CN113393079B - Traffic cell division method based on public transport data - Google Patents
Traffic cell division method based on public transport data Download PDFInfo
- Publication number
- CN113393079B CN113393079B CN202110493843.XA CN202110493843A CN113393079B CN 113393079 B CN113393079 B CN 113393079B CN 202110493843 A CN202110493843 A CN 202110493843A CN 113393079 B CN113393079 B CN 113393079B
- Authority
- CN
- China
- Prior art keywords
- clustering
- traffic
- sites
- density
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 17
- 230000032823 cell division Effects 0.000 title claims description 6
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 101150050673 CHK1 gene Proteins 0.000 claims description 2
- 101100220616 Caenorhabditis elegans chk-2 gene Proteins 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 238000010606 normalization Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0204—Market segmentation
- G06Q30/0205—Location or geographical consideration
-
- 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
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Traffic Control Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
Aiming at the defect that the traffic cells divided by the traditional or traditional improved traffic cells are mostly bounded by roads, so that opposite bus stops are usually in different traffic cells, and the upward and downward passenger flows of opposite stops are mostly the same lot of people, the invention designs a traffic cell dividing method based on bus data. Dividing traffic cells through a graph clustering algorithm, clustering stations according to the relationship between the upper stations and the lower stations of passengers, and reflecting the internal relationship between the stations; the data of the opposite sites are integrated into one by taking the internal contact of the sites into consideration, so that most of the opposite sites are clustered into one type, and the problem that the target sites are at the edge of a traffic cell is solved; and the central area with high density is clustered for the second time, so that traffic cells of the central urban area are divided more densely, and the method is more suitable for specific application.
Description
Technical Field
The invention belongs to the field of rail transit station planning, and particularly relates to a traffic cell division method based on public transit data.
Background
Traffic cells are the basic unit of traffic planning and play an important role in traffic planning. The appropriate traffic cells can be divided, so that a good reference can be provided for future travel planning. In order to fully understand the travel characteristics of each traffic cell and the conditions of each traffic source, it is necessary to know the cell attraction, the production and the distribution of the city. For the division of traffic cells, the size of the division blocks can be controlled according to specific requirements, but the division of the traffic cells cannot meet the specific requirements due to the fact that the division is too large or too small, the workload is increased due to the fact that the division is meaningless, and the difficulty of traffic investigation, analysis and prediction is increased.
The existing traffic cells are generally divided according to administrative areas, homogeneity, regional population and regional economy of cities, and certain constraints are imposed on population, regional functions and regional sizes. Problems associated therewith include the inability to precisely grasp the inter-connection between traffic cells, etc.
In the prior art, traffic cells are divided in a traditional mode, and administrative areas, population and economical differences of the traffic cells are considered, so that each traffic cell has similar area size, population and economical properties. A drawback of this type is that no link between traffic cells, such as the creation of attractive relationships of people flows between traffic cells, is manifested.
A subsequent improvement is to cluster traffic cells based on certain features based on the partitioning of conventional traffic cells. The method is to aggregate the existing traffic cells, and basically macroscopic traffic cells are aggregated according to traffic semantics according to certain passenger flow indexes, although the relationship among the traffic cells is considered, and the specific attraction relationship among the traffic cells is not considered.
However, the above conventional or conventional improved traffic cell division has a unified disadvantage: the divided traffic cells are mostly bordered by roads, so that opposite bus stops are usually in different traffic cells, and the upward and downward passenger flows of opposite stops are mostly the same lot of people, and a certain influence is exerted on the subsequent travel planning scheme formulation.
Disclosure of Invention
Aiming at the defect that the traffic cells divided by the traditional or traditional improved traffic cells are mostly bounded by roads, so that opposite bus stops are usually in different traffic cells, and the upward and downward passenger flows of opposite stops are mostly the same lot of people, the invention designs a traffic cell dividing method based on bus data.
A traffic cell dividing method based on public traffic data comprises the following steps:
step one: acquiring bus data and preprocessing the data to meet the calculation requirement;
step two: performing cluster analysis on the data processed in the first step according to actual traffic semantics;
step three: changing different clustering modes of the second step, continuously verifying the clustering result, and finally confirming the clustering number of traffic semantics;
step four: carrying out multi-factor clustering by combining the clustering number of the traffic semantics in the step three with the administrative region number of the actual city to ensure that the clustering result obtained in practice fits with the city expectation;
step five: screening the clustering result dense areas appearing in the fourth step, and clustering the dense areas again to meet the requirement of finer central urban area division;
step six: taking the clustering result as a point and acquiring a label according to other results around the point so as to correct the clustering result, correcting error classification in the clustering result by using the characteristic that the sites of the same category have similar macroscopic passenger flow characteristics and microscopic site relativity, and obtaining an actual clustering result;
step seven: and D, generating a traffic cell according to the corrected clustering result in the step six.
