017-01-20 | 2017-06-13 | 亚信蓝涛（江苏）数据科技有限公司 | A kind of visual public transport big data analysis system |
| US20170178044A1 (en) * | 2015-12-21 | 2017-06-22 | Sap Se | Data analysis using traceable identification data for forecasting transportation information |
| CN109146757A (en) * | 2018-07-06 | 2019-01-04 | 东南大学 | A kind of rail traffic emphasis volume of the flow of passengers section preparation method and its system |
-
2019
- 2019-01-11 CN CN201910025828.5A patent/CN109740957B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170178044A1 (en) * | 2015-12-21 | 2017-06-22 | Sap Se | Data analysis using traceable identification data for forecasting transportation information |
| CN106294679A (en) * | 2016-08-08 | 2017-01-04 | 大连理工大学 | A kind of method for visualizing carrying out website cluster based on subway data |
| CN106408939A (en) * | 2016-10-29 | 2017-02-15 | 浙江大学 | Traffic flow sequence classification method based on density peak value clustering |
| CN106844624A (en) * | 2017-01-20 | 2017-06-13 | 亚信蓝涛（江苏）数据科技有限公司 | A kind of visual public transport big data analysis system |
| CN109146757A (en) * | 2018-07-06 | 2019-01-04 | 东南大学 | A kind of rail traffic emphasis volume of the flow of passengers section preparation method and its system |
Non-Patent Citations (1)
| Title |
|---|
| 尹芹等: "基于客流特征的北京地铁站点类型识别", 《地理科学进展》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458459A (en) * | 2019-08-13 | 2019-11-15 | 深圳前海微众银行股份有限公司 | Visual analysis method, device, equipment and the readable storage medium storing program for executing of traffic data |
| WO2021120817A1 (en) * | 2019-12-19 | 2021-06-24 | 广州新科佳都科技有限公司 | Node control-based method and device for subway station passenger flow control |
| CN112784423A (en) * | 2021-01-28 | 2021-05-11 | 河北师范大学 | Urban area feature analysis method based on complex network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109740957B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zeng et al. | Visualizing mobility of public transportation system | |
| Kang et al. | Understanding operation behaviors of taxicabs in cities by matrix factorization | |
| CN107656987B (en) | Subway station function mining method based on L DA model | |
| Wang et al. | Re-evaluating polycentric urban structure: A functional linkage perspective | |
| CN105206048A (en) | Urban resident traffic transfer mode discovery system and method based on urban traffic OD data | |
| CN107134142A (en) | A kind of urban road method for predicting based on multisource data fusion | |
| CN109740957A (en) | A kind of urban traffic network node-classification method | |
| Jiang et al. | Large-scale taxi O/D visual analytics for understanding metropolitan human movement patterns | |
| CN106294679A (en) | A kind of method for visualizing carrying out website cluster based on subway data | |
| Zhong et al. | Identifying Spatial Structure of Urban Functional Centers Using Travel Survey Data: A Case Study of Singapore | |
| CN111931998B (en) | Individual travel mode prediction method and system based on mobile positioning data | |
| CN114363842B (en) | Bus passenger departure station prediction method and device based on mobile phone signaling data | |
| CN104462193A (en) | Vehicle movement trajectory searching system and method based on time-space matching | |
| CN104036020A (en) | MapX-based GIS bus information visualization method | |
| He et al. | What is the developmental level of outlying expansion patches? A study of 275 Chinese cities using geographical big data | |
| Zhao et al. | Interactive visual exploration of human mobility correlation based on smart card data | |
| Yang et al. | How to improve urban transportation planning in big data era? A practice in the study of traffic analysis zone delineation | |
| CN112000755A (en) | Regional trip corridor identification method based on mobile phone signaling data | |
| CN113240265B (en) | Urban space division method based on multi-mode traffic data | |
| Zhu et al. | Urban population migration pattern mining based on taxi trajectories | |
| Zhu et al. | Urban principal traffic flow analysis based on taxi trajectories mining | |
| CN106157601B (en) | A kind of investigation method of the bus passenger flow demand based on mobile data | |
| CN108960684B (en) | Public transport passenger closed travel chain mining method based on incomplete track segment | |
| CN116628462A (en) | Urban three-dimensional space land function attribute identification and space-time change monitoring analysis method | |
| Chen | Application of GNN in urban computing |
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 | ||
| CP03 | Change of name, title or address |
Address after: 210019 Building B3, No. 1, Yunlongshan Road, Jianye District, Nanjing, Jiangsu Patentee after: Jiangsu urban planning and Design Institute Co.,Ltd. Address before: 210036 Jiangsu Jianshe Building, No. 88, Caochangmen Street, Gulou District, Nanjing, Jiangsu Patentee before: JIANGSU INSTITUTE OF URBAN PLANNING AND DESIGN |
|
| CP03 | Change of name, title or address |