CN108427965B - Hot spot area mining method based on road network clustering - Google Patents
Hot spot area mining method based on road network clustering Download PDFInfo
- Publication number
- CN108427965B CN108427965B CN201810179464.1A CN201810179464A CN108427965B CN 108427965 B CN108427965 B CN 108427965B CN 201810179464 A CN201810179464 A CN 201810179464A CN 108427965 B CN108427965 B CN 108427965B
- Authority
- CN
- China
- Prior art keywords
- clustering
- points
- data
- road network
- track
- 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 27
- 238000005065 mining Methods 0.000 title claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000010586 diagram Methods 0.000 claims abstract description 5
- 230000000694 effects Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 2
- 230000006872 improvement Effects 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000033001 locomotion Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 238000007418 data mining Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a travel hot spot region mining method based on road network track clustering. In the method, taxi tracks are mapped to a road network, and a clustering method combining interest points and tracks collected from an actual road is adopted. And in combination with a density peak clustering algorithm, an OPAM algorithm based on density peak optimization initial center, namely DP-OPAM, is provided. The algorithm adopts the local density of the data points and the shortest distance from the points to the higher density points, and selects the category to which the data points with higher density and closest distance belong by adopting a decision diagram as an initial clustering center. And obtaining a clustering result by adopting an OPAM clustering algorithm for increasing reverse learning according to the initial clustering center. The new algorithm is compared with the original OPAM algorithm, the new algorithm can automatically determine the clustering center, improve the accuracy and the clustering time and realize the analysis of the user travel hot spot region.
Description
Technical Field
The invention belongs to a data mining method, and particularly relates to a taxi track clustering method based on a road network.
Background
The intelligent transportation is as the hot spot of present world transportation development, when supporting transportation management, pays more attention to satisfying the demand of people's trip and public transportation trip. In recent years, the construction of intelligent traffic systems has been rapidly developed, and many advanced technologies are widely applied to the intelligent traffic systems. The wide application of the GPS equipment makes the extraction of the track more convenient. The GPS equipment can collect a large amount of mobile position sequence information and vehicle-mounted state information, and the data contains abundant traffic information and user behavior information. By analyzing and mining the trajectory data, the traffic condition can be known, the journey can be reasonably planned, the behavior characteristics of the crowd can be found, and the traffic condition can be improved in an assisting manner.
The taxi track can cover urban road network traffic in all directions, and not only can reflect real-time traffic intensity and circulation degree, but also can reflect the travel rule and the regional characteristics of people. Therefore, the mass data of the taxi track is analyzed, the deep information hidden in the data is found, the data overall feature description and the traffic situation development prediction are analyzed by means of a data mining technology, and the important functions are played in the aspects of providing support for traffic detection and road control of a traffic management department and the like.
The cluster analysis is a common data mining technology, and can be used as a tool for obtaining the distribution condition of data, so that the characteristics of each cluster of data can be observed conveniently, and a specific cluster set is further analyzed in a centralized manner. In addition, it can be used as a preprocessing step of other algorithms (such as classification and qualitative induction algorithms). And (4) clustering the tracks of the moving objects, and discovering the motion rules and behavior patterns of the moving objects by discovering similar motion tracks, extracting motion characteristics and the like. The taxi track is composed of discontinuous sequence points. In the traditional clustering analysis of the track, when the similarity of the track is measured, the linear distance between points is mostly considered, and the real distance reachable situation is ignored.
