CN110232421B - Step-by-step combined OD flow direction space-time combined clustering method - Google Patents

Step-by-step combined OD flow direction space-time combined clustering method Download PDF

Info

Publication number
CN110232421B
CN110232421B CN201910540421.6A CN201910540421A CN110232421B CN 110232421 B CN110232421 B CN 110232421B CN 201910540421 A CN201910540421 A CN 201910540421A CN 110232421 B CN110232421 B CN 110232421B
Authority
CN
China
Prior art keywords
flow direction
flow
cluster
similarity
merging
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.)
Expired - Fee Related
Application number
CN201910540421.6A
Other languages
Chinese (zh)
Other versions
CN110232421A (en
Inventor
邬群勇
项秋亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuzhou University
Original Assignee
Fuzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fuzhou University filed Critical Fuzhou University
Priority to CN201910540421.6A priority Critical patent/CN110232421B/en
Publication of CN110232421A publication Critical patent/CN110232421A/en
Application granted granted Critical
Publication of CN110232421B publication Critical patent/CN110232421B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to a spatial-temporal joint clustering method for gradually merging OD flow directions, which comprises the following steps: preprocessing the original flow direction data to construct an OD flow direction set F; flow direction F is counted by utilizing space-time similarity measurementiNumber of num of flow directions similar to the circumferencei(ii) a Screening out initial clustering clusters and constructing a flow direction cluster set Cset according to the initial clustering clusters; and combining the OD flow direction cluster step by step according to the sequence of the OD flow direction cluster combination grade, updating the flow direction cluster set Cset, and finishing the clustering process of the OD flow direction. The method fully considers the influence of factors such as OD flow direction length, angle, time and the like on OD flow direction clustering in the flow direction similarity measurement, the clustering cluster comprises space characteristics and time characteristics, clustering results of different time scales and space scales can be obtained by adjusting time parameters and space parameters in the similarity measurement, and the method has high practical value.

