CN108170793B - Vehicle semantic track data-based dwell point analysis method and system - Google Patents
Vehicle semantic track data-based dwell point analysis method and system Download PDFInfo
- Publication number
- CN108170793B CN108170793B CN201711447961.7A CN201711447961A CN108170793B CN 108170793 B CN108170793 B CN 108170793B CN 201711447961 A CN201711447961 A CN 201711447961A CN 108170793 B CN108170793 B CN 108170793B
- Authority
- CN
- China
- Prior art keywords
- track data
- point set
- point
- semantic
- cluster
- 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
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a vehicle semantic track data-based dwell point analysis method and a system thereof, wherein the method comprises the following steps: acquiring track data of a vehicle within a preset time length; acquiring a suspicious stop point set according to the track data; performing cluster analysis on the suspicious stop point set to obtain at least one cluster point set; and analyzing each clustering point set based on the semantic, and acquiring a clustering center corresponding to a preset keyword. The method is based on the analysis processing of the track data in the vehicle preset historical time, firstly, a suspicious stop point set is obtained, then clustering analysis is carried out according to the suspicious stop point set, semantic-based clustering center locking is carried out in a clustering result according to actual business requirements, and all clustering centers are obtained to serve as final stop point results. The method can provide decision information for subsequent practical application and meet the requirements of real services.
Description
Technical Field
The invention relates to the field of vehicle track data analysis and processing, in particular to a vehicle semantic track data-based stop point analysis method and a vehicle semantic track data-based stop point analysis system.
Background
With the continuous development of mobile interconnection technology, in the fields of transportation and the like, the collection of track data constrained by a road network becomes possible. Knowledge acquisition and information analysis processing of moving objects are also becoming the focus of research. In the fields of mobile location-oriented service and intelligent traffic, by analyzing the characteristics of vehicle tracks and utilizing a clustering method to carry out data mining analysis, the motion rule and behavior pattern of a vehicle are found, hot spot analysis is carried out, and auxiliary decision information is provided for the fields of vehicle management, city planning, traffic management and the like.
The semantic track data refers to track point data which not only contains the longitude and latitude and the time of the current moving object, but also contains information such as the name (address code) of the landmark where the current point is located, the attribute of the moving object and the like. The track points comprise a starting point, a moving point, a stopping point and an end point, and the semantic track points form a semantic track.
The invention provides a dwell point analysis method and a system thereof based on semantic track data, which can accurately find vehicle dwell points from the track data of vehicles and provide decision information for practical application.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the system for analyzing the stop points based on the semantic track data can accurately acquire the stop points of the vehicle and further acquire the motion rule and the behavior mode of the vehicle.
In order to solve the technical problems, the invention adopts the technical scheme that:
a dwell point analysis method based on semantic track data comprises the following steps:
acquiring track data of a vehicle within a preset time length;
acquiring a suspicious stop point set according to the track data;
performing cluster analysis on the suspicious stop point set to obtain at least one cluster point set;
and analyzing each clustering point set based on the semantic, and acquiring a clustering center corresponding to a preset keyword.
The invention provides another technical scheme as follows:
a system for semantic track data based analysis of a stop point comprising one or more processors and a memory, said memory storing a computer program which, when configured to be executed by said one or more processors, is capable of carrying out the steps comprised in the above-mentioned method for semantic track data based analysis of a stop point.
The invention has the beneficial effects that: the method comprises the steps of analyzing and processing track data in a preset historical time of the vehicle, acquiring a suspicious stop point set, performing clustering analysis according to the suspicious stop point set, performing semantic-based clustering center locking in a clustering result according to actual business requirements, acquiring all clustering centers as final stop point results, further acquiring the motion rule and behavior mode of the vehicle, and providing decision information for subsequent actual application. The invention can well meet the requirements of practical services, such as accurately and efficiently searching vehicle stop points such as suspected illegal refueling stations of vehicles and suspected illegal passenger carrying and getting-off points of tourism passenger vehicles; or providing accurate delivery of services, such as advertisement push, centralized setting of leisure areas or shops, and the like.
Drawings
FIG. 1 is a schematic flow chart of a method for analyzing a stop point based on semantic track data according to the present invention;
FIG. 2 is a schematic flow chart according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of filtering drift trip point conditions in an embodiment of the invention.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
The most key concept of the invention is as follows: analyzing and processing the trajectory data in the preset historical time of the vehicle, firstly obtaining a suspicious stop point set, then performing clustering analysis, performing semantic-based clustering center locking in a clustering result according to actual service requirements, and obtaining all clustering centers as final stop point results.
Referring to fig. 1, the present invention provides a method for analyzing a stop point based on semantic track data, including:
acquiring track data of a vehicle within a preset time length;
acquiring a suspicious stop point set according to the track data;
performing cluster analysis on the suspicious stop point set to obtain at least one cluster point set;
and analyzing each clustering point set based on the semantic, and acquiring a clustering center corresponding to a preset keyword.
From the above description, the beneficial effects of the present invention are: with the high development of mobile internet, mobile location-oriented services are becoming more and more perfect. According to the invention, the vehicle motion rule and behavior pattern can be found by analyzing the vehicle track characteristics, and the stop point analysis is carried out, so that the accurate service delivery can be provided, and the system can be used in the aspects of special service scenes, such as advertisement pushing, illegal refueling site searching, centralized leisure area setting and the like; meanwhile, the system can meet the requirements of actual services, such as providing decision information for accurately and efficiently searching vehicle stop points such as suspected illegal refueling stations of vehicles and suspected illegal passenger carrying and getting off points of touring passenger vehicles.