The cluster analysis research of the vehicle track mainly comprises two methods: one is to classify and compare the whole track as an object, and the other is to classify the track into sub-track segments according to a certain standard and classify the obtained sub-track segments. The method has the advantages that the method is simple and is convenient for visually evaluating the similarity between the tracks, but meanwhile, the method cannot well distinguish the local characteristics of the tracks, and the clustering effect is often not ideal. The latter method can improve the problem brought by the former in the aspect of track local characteristics, and has better clustering effect on tracks of different shapes. However, the track segmentation method has a large influence on the clustering result, and different segmentation methods may cause a large difference in the result.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. The hot spot region mining method based on road network clustering can remarkably improve clustering effect and realize user travel region mining. The technical scheme of the invention is as follows:
a hot spot region mining method based on road network clustering comprises the following steps:
step 1: collecting a taxi track data set, carrying out data preprocessing including data standardization and normalization, reserving effective fields, deleting redundant data, and obtaining preprocessed upper and lower taxi track points;
step 2: determining the latitude and longitude range of a city, and extracting interest points of the city including a shopping mall and a school on an open source website;
and step 3: acquiring city road network information, and mapping track points into a road network;
and 4, step 4: selecting 80% of the upper and lower passenger track points of the vehicle preprocessed in the step 1 as a training set, and clustering out an area representing an upper and lower hot spot by adopting an improved OPAM algorithm based on a density peak value optimization initial center, wherein the improvement points mainly comprise: selecting an initial clustering center by using a density peak, wherein the selection of initial points is more accurate and convenient, the rest 20 percent of the initial points are used as a test set, and the clustering effect of a model built by taking 80 percent of upper and lower guest track points as a training set is tested;
and 5: and (4) inputting the interest points with the road network information acquired in the step (2) into the model in the step (4), clustering to obtain the hot spot activity areas of residents with road network characteristics, comparing the clustering result with the acquired interest points, and judging the hot spot areas of the residents going out.
Further, the step 1 specifically comprises: firstly, a taxi track data set of a city in a month is collected, track data of one week with a more concentrated city data volume is selected for data preprocessing, effective fields such as track point longitude and latitude data of an on-off taxi, data of the on-off taxi and the like are reserved, and redundant data are deleted.
Further, the step 2 determines the latitude and longitude range of the city, and extracts the interest points of the city including the shopping mall and the school from the open source website, specifically:
firstly, inputting the longitude and latitude range of a target city on an open source website opentreetmap, downloading a map of the whole city, and leading out ways in OSM map data to represent the moving track of a user and nodes to represent a path. And selecting node labels as residual, school and shop as representative interest points.
Further, step 3 acquires road network information of the city, and maps the track points into the road network, specifically:
obtaining electronic map data by adopting TAREEG network service project, extracting road network information of the city, projecting the obtained GPS moving track to the obtained road network map by ST-Matching model after extracting the road network data of the city, and obtaining (j-1+1) continuous moments p of the driver passing each road section e i ,…,p j The track points.
Further, the step 4 specifically includes: firstly, selecting 80% of processed upper and lower vehicle track points as a training set, clustering out an area representing an upper and lower vehicle hot point by adopting an improved inverse learning-based partitioning and clustering algorithm (OPAM) around a central point, wherein the improved OPAM algorithm is divided into three stages: initializing a first stage, constructing a decision diagram, and selecting density peak points in an upper right corner area far away from most samples as an initial clustering center, wherein the number of the density peak points is a cluster number k; constructing initial clustering centers, calculating the minimum distance between each point in the data set and each clustering center, distributing the rest sample points to the nearest initial clustering center to form initial division, and calculating the square sum of clustering errors; and the third stage reversely learns and substitutes a division clustering algorithm (PAM) surrounding a central point, k clusters obtained by a typical PAM clustering algorithm and k reverse clusters obtained after reverse learning are arranged and combined to obtain k multiplied by k cluster combinations, and the cluster combination with the maximum outline coefficient is searched.
Further, the PAM algorithm comprises the following steps:
(1) from a given data set DThe method comprises the steps of selecting k elements, marking the selected k elements as initial representative objects or seeds o j ；
(2) Calculating any non-representative object o in the data set D according to the Euclidean distance calculation mode i And k representative objects, and o i Allocating to the cluster represented by the representative object closest to the cluster;
(3) arbitrarily selecting a non-representative object o random ；
(4) Calculating the total cost S:
S＝dist(p,o random )-dist(p,o j )
(5) if the total cost S < 0, indicating a non-representative object o random Is a better solution, element o random Can replace the element o j Forming a new k representative object set, continuously returning to the step (2), and performing a new round of object allocation;
(6) if the total cost S > 0, it indicates that the representative object o j And (4) returning to the step (3), and reselecting the non-representative object to compare the total cost until the cost S is not changed any more, so that the k clusters with the minimum total cost are obtained.