Description

Step-by-step combined OD flow direction space-time combined clustering method
Technical Field
The invention relates to a spatio-temporal joint clustering method for gradually merging OD flow directions.
Background
With the rapid development and popularization of mobile positioning technology, large-data-volume geographic movement data such as human daily activity trajectory data, group migration data, vehicle trajectory data and the like are more and more easily acquired. The OD flow direction data is special mobile data, only the position information of Origin and Destination is reserved but actual track information is ignored, the flow direction and hot points of the traveling of residents can be identified by clustering the vehicle OD flow direction data with large data volume level, the traveling characteristics of urban residents, the time-space relation of group flow among different areas of the city and the change trend of the group flow can be accurately grasped, and the OD flow direction data has important significance for traffic planning design and city management.
At present, the home and abroad clustering methods for OD flow direction mainly comprise a clustering method based on scanning statistics, a density clustering method and a hierarchical clustering method. The existing clustering method has the following problems that a part of clustering algorithms have relations among cut OD points for clustering; part of algorithms can only identify flow direction clusters, and can not automatically cluster the whole region; most algorithms do not consider time factors or only divide time periods for clustering, and clustering results cannot accurately reflect the time attribute of OD flow direction clusters.
Disclosure of Invention
In view of the above, the present invention provides a method for spatio-temporal joint clustering by combining OD flow directions step by step, which solves the problem of spatio-temporal joint clustering by OD flow directions on the basis of not splitting the relation between the O point and the D point.
In order to achieve the purpose, the invention adopts the following technical scheme:
a spatial-temporal combined clustering method for gradually merging OD flow directions comprises the following steps:
step S1: collecting track data to be detected;
step S2: extracting original flow direction data from the track data and preprocessing the original flow direction data to form an OD flow direction set F;
step S3: counting each OD flow direction F in F according to the similarity measurement of the OD flow directionsiSimilar flow direction number num ofi；
Step S4: if the flow direction is F, the similar flow direction numbers of all OD flow directions calculated in step S2 are usediSatisfies the condition numiIf > 0, flow will be to FiFlow as original OD flow to class cluster CiScreening out all OD flow directions F meeting the conditionsiConstructing a flow direction cluster Cset;
step S5: presetting the levels of the high similarity highSim between the clusters and the similarity threshold, and combining the two levels to set the OD flow direction cluster merging level;
step S6: traversing OD flow direction class cluster merging levels, and screening flow direction class clusters C to be merged according with the merging conditions of the current merging levelsjAnd CkConstructing cluster combinations to be merged, combining all the cluster combinations to be merged to form a set Merge, and ranking according to highSim between the cluster combinations to be mergedSequentially combining the cluster types to be combined in the Merge according to the sequence from big to small of the highSim, and skipping if the cluster types which are already combined exist in the Merge;
step S7: and (5) circulating the step (S6) until the merging of all the class clusters under the condition of merging grades is completed, and obtaining a final flow direction class cluster set Cset, namely a spatio-temporal joint clustering result of the flow direction of the track data OD to be detected.
Further, the step S2 is specifically: and extracting the serial number of each piece of track data, longitude and latitude coordinate information of the O point and the D point and time information from the track data to form original flow direction data, and preprocessing all the flow direction data to form an OD flow direction set F.
Further, the measure of similarity of the OD flow direction is as follows:
sim(Fi，Fj)＝1-func(ratioO)*func(ratioD)*func(ratioTime)/23
ratioO＝dist(Oi，Oj)/disLimit
ratioD＝dist(Di，Dj)/disLimit
ratioTime＝span(timei，timej)/timeLimit
Figure BDA0002102377350000021
wherein, dist (O)i，Oj) In the direction of flow FiAnd FjDistance at point O, dist (D)i，Dj) In the direction of flow FiAnd FjDistance at point D, span (time)i，timej) In the direction of flow FiAnd FjThe time limit is a manually input time parameter, the unit is minutes or hours, and the distance is a spatial similarity parameter.
Further, the distimit is a spatial similarity parameter, and the calculation method is as follows:
Figure BDA0002102377350000031