Preferably, the first step is to establish a bus stop index evaluation system before acquiring bus data, and pre-process the acquired bus data according to the bus stop index evaluation system.
Preferably, in the third step, the clustering result is evaluated using the target contour coefficient and the CH coefficient.
Preferably, the pretreatment includes: reject the unnecessary and erroneous sites and normalize the data for subsequent computation.
Preferably, the fifth step uses a kernel density function to distinguish whether the clustering result generated in the fourth step is a dense region. The obtained density is the nuclear density of a single site, and the larger the density is, the more similar sites around the site are; taking the average value of the site core density of the same class as the density of the class, the higher the density is, the stronger the aggregation of the sites of the class is, the closer the sites of the class are to the city center, and the clustering of the sites with high density can meet the finer requirement of the center city area division.
Preferably, in the fifth step, in order to cluster the opposite sites in the same category and achieve the purpose that the opposite sites are in the same traffic cell, the clustering is performed by using the up-down traffic matrix as an index matrix and using spectral clustering.
Preferably, after the clustering result corrected in the step six is obtained, the step seven forms a Thiessen polygon with the site as the center and merges the Thiessen polygons adjacent to the same category into a traffic cell.
The invention has the substantial effects that according to the modern information technology, the traffic cells are divided through the travel data such as mobile phones, subways, buses and the like and the macroscopic traffic semantics of the stations are distinguished by combining the macroscopic traffic indexes of the stations, so that the external connection among the stations is considered; clustering stations according to the relation between the upper stations and the lower stations of passengers, so that the internal relation between the stations is reflected; the data of the opposite sites are integrated into one by taking the internal contact of the sites into consideration, so that most of the opposite sites are clustered into one type, and the problem that the target sites are at the edge of a traffic cell is solved; and the central area with high density is clustered for the second time, so that traffic cells of the central urban area are divided more densely, and the method is more suitable for specific application.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The technical scheme of the invention is further specifically described below through specific embodiments and with reference to the accompanying drawings.
Example 1
As shown in fig. 1, the traffic cell division method based on public traffic data includes the following steps:
step one: acquiring bus data and preprocessing the data to meet the calculation requirement;
step two: performing cluster analysis on the data processed in the first step according to actual traffic semantics;
step three: changing different clustering modes of the second step, continuously verifying the clustering result, and finally confirming the clustering number of traffic semantics; when the method is used for primary selection, K is determined according to the traffic semantic classification quantity, and the data is processed by using a K-means++ algorithm;
step four: carrying out multi-factor clustering by combining the clustering number of the traffic semantics in the step three with the administrative region number of the actual city to ensure that the clustering result obtained in practice fits with the city expectation;
step five: screening the clustering result dense areas appearing in the fourth step, and clustering the dense areas again to meet the requirement of finer central urban area division;
step six: taking the clustering result as a point and acquiring a label according to other results around the point so as to correct the clustering result, correcting error classification in the clustering result by using the characteristic that the sites of the same category have similar macroscopic passenger flow characteristics and microscopic site relativity, and obtaining an actual clustering result;
step seven: and D, generating a traffic cell according to the corrected clustering result in the step six.
The first step is to establish a bus stop index evaluation system before acquiring bus data, and pre-process the acquired bus data according to the bus stop index evaluation system.
When the station evaluation index system is established, 10 indexes including peak value, kurtosis, skewness, passenger flow period distribution equilibrium coefficient and peak hour coefficient are adopted according to morphological characteristics, structural characteristics and passenger flow time distribution characteristics, wherein the kurtosis can judge whether traffic semantics of the bus station are out of residence or employment, and the kurtosis can approximately judge whether the duty ratio of the passenger flow in the general passenger flow is larger or not.
The selected indexes are all positive evaluation on passenger flow, and the clustering effect only sees the distance difference, so the indexes are all positive indexes.
The specific index types are shown in Table 1.
TABLE 1 rule Table of index System
Wherein peak traffic hour coefficient = peak traffic/day total traffic; passenger flow period distribution uniformity coefficient = early-late peak average passenger flow volume/flat peak average passenger flow volume; the ratio is obtained because only the passenger flow form of the stations is needed to be known, and the passenger flow between the stations can influence the result.
In the third step, the clustering result is evaluated by using the standard contour coefficient and the CH coefficient.