The invention has the following advantages and beneficial effects:
according to the method, travel hotspot analysis of residents is combined with a road network, the method of combining the interest areas in the specific road network with the original cluster clusters is adopted, the original clusters are gathered to the interest area features contained in the new clusters again to show the travel hotspot areas of the residents, and the defects in the aspects of time and space in Euclidean space are overcome. The method adopts a method of optimizing the initial center based on the density peak value to construct a decision tree to determine the initial center, thereby reducing the calculation amount and leading the clustering accuracy to be higher. And through the combination clustering of the special interest points and the tracks, the problems of data sparsity and huge calculation amount are solved, and the track behavior analysis of the user is realized.
Drawings
FIG. 1 is a flow chart of a PAM clustering algorithm according to a preferred embodiment of the present invention;
fig. 2 is a flow chart of an OPAM clustering algorithm.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings. The described embodiments are only some of the embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
as shown in FIG. 2, the method for mining the hot spot region by combining the OPAM clustering algorithm based on the density peak value optimization initial center and the road network comprises the following specific steps:
step 1: and collecting a taxi track data set of a certain month in a city, and selecting track data of a week with more concentrated city data volume. And (4) carrying out data preprocessing, reserving effective fields such as track point longitude and latitude data of the vehicles on and off, time data of the vehicles on and off and the like, and deleting redundant data.
Step 2: and inputting the latitude and longitude range of the target city on the opentreetmap of the open source website, and downloading the map of the whole city. The way in the derived OSM map data represents the movement locus of the user, and the node represents the path. Since the way object in the OSM source data records the user movement track, the way does not only represent the road information, but also represents the building information, such as: an exterior profile of a building. Therefore, we also need to filter the way objects accordingly, and remove the unnecessary way information. On the other hand, the number of node sampling points in the downloaded map source data is very large, and the intersection points of the ways are only needed to be known in the actual route planning process. There are many tags representing different attributes in the way and the node, the only attribute in the way is reserved as highway attribute value, residual, service, living _ string, unclassified, trunk _ link, secondary _ link, primary, tertiary _ link, and the node deletes the node with the same node but different way. And selecting node labels as residual, school and shop as representative interest points.
And step 3:
the collected driver's GPS track contains the information that the instantaneous position coordinates hide which road section the driver is on at each moment. Using TAREEG web service itemsAnd obtaining electronic map data and extracting road network information of the city. After urban road network data is extracted, the obtained GPS movement track is projected onto the obtained road network map through an ST-Matching model, and (j-1+1) continuous moments p when a driver passes through each road section e are obtained i ,…,p j The track points.
Step 4
And selecting 80% of the processed upper and lower passenger track points of the vehicle as a training set, and clustering out an area representing an upper and lower hot spot by adopting an improved OPAM algorithm. The DP-OPAM algorithm is divided into three phases: initializing, constructing an initial clustering center, reversely learning and substituting the initial clustering center into a PAM algorithm.
Let the data point of the sample be i and the local density be ρ i Local density ρ of data point i i The calculation method is as follows:
wherein,
d c to truncate the distance, the local density is essentially the relative density between data points for a large amount of data, so d c Has robustness. Definition of δ i Is the minimum of the distance of a data point i to any point that is denser than it: delta. for the preparation of a coating i ＝min j:ρj＞ρi (d ij ) For the point with the maximum local density, special treatment is needed, and the point is generally changed into the following value: delta i ＝max j (d ij )
First phase initialization
(1) Initializing and solving a distance matrix D ═ D between data points ij I, j ═ 1.. times, n, and determine the truncation distance.
(2) According to the formula S ═ dist (p, o) random )-dist(p,o j ) Obtaining local density by formula
Calculating a high density distance delta of a sample i 。
(3) Constructing rho as a horizontal axis and a decision diagram of a delta longitudinal axis, selecting data points with higher local density rho and high density distance delta, taking density peak points obviously far away from the upper right corner area of most samples as initial clustering centers, and taking the number of the density peak points as a cluster number k.
Second stage construction of initial clustering center
(1) And calculating the minimum distance between each point in the data set and each cluster center, distributing the rest sample points to the nearest initial cluster center to form initial division, and calculating the square sum of the clustering errors.