wherein len (F)i) In the direction of flow FiLength of (k)>3; when sim (F)i，Fj)∈[0，0.875]While flowing to FiAnd FjSpatio-temporal similarity, and sim (F)i，Fj) The larger, the flow direction FiAnd FjThe higher the degree of spatiotemporal similarity.
Further, the definition and merging level of the preset inter-cluster high similarity highSim and the similarity threshold are set as follows:
(1) high similarity between clusters highSim: the ratio of the number of the flow direction combinations with high similarity between two flow direction clusters to all combinations is calculated as follows:
Figure BDA0002102377350000032
wherein m and n are flow direction clusters Cm，CnThe number of middle flow directions; fi∈Cm，Fj∈Cn；
threshold∈[0,0.875]Is a similarity threshold; considering the asymmetry of the similarity measure formula between flow directions, i.e. sim (F)i Fj)≠sim(Fj,Fi) The similarity value between the two flow directions is the larger value of the two calculation modes; (2) the similarity threshold is set to a levels t1、t2、…、ti、…、ta(wherein 0.875. gtoreq.t1> t2>…>ti>…>ta>0) The inter-cluster high similarity highSim is set to b levels h1、h2、…、hj、…、 hb(wherein 1. gtoreq.h1>h2>…>hj>…>hbNot less than 0), the obtained step-by-step merging grade is t1，h1、t1，h2、…、 ta，hb-1、ta，hbA x b merged levels.
Further, the merging condition of the current merging level in step S6 is as follows:
when the merging level is ti，hjWhen, if t isiIf the minimum level is not the similarity threshold, the merging condition is:
(1)highSim(Cm,Cn)≥hj，(threshold＝ti)；
(2)highSim(Cm,Cn)≥1，(threshold＝ti-1)；
if t isiIf the minimum level is the similarity threshold, the merging condition is as follows:
(1)highSim(Cm,Cn)≥hj，(threshold＝ti)；
(2) flow direction cluster CmAnd CnThe flow directions in (2) are similar in pairs.
Compared with the prior art, the invention has the following beneficial effects:
1. the method fully considers the length, angle and time of the flow direction, clusters the OD flow direction, and obtains a cluster which comprises both time attributes and space attributes;
2. according to the method, the clustering results of different time scales can be obtained by adjusting the parameter timeLimit in the similarity measurement formula of the OD flow direction, the larger the parameter timeLimit is set, the larger the time scale of the clustering cluster is, and vice versa;
3. according to the method, clustering results of different spatial scales can be obtained by adjusting the parameter k in the similarity measurement formula of the OD flow direction, the larger the parameter k is set, the smaller the spatial scale of the clustering cluster is, and vice versa;
4. the method controls the OD flow direction cluster merging sequence by setting the OD flow direction cluster merging level to ensure the accuracy of the clustering result, and simultaneously, a plurality of cluster combinations to be merged are arranged at each merging level, so that the clustering efficiency is greatly improved compared with the classic bottom-up hierarchical clustering method that only one cluster combination is merged in each iteration, and the running time is greatly reduced under the condition that the OD flow direction data volume is large.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
FIG. 2 is an OD flow data in one embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating an OD flow direction cluster merging process according to an embodiment of the present invention;
fig. 4 shows the clustering results at the early peak (7: 00-10: 00) and the late peak (17: 00-20: 00) according to an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
In this embodiment, referring to fig. 1, the present invention provides a method for merging OD flow directions step by step and spatio-temporal joint clustering, which is characterized by comprising the following steps:
step S1: extracting the number of each piece of track data, longitude and latitude coordinate information of an O point and a D point and time information from track data of a drop-out rental car of a metropolis of 11-1-year-2016, forming original flow direction data, and preprocessing all flow direction data to form an OD flow direction set F; the pretreatment is as follows: and taking a division map of the research area range as a base map, overlapping the original flow direction data with the map, and eliminating the OD flow direction of the O point or the D point outside the research area. The obtained OD flow data is shown in fig. 2.
Flow direction FiThe object may be designed according to the following data structure:
Figure BDA0002102377350000051
step S2: counting each OD flow direction F in F by using OD flow direction similarity measurement formulaiNumber of similar flow directions numi(ii) a The OD flow direction similarity measure is formulated as follows:
sim(Fi，Fj)＝1-func(ratioO)*func(ratioD)*func(ratioTime)/23
ratioO＝dist(Oi，Oj)/disLimit
ratioD＝dist(Di，Dj)/disLimit
ratioTime＝span(timei，timej)/timeLimit
Figure BDA0002102377350000052