The pretreatment comprises the following steps: reject the unnecessary and erroneous sites and normalize the data for subsequent computation.
The rejected useless sites include: stations without passenger flow data and stations with maximum boarding or alighting number less than 1 person in average month, and stations without longitude and latitude or matched station reporting records.
And step five, using a kernel density function to distinguish whether the clustering result generated in the step four is a dense region or not. The obtained density is the nuclear density of a single site, and the larger the density is, the more similar sites around the site are; taking the average value of the site core density of the same class as the density of the class, the higher the density is, the stronger the aggregation of the sites of the class is, the closer the sites of the class are to the city center, and the clustering of the sites with high density can meet the finer requirement of the center city area division.
In the fifth step, in order to cluster the opposite sites in the same category and achieve the purpose that the opposite sites are in the same traffic cell, the upper and lower passenger flow matrixes are used as index matrixes, and the clustering is performed by using spectral clustering.
And step seven, after the clustering result corrected in the step six is obtained, forming a Thiessen polygon by taking a site as a center and combining the Thiessen polygons adjacent to the same category into a traffic cell.
The multi-factor clustering and the corresponding evaluation in the fourth step are specifically as follows: obtaining the number of administrative regions of a city where a data source is located, setting the number of administrative regions as k1, setting the product of the number of administrative regions and the number of traffic semantics as k2, traversing the integer k in k1 to k2, clustering the results of the step three again by k to obtain a standard profile coefficient array Si= { Sk1, sk+ … … Sk2} k1 is less than or equal to i and less than or equal to k2, and obtaining a CH coefficient array CHj= { CHk1, CHk+ … … CHk2} k1 is less than or equal to j and less than or equal to k2; normalizing the array Si and the array CHj, adding the normalized results, and finding the K value with the largest value of the results; the K value obtained by searching is the K value required by multi-factor clustering.
The normalization comprises the following steps: judging the type of the index to be processed currently as a forward index, a reverse index or a neutral index; let the original value be x j J=1, 2..n, the value after normalization is y j ,j＝1,2...n。
For the forward index, the normalization is as follows:
for the reverse index, the normalization is as follows:
for neutral indicators, the normalization is as follows:
wherein x is m1 ,x m2 For the custom value, it is determined according to the actual index, and the final normalized result is between 0 and 1.
The nuclear density calculation formula is as follows:
wherein D is k For the site set of the same class as the kth site, h is a standard distance, i.e. the sites of the same class which are more than h away from the kth site are not calculated, wherein h is required to be determined according to practical experience and requirements and is generally selected to be 500 meters.
The obtained ρ k (h) And performing spectral clustering on the clustering result with the density evaluation result being larger than the set value Pa.
The method also needs to determine the number of clusters in advance, and considers the actual requirement to set the definition domain of the number of each type of sites as [ n ] min ,n max ]Other applications can set the definition domain of the number of categories as [ k ] according to actual conditions min ,k max ]Wherein n is min ,n max ,k min ,k max Is a self-defined value, and n is set in Hangzhou example min ＝20,n max And (50) selecting the number k of the small categories with the best contour coefficients of each large category in the interval, and obtaining a final clustering result by using a spectral clustering algorithm.
Claims (3)
1. The traffic district dividing method based on the public traffic data is characterized by comprising the following steps:
step one: acquiring bus data and preprocessing the data to meet the calculation requirement;
step two: performing cluster analysis on the data processed in the first step according to actual traffic semantics;
step three: changing different clustering modes of the second step, continuously verifying the clustering result, and finally confirming the clustering number of traffic semantics; evaluating the clustering result by using the standard contour coefficient and the CH coefficient;
step four: carrying out multi-factor clustering by combining the clustering number of the traffic semantics in the step three with the administrative region number of the actual city to ensure that the clustering result obtained in practice fits with the city expectation;
the multi-factor clustering and the corresponding evaluation in the fourth step are specifically as follows: obtaining the number of administrative regions of a city where a data source is located, setting the number of administrative regions as k1, setting the product of the number of administrative regions and the number of traffic semantics as k2, traversing the integer k in k1 to k2, clustering the results of the step three again by k to obtain a standard profile coefficient array Si= { Sk1, sk+ … … Sk2} k1 is less than or equal to i and less than or equal to k2, and obtaining a CH coefficient array CHj= { CHk1, CHk+ … … CHk2} k1 is less than or equal to j and less than or equal to k2; normalizing the array Si and the array CHj, adding the normalized results, and finding the K value with the largest value of the results; the K value obtained by searching is the K value required by multi-factor clustering;
step five: the clustering result generated in the step four is used for distinguishing whether the clustering result is a dense region or not by using a density function, and the dense region is clustered again by spectral clustering so as to meet the requirement of finer division of a central urban area; the density function is nuclear density; the obtained density is the nuclear density of a single site, and the larger the density is, the more similar sites around the site are; taking the average value of the site core density of the same class as the density of the class, wherein the higher the density is, the stronger the aggregation of the sites of the class is, and meanwhile, the closer the sites of the class are to the city center, and the clustering of the sites with high density can meet the finer requirement of the center city area division; in the fifth step, the clustering is performed by using an up-down passenger flow matrix as an index matrix in order to cluster the opposite sites in the same category and achieve the purpose that the opposite sites are in the same traffic cell;
step six: taking the clustering result as a point and acquiring a label according to other results around the point so as to correct the clustering result, correcting error classification in the clustering result by using the characteristic that the sites of the same category have similar macroscopic passenger flow characteristics and microscopic site relativity, and obtaining an actual clustering result;
step seven: and D, after the clustering result corrected in the step six is obtained, forming Thiessen polygons by taking the site as the center, and merging the Thiessen polygons adjacent to the same category into a traffic cell.