Third-stage reverse learning and substituting PAM algorithm
(1) And performing reverse learning on the k original clusters to obtain k corresponding reverse clusters.
(2) And (3) carrying out permutation and combination on k clusters obtained by a typical PAM clustering algorithm and k reverse clusters obtained after reverse learning to obtain k multiplied by k cluster combinations.
(3) Calculating the inter-cluster spacing a (o), the inter-cluster spacing b (o) and the contour coefficient s (o) of each cluster combination, and comparing s 1 ,s 2 ,...,s k×k And finding the cluster combination with the maximum contour coefficient.
The PAM algorithm comprises the following steps:
(1) arbitrarily selecting k elements from a given dataset D, marking the selected k elements as initial representative objects or seeds o j ；
(2) Calculating any non-representative object o in the data set D according to the Euclidean distance calculation mode i And k representative objects, and o i Allocating to the cluster represented by the representative object closest to the cluster;
(3) arbitrarily selecting a non-representative object o random ；
(4) Calculating the total cost S:
S＝dist(p,o random )-dist(p,o j )
(5) if the total cost S is less than 0, indicating that the non-representative object o random Is a better solution, element o random Can replace the element o j Forming a new set of k representative objects, and continuously returning to the step (2) to make a new roundThe object allocation of (1);
(6) if the total cost S > 0, it indicates that the representative object o j And (4) returning to the step (3), and reselecting the non-representative object to compare the total cost until the cost S is not changed any more, so that the k clusters with the minimum total cost are obtained.
Step 5
And (4) inputting the interest points with the road network information collected in the step (2) into the model in the step (4), carrying out similarity measurement on k clusters obtained by clustering results and collected representative interest points, and analyzing the interest points to which the resident trip areas belong so as to analyze the resident hot spot areas. And clustering to obtain the residential hot spot activity area with the road network characteristics. And comparing the clustering result with the collected interest points, and judging the hot spot area of the resident trip.
For the track tr to be measured a And tr b The Hausdorff distance is used to measure the trajectory similarity. H (tr) a ,tr b )＝max{h(tr a ,tr b ),h(tr b ,tr a ) Therein of
The Hausdorff distance is used to calculate the minimum value from each point in the two tracks to all points on the other track, and then the maximum value is found from the respective minimum value set. When the similarity is smaller than the similarity threshold value, the point of interest is considered to be similar to the space of the point of interest, and the point of interest is saved in the candidate set. And deleting the tracks with the distance greater than a certain threshold value in the candidate set to obtain the road network interest points closest to the tracks, namely the resident trip hot spot area.
The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure in any way whatsoever. After reading the description of the present invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (4)
1. A hot spot region mining method based on road network clustering is characterized by comprising the following steps:
step 1: collecting a taxi track data set, carrying out data preprocessing including data standardization and normalization, reserving effective fields, deleting redundant data, and obtaining preprocessed upper and lower taxi track points;
step 2: determining the latitude and longitude range of a city, and extracting interest points of the city including a shopping mall and a school on an open source website;
and 3, step 3: acquiring city road network information, and mapping track points into a road network;
and 4, step 4: selecting 80% of the upper and lower passenger track points of the vehicle preprocessed in the step 1 as a training set, and clustering out an area representing an upper and lower vehicle hot point by adopting an improved reverse learning-based center point partitioning clustering algorithm, wherein the improvement point is as follows: selecting an initial clustering center by using the density peak; the other 20 percent is used as a test set, and the clustering effect of a model built by taking 80 percent of upper and lower guest track points as a training set is tested;
and 5: inputting the interest points with road network information acquired in the step 3 into the model in the step 4, clustering to obtain a resident hot spot activity area with road network characteristics, comparing a clustering result with the acquired interest points, and judging a hot spot area of resident travel;