wherein, dist (O)i,Oj) In the direction of flow FiAnd FjDistance at point O, dist (D)i,Dj) In the direction of flow FiAnd FjDistance at point D, span (time)i,timej) In the direction of flow FiAnd FjThe time difference of getting on the vehicle or getting off the vehicle is manually input time parameter, the unit is minutes or hours, in this embodiment, the input of the time limit is 1 h. disLimit is a spatial similarity parameter, and the calculation method comprises the following steps:
Figure BDA0002102377350000061
wherein len (F)i) In the direction of flow FiLength of (k)>3. In order to prevent the spatial characteristics of the clustering result from being very fuzzy due to the excessively long flow direction length of the OD, the invention adds a limiting condition that when the flow direction length is more than 5000m, the distimit is a fixed value 5000/k (unit: meter)
When sim (F)i，Fj)∈[0，0.875]While flowing to FiAnd FjSpatio-temporal similarity, and sim (F)i，Fj) The larger, the flow direction FiAnd FjThe higher the degree of spatiotemporal similarity.
In the embodiment, the parameter timeLimit is selected to be 1h, the maximum time span of the obtained clustering cluster is 1h, if the timeLimit is larger, the maximum time span of the obtained clustering cluster is longer, and vice versa. In the embodiment, the parameter k is selected to be 4, if k is larger, the spatial range of the obtained cluster is smaller, and vice versa.
Step S3: if the flow direction is F, the number of similar flow directions of all OD flow directions calculated in step S2iSatisfy the requirement ofCondition numi>0, then flow will be to FiFlow as original OD flow to class cluster CiScreening out all OD flow directions F meeting the conditionsiConstructing a flow direction cluster Cset; original OD flow to cluster CiIs namely { Fi} flow direction class set Cset is { C1，C2，…，Ci，…}。
Step S4: setting the grade of the high similarity highSim between the clusters and the grade of the similarity threshold, and combining the two grades to set the OD flow direction cluster merging grade; the settings for the above levels are as follows:
the grades of the high similarity highSim among the clusters are set to be 0.75, 0.5, 0.25 and 0;
the level of the similarity threshold is set to 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1;
the level of OD flow direction cluster merging is set as: threshold is 0.8, highSim is 0.75, threshold is 0.8, highSim is 0.5, threshold is 0.8, highSim is 0.25, …, threshold is 0.1, highSim is 0.25, threshold is 0.1, highSim is 0.0, highSim is 0.1, highSim is 0.8;
when the above levels are more set, the OD flow is more accurate to the clustering result, but the clustering time is also longer.
Step S5: traversing OD flow direction class cluster merging levels, and screening flow direction class clusters C to be merged according with the merging conditions of the current merging levelsmAnd CnConstructing cluster combinations to be merged, combining all the cluster combinations to be merged to form a set Merge, sequencing the Merge according to highSim among the cluster combinations to be merged, and merging the Merge according to the descending order of the highSimiClass cluster to be merged if MergeiIf the cluster class exists, the merging is already finished, the new Cset is obtained after all the merging is finished, and the process is executed until the merging under the condition of the merging level of all the cluster classes is finished. The above-mentioned current merging level merging condition and merging process are as follows:
when the merging level of the flow direction cluster is highSim ═ 0.75 and threshold ═ 0.8(0.8 is not the minimum level of the similarity threshold), the merging condition is that
(1)highSim(Cm,Cn) Not less than 0.75 (the similarity threshold of highSim is calculated to be 0.8);
(2)highSim(Cm,Cn) 1 (similarity threshold of highSim is calculated to be 0.7); when the merging level of the flow direction cluster is highSim ═ 0.75 and threshold ═ 0.1(0.1 is the minimum level of the similarity threshold), the merging condition is that
(1)highSim(Cm,Cn) Not less than 0.75 (the similarity threshold of highSim is calculated to be 0.1);
(2) class CmAnd CnThe flow directions in (1) are similar in pairs;
the merging process of OD flow to clusters with merging rank highSim of 0.75 and threshold of 0.8 is shown in fig. 3.
The above specific implementation steps and parameter settings were followed to obtain spatio-temporal joint clustering results of OD flow directions, showing the clustering results at early peak (7: 00-10: 00) and late peak (17: 00-20: 00), as shown in fig. 4. Each flow direction class cluster in fig. 4 has a time attribute.
By combining the specific implementation mode and the case, the method can effectively implement space-time combined clustering on the OD flow direction data, so that the travel modes of urban residents at different moments can be extracted from disordered OD data, and reasonable suggestions are provided for urban traffic allocation and infrastructure construction.
The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the claims of the present invention should be covered by the present invention.