2. The traffic cell division method based on public transportation data according to claim 1, wherein the first step is to establish a bus stop index evaluation system before acquiring the public transportation data, and to preprocess the acquired public transportation data according to the bus stop index evaluation system.
3. The traffic zone division method based on public transportation data according to claim 2, wherein the preprocessing comprises: reject the unnecessary and erroneous sites and normalize the data for subsequent computation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110493843.XA CN113393079B (en) | 2021-05-07 | 2021-05-07 | Traffic cell division method based on public transport data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110493843.XA CN113393079B (en) | 2021-05-07 | 2021-05-07 | Traffic cell division method based on public transport data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113393079A CN113393079A (en) | 2021-09-14 |
| CN113393079B true CN113393079B (en) | 2024-01-09 |
Family
ID=77616869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110493843.XA Active CN113393079B (en) | 2021-05-07 | 2021-05-07 | Traffic cell division method based on public transport data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113393079B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639238B (en) * | 2022-02-23 | 2023-02-14 | 东南大学 | Urban expressway traffic state estimation method based on normalized spectral clustering algorithm |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN102890860A (en) * | 2012-09-28 | 2013-01-23 | 北京世纪高通科技有限公司 | Method and device for classifying traffic zone |
| CN107103394A (en) * | 2017-05-27 | 2017-08-29 | 重庆大学 | A kind of real-time passenger flow forecasting of track traffic based on neutral net |
| CN108009973A (en) * | 2017-11-15 | 2018-05-08 | 上海电科智能系统股份有限公司 | A kind of cavitation modeling method of holography urban track traffic object |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN109543883A (en) * | 2018-10-26 | 2019-03-29 | 上海城市交通设计院有限公司 | A kind of hinge flow space-time distribution prediction modeling method based on multisource data fusion |
| CN109934401A (en) * | 2019-03-09 | 2019-06-25 | 吉林大学 | A kind of customization public transport method based on mobile interchange |
| CN110176141A (en) * | 2019-05-09 | 2019-08-27 | 中电海康集团有限公司 | A kind of traffic zone division method and system based on POI and traffic characteristic |
| CN111027888A (en) * | 2019-12-25 | 2020-04-17 | 苏州规划设计研究院股份有限公司 | Connection characteristic analysis method based on track station |
| CN111259965A (en) * | 2020-01-17 | 2020-06-09 | 中国电力科学研究院有限公司 | Method and system for carrying out mean value clustering on electrical characteristic data based on dimension reduction |
| CN111402618A (en) * | 2020-03-27 | 2020-07-10 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining boarding station, storage medium and electronic equipment |
| CN111770452A (en) * | 2020-05-27 | 2020-10-13 | 中山大学 | Mobile phone signaling stop point identification method based on personal travel track characteristics |
| CN116090903A (en) * | 2023-02-06 | 2023-05-09 | 杭州数知梦科技有限公司 | Rail public transportation two-network fusion comprehensive evaluation method based on multi-source data and application thereof |
-
2021
- 2021-05-07 CN CN202110493843.XA patent/CN113393079B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN102890860A (en) * | 2012-09-28 | 2013-01-23 | 北京世纪高通科技有限公司 | Method and device for classifying traffic zone |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN107103394A (en) * | 2017-05-27 | 2017-08-29 | 重庆大学 | A kind of real-time passenger flow forecasting of track traffic based on neutral net |
| CN108009973A (en) * | 2017-11-15 | 2018-05-08 | 上海电科智能系统股份有限公司 | A kind of cavitation modeling method of holography urban track traffic object |
| CN109543883A (en) * | 2018-10-26 | 2019-03-29 | 上海城市交通设计院有限公司 | A kind of hinge flow space-time distribution prediction modeling method based on multisource data fusion |
| CN109934401A (en) * | 2019-03-09 | 2019-06-25 | 吉林大学 | A kind of customization public transport method based on mobile interchange |