the step 4 specifically comprises the following steps: firstly, selecting 80% of processed upper and lower passenger track points of a vehicle as a training set, clustering an area representing an upper and lower hot spot by adopting an improved reverse learning-based central point partition clustering algorithm, and dividing the improved reverse learning-based central point partition clustering algorithm into three stages: initializing a first stage, constructing a decision diagram, and selecting density peak points in an upper right corner area far away from most samples as initial clustering centers, wherein the number of the density peak points is a cluster number k; constructing initial clustering centers, calculating the minimum distance between each point in the data set and each clustering center, distributing the rest sample points to the nearest initial clustering center to form initial division, and calculating the clustering error square sum; the third stage reversely learns and substitutes the algorithm for dividing and clustering around the central point, k clusters obtained by dividing and clustering around the central point and k reverse clusters obtained after reversely learning are arranged and combined to obtain k multiplied by k cluster combinations, and the cluster combination with the maximum outline coefficient is searched;
the step of dividing the clustering algorithm around the center point is as follows:
(1) arbitrarily selecting k elements from a given data set D, and marking the selected k elements as initial representative objects or seeds o j ；
(2) Calculating any non-representative object o in the data set D according to the Euclidean distance calculation mode i And k representative objects, and o i Allocating to the cluster represented by the representative object closest to the cluster;
(3) arbitrarily selecting a non-representative object o random ；
(4) Calculating the total cost S:
S＝dist(p,o random )-dist(p,o j )，
(5) if the total cost S < 0, indicating a non-representative object o random Is a better solution, element o random In place of the element o j Forming a new k representative object set, continuously returning to the step (2), and performing a new round of object allocation;
(6) if the total cost S > 0, it indicates that the representative object o j If the total cost is the optimal solution, turning to the step (3), reselecting the non-representative object to compare the total cost until the cost S is not changed any more, and obtaining k class clusters with the minimum total cost;
for the track tr to be measured a And tr b Track similarity, H (tr), is measured using the Hausdorff distance a ,tr b )＝max{h(tr a ,tr b ),h(tr b ,tr a ) Therein of
Calculating the distance from each point of the two tracks to the other track by using Hausdorff distanceThe minimum value with points is found out, and then the maximum value is found out from the respective minimum value set; when the similarity is smaller than the similarity threshold value, the spatial similarity with the interest point is considered, and the similarity is stored in the candidate set; deleting the tracks with the distance greater than a certain threshold value in the candidate set to obtain the road network interest points closest to the tracks, namely the resident trip hot spot areas;
let the data point of the sample be i and the local density be ρ i Local density ρ of data point i i The calculation method is as follows:
wherein,
d c for the truncation distance, δ is defined i Is the minimum of the distance of a data point i to any point greater than its local density: delta i ＝min j:ρj＞ρi (d ij ) For the point with the maximum local density, special treatment is needed, and the point is changed into the following value: delta i ＝max j (d ij )；
First phase initialization
(1) Initializing and solving a distance matrix D ═ D between data points ij I, j ═ 1.. times, n, and determining a truncation distance;
(2) according to the formula S ═ dist (p, o) random )-dist(p,o j ) Calculating local density by formula
Calculating a high density distance δ of a sample i ；
(3) And constructing a decision diagram with rho as a horizontal axis and delta as a vertical axis, selecting data points with higher local density rho and high density distance delta, taking density peak points of the upper right corner area far away from most samples as initial clustering centers, and taking the number of the density peak points as a clustering number k.
2. The road network clustering-based hot spot region mining method according to claim 1, wherein the step 1 specifically comprises: firstly, a taxi track data set of a certain month in a city is collected, track data of a week in the city data set is selected, data preprocessing is carried out, longitude and latitude data of track points of an upper taxi and a lower taxi are reserved, effective fields of the data of the time of the upper taxi and the lower taxi are reserved, and redundant data are deleted.
3. The road network clustering-based hotspot region mining method of claim 1, wherein the step 2 determines a city latitude and longitude range, extracts interest points of the city including shopping malls and schools from an open source website, and specifically comprises the following steps:
firstly, inputting the longitude and latitude range of a target city on an open source website opentreetmap, downloading a map of the whole city, deriving ways in OSM map data to represent the moving track of a user, representing paths by nodes, and selecting node labels as residual, school and shop to represent interest points.