Claims (6)

1. A method for combining OD flow directions step by step and performing spatiotemporal joint clustering is characterized by comprising the following steps:
step S1: collecting track data to be detected;
step S2: extracting original flow direction data from the track data and preprocessing the original flow direction data to form an OD flow direction set F;
step S3: counting each OD flow direction F in the F according to the similarity measurement of the OD flow directionsiIs likeNumber of streams numi；
Step S4: if the flow direction is F, the similar flow direction numbers of all OD flow directions calculated in step S2 are usediSatisfies the condition numiIf > 0, flow will be to FiFlow as original OD flow to class cluster CiScreening out all OD flow directions F meeting the conditionsiConstructing a flow direction cluster Cset;
step S5: presetting the levels of the high similarity highSim between the clusters and the similarity threshold, and combining the two levels to set the OD flow direction cluster merging level;
step S6: traversing OD flow direction class cluster merging levels, and screening flow direction class clusters C to be merged according with the merging conditions of the current merging levelsjAnd CkConstructing cluster combinations to be merged, combining all the cluster combinations to be merged to form a set Merge, sequencing according to highSim among the cluster combinations to be merged, merging the cluster combinations to be merged in the Merge according to the descending order of the highSim, and skipping if the cluster combinations which are already merged exist in the Merge;
step S7: and (5) circulating the step (S6) until the merging of all the class clusters under the condition of merging grades is completed, and obtaining a final flow direction class cluster set Cset, namely a spatio-temporal joint clustering result of the flow direction of the track data OD to be detected.
2. The method according to claim 1, wherein the step S2 specifically comprises: and extracting the serial number of each piece of track data, longitude and latitude coordinate information of the O point and the D point and time information from the track data to form original flow direction data, and preprocessing all the flow direction data to form an OD flow direction set F.
3. The method of claim 1, wherein the OD flow direction spatiotemporal joint clustering method is combined step by step, and the OD flow direction similarity measure is as follows:
sim(Fi，Fj)＝1-func(ratioO)*func(ratioD)*func(ratioTime)/23
ratioO＝dist(Oi，Oj)/disLimit
ratioD＝dist(Di，Dj)/disLimit
ratioTime＝span(timei，timej)/timeLimit
Figure FDA0002102377340000021
wherein, dist (O)i，Oj) In the direction of flow FiAnd FjDistance at O Point, dist (D)i，Dj) In the direction of flow FiAnd FjDistance at point D, span (time)i，timej) In the direction of flow FiAnd FjThe time limit is a manually input time parameter, the unit is minutes or hours, and the distance is a spatial similarity parameter.
4. The method according to claim 3, wherein the distimit is a spatial similarity parameter and is calculated by:
Figure FDA0002102377340000022
wherein len (F)i) In the direction of flow FiK ═ 3; when sim (F)i，Fj)∈[0，0.875]While flowing to FiAnd FjSpatio-temporal similarity, and sim (F)i，Fj) The larger, the flow direction FiAnd FjThe higher the degree of spatiotemporal similarity.
5. The method as claimed in claim 1, wherein the definitions of the preset inter-cluster high similarity highSim and the similarity threshold and the merging level are set as follows:
(1) high similarity between clusters highSim: the ratio of the number of highly similar flow direction combinations between two flow direction clusters to all combinations is calculated as follows:
Figure FDA0002102377340000031
wherein m and n are flow direction clusters Cm，CnThe number of middle flow directions; fi∈Cm，Fi∈Cn；
threshold∈[0，0.875]Is a similarity threshold; considering the asymmetry of the similarity measure formula between flow directions, i.e. sim (F)iFj)≠sim(Fj，Fi) The similarity value between the two flow directions is a larger value in two calculation modes;
(2) the similarity threshold is set to a levels t1、t2、...、ti、...、ta(wherein 0.875. gtoreq.t1＞t2＞...＞ti＞...＞ta> 0), high similarity between clusters, highSim, is set to b levels h1、h2、...、hj、...、hb(wherein 1. gtoreq.h1＞h2＞...＞hj＞...＞hbNot less than 0), the obtained level-by-level merging level is t1，h1、t1，h2、...、ta，hb-1、ta，hbA x b merged levels.
6. The method for sequential combination of OD flow direction spatiotemporal joint clustering according to claim 1, wherein the combination condition of the current combination level in the step S6 is as follows:
when the merging level is ti，hjWhen, if t isiIf the minimum level is not the similarity threshold, the merging condition is:
(1)highSim(Cm，Cn)≥hj，(threshold＝ti)；
(2)highSim(Cm，Cn)≥1，(threshold＝ti-1)；
if t isiIf the minimum level is the similarity threshold, the merging condition is as follows:
(1)highSim(Cm，Cn)≥hj，(threshold＝ti)；
(2) flow direction cluster CmAnd CnThe flow directions in (1) are similar in pairs.
CN201910540421.6A 2019-06-21 2019-06-21 Step-by-step combined OD flow direction space-time combined clustering method Expired - Fee Related CN110232421B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910540421.6A CN110232421B (en) 2019-06-21 2019-06-21 Step-by-step combined OD flow direction space-time combined clustering method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910540421.6A CN110232421B (en) 2019-06-21 2019-06-21 Step-by-step combined OD flow direction space-time combined clustering method