| CN110176141A (en) * | 2019-05-09 | 2019-08-27 | 中电海康集团有限公司 | A kind of traffic zone division method and system based on POI and traffic characteristic |
| CN111027888A (en) * | 2019-12-25 | 2020-04-17 | 苏州规划设计研究院股份有限公司 | Connection characteristic analysis method based on track station |
| CN111259965A (en) * | 2020-01-17 | 2020-06-09 | 中国电力科学研究院有限公司 | Method and system for carrying out mean value clustering on electrical characteristic data based on dimension reduction |
| CN111402618A (en) * | 2020-03-27 | 2020-07-10 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining boarding station, storage medium and electronic equipment |
| CN111770452A (en) * | 2020-05-27 | 2020-10-13 | 中山大学 | Mobile phone signaling stop point identification method based on personal travel track characteristics |
| CN116090903A (en) * | 2023-02-06 | 2023-05-09 | 杭州数知梦科技有限公司 | Rail public transportation two-network fusion comprehensive evaluation method based on multi-source data and application thereof |
Non-Patent Citations (5)
| Title |
|---|
| 城市公交数据大脑建设及应用;王瑞利;;交通与港航(第01期);全文 * |
| 城市轨道交通站点分类的聚类方法研究;李向楠;;铁道标准设计(第04期);全文 * |
| 基于公交IC卡数据的OD推算技术研究;周涛;翟长旭;高志刚;;城市交通(第03期);全文 * |
| 改进聚类算法在公交数据挖掘中的应用研究;刘凯;龚兰兰;凌兴宏;周家骎;;计算机技术与发展(第06期);全文 * |
| 走廊层面交通小区划分方法的优化;宋俪婧;朱家正;刘雪杰;陈静;缐凯;;交通运输系统工程与信息(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113393079A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gecchele et al. | Data mining methods for traffic monitoring data analysis: A case study | |
| US20230215272A1 (en) | Information processing method and apparatus, computer device and storage medium | |
| CN113159364A (en) | Passenger flow prediction method and system for large-scale traffic station | |
| CN113393079B (en) | Traffic cell division method based on public transport data | |
| CN110866775A (en) | User air-rail joint inter-city trip information processing method based on machine learning | |
| Yang et al. | Spatial evolution and growth mechanism of urban networks in western China: A multi-scale perspective | |
| CN112884013A (en) | Energy consumption partitioning method based on data mining technology | |
| CN115796942A (en) | Shared bicycle space-time layout determination method based on clustering | |
| Zeng et al. | Analysing airport efficiency in East China using a three-stage data envelopment analysis | |
| CN113240265A (en) | Urban space division method based on multi-mode traffic data | |
| CN114579748A (en) | Method for constructing autonomous traffic system functional architecture | |
| CN114612800A (en) | Method and system for accounting urban building material stock and space-time change | |
| CN109508815B (en) | General activity spatial measure analysis method based on subway IC card data | |
| Wei et al. | Classifying High-Speed Rail Stations in the Yangtze River Delta, China: The Node-Place Modelling Approach | |
| Li et al. | Data-driven bus timetabling with spatial-temporal travel time | |
| CN109711447A (en) | A kind of special population event early warning and monitoring method and device | |
| CN111710157A (en) | Method for extracting hot spot area of taxi | |
| CN113763044B (en) | High-speed railway dynamic pricing method based on passenger travel behavior analysis | |
| Qiu et al. | Layout planning towards urban transportation hub based on clustering analysis method | |
| Seo et al. | Strategy for introducing autonomous driving mobility service in transportation vulnerable areas: A case study of gyeonggi province in Republic of Korea | |
| CN117370905B (en) | Method for classifying comprehensive passenger transport hubs facing abnormal events | |
| FENG et al. | Analysis of Satisfaction Degree of Senior-Friendly Public Transit: A Case Study in Shanghai [J] | |
| Radam et al. | Typical river transport for Banjarmasin based on the criteria of the National Transportation System | |
| Gong et al. | Traffic Status Identification Based On Clustering Algorithm | |
| Zhang et al. | Synergetic Development Measure of Airport Groups Composite System and Its Influencing Factors Analysis: Some Evidence from China |
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 |