4. The road network clustering-based hotspot region mining method according to claim 3, wherein the step 3 acquires road network information of a city, and maps track points into a road network, specifically:
obtaining electronic map data by adopting TAREEG network service items, extracting road network information of the city, projecting the obtained moving track on the obtained road network map through an ST-Matching model after extracting the road network data of the city, and obtaining the track points p of a driver passing through j continuous moments on each road section e i ,…,p j 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810179464.1A CN108427965B (en) | 2018-03-05 | 2018-03-05 | Hot spot area mining method based on road network clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810179464.1A CN108427965B (en) | 2018-03-05 | 2018-03-05 | Hot spot area mining method based on road network clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108427965A CN108427965A (en) | 2018-08-21 |
| CN108427965B true CN108427965B (en) | 2022-08-23 |
Family
ID=63157793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810179464.1A Active CN108427965B (en) | 2018-03-05 | 2018-03-05 | Hot spot area mining method based on road network clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108427965B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408562B (en) * | 2018-11-07 | 2021-11-26 | 广东工业大学 | Grouping recommendation method and device based on client characteristics |
| CN109739585B (en) * | 2018-12-29 | 2022-02-18 | 广西交通科学研究院有限公司 | Spark cluster parallelization calculation-based traffic congestion point discovery method |
| CN110135450B (en) * | 2019-03-26 | 2020-06-23 | 中电莱斯信息系统有限公司 | Hot spot path analysis method based on density clustering |
| CN110427444B (en) * | 2019-07-26 | 2022-05-24 | 北京百度网讯科技有限公司 | Navigation guide point mining method, device, equipment and storage medium |
| CN110399686B (en) * | 2019-07-30 | 2024-03-19 | 中国民航大学 | Parameter-independent aircraft flight trajectory clustering method based on contour coefficients |
| CN110609824B (en) * | 2019-09-09 | 2022-09-09 | 南京师范大学 | Hot spot area detection method based on dynamic space network model under urban road network environment |
| CN110726418B (en) * | 2019-10-10 | 2021-08-03 | 北京百度网讯科技有限公司 | Method, device and equipment for determining interest point region and storage medium |
| CN110849379B (en) * | 2019-10-23 | 2023-04-25 | 南通大学 | Entrance and exit traffic state symbol expression method for navigation map |
| CN110866559A (en) * | 2019-11-14 | 2020-03-06 | 上海中信信息发展股份有限公司 | Poultry behavior analysis method and device |
| CN111121803B (en) * | 2019-11-27 | 2021-12-03 | 北京中交兴路信息科技有限公司 | Method and device for acquiring common stop points of road |
| CN111275962B (en) * | 2019-12-30 | 2021-09-03 | 深圳市麦谷科技有限公司 | Vehicle track data aggregation effect prediction method and device |
| CN111708853B (en) * | 2020-05-25 | 2022-08-30 | 安徽师范大学 | Taxi hot spot region extraction method based on characteristic density peak clustering |
| CN114120018B (en) * | 2020-08-25 | 2023-07-11 | 四川大学 | Spatial vitality quantification method based on crowd clustering trajectory entropy |
| CN112163370A (en) * | 2020-09-18 | 2021-01-01 | 国网冀北电力有限公司承德供电公司 | Power distribution network line loss calculation method based on improved ASMDE algorithm |
| CN112070179B (en) * | 2020-09-22 | 2024-05-31 | 中国人民解放军国防科技大学 | Self-adaptive space-time track clustering method based on density peak value |
| CN113158817B (en) * | 2021-03-29 | 2023-07-18 | 南京信息工程大学 | Objective weather typing method based on rapid density peak clustering |
| CN113611115B (en) * | 2021-08-06 | 2022-06-21 | 安徽师范大学 | Vehicle track clustering method based on road network sensitive characteristics |
| CN113869465A (en) * | 2021-12-06 | 2021-12-31 | 深圳大学 | I-nice algorithm optimization method, device, equipment and computer readable storage medium |
| CN114485696B (en) * | 2021-12-23 | 2024-06-28 | 高德软件有限公司 | Arrival point acquisition method, electronic device and storage medium |
| CN114677048B (en) * | 2022-04-22 | 2024-01-16 | 北京阿帕科蓝科技有限公司 | Method for excavating demand area |