Publications (2)

Publication Number Publication Date
CN110232421A CN110232421A (en) 2019-09-13
CN110232421B true CN110232421B (en) 2022-05-24

Family

ID=67857109

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910540421.6A Expired - Fee Related CN110232421B (en) 2019-06-21 2019-06-21 Step-by-step combined OD flow direction space-time combined clustering method

Country Status (1)

Country Link
CN (1) CN110232421B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110781958B (en) * 2019-10-25 2022-06-17 福州大学 OD flow direction clustering method based on maximum spanning tree and optimal graph segmentation
CN111753888B (en) * 2020-06-10 2021-06-15 重庆市规划和自然资源信息中心 Multi-granularity time-space event similarity matching working method in intelligent environment
CN114937165B (en) * 2022-07-20 2022-10-28 浙江大华技术股份有限公司 Cluster merging method, device, terminal and computer readable storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107770744A (en) * 2017-09-18 2018-03-06 上海世脉信息科技有限公司 The identification of travelling OD node and hop extracting method under big data environment

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7958125B2 (en) * 2008-06-26 2011-06-07 Microsoft Corporation Clustering aggregator for RSS feeds

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107770744A (en) * 2017-09-18 2018-03-06 上海世脉信息科技有限公司 The identification of travelling OD node and hop extracting method under big data environment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
一种逐级合并OD流向时空联合聚类算法;项秋亮等;《地球信息科学学报》;20200630;全文 *
顾及出租车OD点分布密度的空间Voronoi剖分算法及OD流可视化分析;信睿等;《地球信息科学学报》;20151030;全文 *

Also Published As

Publication number Publication date
CN110232421A (en) 2019-09-13

Similar Documents

Publication Publication Date Title
CN110232421B (en) Step-by-step combined OD flow direction space-time combined clustering method
CN110516708B (en) Path prediction method based on track and road network matching
CN108596202B (en) Method for calculating personal commuting time based on mobile terminal GPS positioning data
CN106912015B (en) Personnel trip chain identification method based on mobile network data
CN106651027B (en) Internet regular bus route optimization method based on social network
CN110176141B (en) Traffic cell division method and system based on POI and traffic characteristics
CN108415975B (en) BDCH-DBSCAN-based taxi passenger carrying hot spot identification method
WO2022089031A1 (en) Network optimization method based on big data and artificial intelligence
CN109359682B (en) A kind of Shuttle Bus candidate's website screening technique based on F-DBSCAN iteration cluster
CN110390349A (en) Bus passenger flow volume based on XGBoost model predicts modeling method
CN104318324B (en) Shuttle Bus website and route planning method based on taxi GPS records
CN105355049B (en) A kind of highway evaluation of running status method based on macroscopical parent map
CN108961758A (en) A kind of crossing broadening lane detection method promoting decision tree based on gradient
CN107622085A (en) A kind of adaptive method of trajectory clustering based on grid and density
WO2020172954A1 (en) Living circle identification method based on positioning data
CN110555544B (en) Traffic demand estimation method based on GPS navigation data
CN107818332B (en) Expressway interchange service range analysis method and device
CN108806287B (en) Traffic signal timing method based on cooperative optimization
Liao et al. Spatial distribution evolution and accessibility of A-level scenic spots in Guangdong Province from the perspective of quantitative geography
CN110443311B (en) Traffic track clustering similarity calculation method based on shape factor adjustment
CN109520499A (en) Region isochronal method in real time is realized based on vehicle GPS track data
CN110659774B (en) Big data method driven parking demand prediction method
CN113342873B (en) Population analysis unit division method based on city morphology and convergence mode
CN114723596A (en) Urban functional area identification method based on multi-source traffic travel data and theme model
CN111738527B (en) Urban traffic cell division method based on hot spot detection model

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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20220524

CF01 Termination of patent right due to non-payment of annual fee