| CN114999151B (en) * | 2022-05-24 | 2023-01-24 | 电子科技大学 | Density-based urban traffic flow hierarchical analysis method and device in GPS track |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104167092A (en) * | 2014-07-30 | 2014-11-26 | 北京市交通信息中心 | Method and device for determining taxi pick-up and drop-off hot spot region center |
| CN105825672A (en) * | 2016-04-11 | 2016-08-03 | 中山大学 | City guidance area extraction method based on floating car data |
| CN107301254A (en) * | 2017-08-24 | 2017-10-27 | 电子科技大学 | A kind of road network hot spot region method for digging |
-
2018
- 2018-03-05 CN CN201810179464.1A patent/CN108427965B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104167092A (en) * | 2014-07-30 | 2014-11-26 | 北京市交通信息中心 | Method and device for determining taxi pick-up and drop-off hot spot region center |
| CN105825672A (en) * | 2016-04-11 | 2016-08-03 | 中山大学 | City guidance area extraction method based on floating car data |
| CN107301254A (en) * | 2017-08-24 | 2017-10-27 | 电子科技大学 | A kind of road network hot spot region method for digging |
Non-Patent Citations (4)
| Title |
|---|
| An improved clustering algorithm based on reverse learning in intelligent transportation;Guoqing Qiu et al;《AIP Conference Proceedings 1839》;20170508;全文 * |
| 基于出租车轨迹的居民出行热点路径和区域挖掘;冯琦森;《中国优秀硕士学位论文全文数据库信息科技辑》;20170315;摘要、第2-5节 * |
| 基于时间序列聚类方法分析北京出租车出行量的时空特征;程静等;《地球信息科学学报》;20161231;摘要、第1-5节 * |
| 密度峰值优化初始中心的K-medoids聚类算法;谢娟英等;《计算机科学与探索》;20161231;摘要、第1-5节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108427965A (en) | 2018-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108427965B (en) | Hot spot area mining method based on road network clustering | |
| CN112949413B (en) | City landscape element classification and locality measurement method based on street view picture | |
| Wu et al. | Mapping building carbon emissions within local climate zones in Shanghai | |
| CN108446470B (en) | Medical facility accessibility analysis method based on vehicle trajectory data and population distribution | |
| WO2016141753A1 (en) | Method of demarcating noise environment function areas based on road network and points of interest | |
| CN111651545A (en) | Urban marginal area extraction method based on multi-source data fusion | |
| CN111814596B (en) | Automatic city function partitioning method for fusing remote sensing image and taxi track | |
| CN113806419B (en) | Urban area function recognition model and recognition method based on space-time big data | |
| CN113034040A (en) | Typical species migration corridor site selection method, device and equipment | |
| CN111782741A (en) | Interest point mining method and device, electronic equipment and storage medium | |
| CN110413855B (en) | Region entrance and exit dynamic extraction method based on taxi boarding point | |
| CN108921173A (en) | A kind of deep learning method of combination OSM and remote sensing image extraction overpass | |
| CN114297532B (en) | High-definition city functional area identification method and system based on crowd movement track | |
| CN114708521A (en) | City functional area identification method and system based on street view image target relation perception network | |
| CN114973657A (en) | Urban traffic noise pollution analysis and evaluation method based on trajectory data | |
| CN116340563A (en) | Urban scene geographic position positioning method with pattern matching | |
| Li | Mapping urban land use by combining multi-source social sensing data and remote sensing images | |
| CN106021499B (en) | Construction land classification method and device based on volunteer geographic information | |
| WO2024069268A1 (en) | Intelligent platform for designing and drawing construction plans based on data mining and artificial intelligence | |
| CN111708859B (en) | Business circle boundary identification method based on spatial data | |
| Droj | GIS and remote sensing in environmental management | |
| CN117036733A (en) | Urban road scene characteristic line extraction method | |
| Costache et al. | The touristic accessibility in the Hunedoara county in terms of road network | |
| CN113610346B (en) | Village development potential evaluation and village classification method and device based on multi-source data | |
| Kulkarni et al. | Land use land cover change detection through GIS and unsupervised learning technique |
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 |