Further, the semantic analysis based on each cluster point set obtains a cluster center corresponding to a preset keyword, specifically:
grouping member points in each clustering point set according to attribute information of the track data, wherein the attribute information is related to a preset keyword;
acquiring grouping weight according to the number of member points in the group or the distance between the member points in the group and the preset keyword;
the highest weighted packet is obtained.
According to the description, the final stop point result is accurately obtained by locking the corresponding semantic clustering center in the clustering result according to the actual service requirement.
Further, the method also comprises the following steps:
and filtering invalid track points including drift jump points, timestamp outliers and points coincident with the building in the track data.
According to the description, the invalid track points are filtered, so that the reality and reliability of the data are guaranteed, and the accuracy of the data analysis result is improved.
Further, the obtaining of the suspicious stopping point set according to the trajectory data specifically includes:
and traversing the track data, determining suspicious stop points according to the time interval between the track points, and acquiring a suspicious stop point set.
According to the description, all possible stopping points of the vehicle are efficiently and accurately found out through the track time interval based on the track data acquisition mode (the vehicle reports the longitude and latitude position information once according to different periodic intervals in the normal running state and the flameout state).
Further, the acquiring of the trajectory data of the vehicle within the preset time specifically includes:
and acquiring track data of the vehicle including longitude and latitude, time, vehicle information and relevant information of the position of the point in a preset time.
According to the description, the track data comprises the relevant information of each track point, and support is provided for subsequent semantic-based analysis.
Further, the cluster analysis is performed on the suspicious stop point set to obtain at least one cluster point set, which specifically includes:
for suspicious stopping point set SstopPerforming cluster analysis to obtain x cluster point sets S stored by arraysgroup＝{S0,S1,…,Sx-1}; wherein x is an integer of 1 or more.
Further, the semantic analysis based on each cluster point set obtains a cluster center corresponding to a preset keyword, specifically:
according to a track data attribute corresponding to a preset keyword, collecting the p-th clustering point Sp＝{Pm,Pm+1,…,PnMember points in the cluster are grouped, and a grouped cluster point set is obtained
Wherein, p is an integer from 1 to X in sequence, and the groupkThe number of the members of the kth group is, and k is the number of groups in a clustering point set;
acquiring grouping weight w according to the number of member points in the group or the distance between the member points in the group and the preset keywordkThen, acquiring longitude and latitude coordinates of the clustering center point:
wherein the weight wkSatisfies the following conditions:
l is a constant number, take
According to the description, efficient and accurate semantic-based clustering analysis can be directly performed through a preset algorithm.
The invention provides another technical scheme as follows:
a system for semantic track data based analysis of a stop point comprising one or more processors and a memory, said memory storing a computer program which, when configured to be executed by said one or more processors, is capable of carrying out the steps comprised in the above-mentioned method for semantic track data based analysis of a stop point.
From the above description, the beneficial effects of the present invention are: the computer program in the storage medium can be called and executed through the processor, analysis processing based on track data in vehicle preset historical time is achieved, a suspicious stop point set is obtained firstly, then clustering analysis is conducted, clustering center locking based on set semantics is conducted in a clustering result according to actual service requirements, and all clustering centers are obtained to serve as final stop point results.
Example one
Referring to fig. 2, the present embodiment provides a dwell point analysis method based on semantic track data, which can analyze and process track data of a certain period in a certain vehicle historical time, and obtain a final dwell point result of the vehicle corresponding to the period of time, so as to further obtain a motion rule and a behavior pattern of the vehicle, and provide decision information for subsequent practical applications. The actual application is based on the application of a stopping point such as searching a suspected illegal refueling station of a vehicle and a suspected illegal passenger carrying point of a tourism passenger vehicle, and the like, or the accurate delivery of service is provided, such as the pushing of advertisements, the centralized setting of leisure areas or shops and the like.
The method of the embodiment comprises the following steps:
s1: track data of a certain period in the historical time of a certain vehicle V0 is obtained.
The length of the certain period depends on the capacity of a processor for data analysis and processing and the precision requirement of the corresponding analysis result. Optionally, the certain period may be flexibly configured according to the actual requirement of the user.
The track data comprises longitude and latitude, time, vehicle information (type numbers and the like) and relevant information of the position of the track point. Preferably, the related information includes POI information (including information about a building name, a business facility name, a sight point name, an environmental hardware facility name, etc. near the location), and the number of times of passing through the track point. Therefore, the trajectory data includes attribute information of a place, time, and the like.
S2: and filtering the track data to remove invalid data.
Specifically, the collected trajectory data is filtered to include invalid trajectory points such as drift jump points, timestamp abnormal points and points coincident with the building.
For example: the filtering process for the drift trip point, i.e. the track trip point, is as follows:
as shown in fig. 3, a diagram of the condition of filtering drift trip points is shown, wherein the circle points are trace points. The trajectory set S ═ { P ═ P generated by the vehicle during runningm,…,P1,D,P2,…,PnAt point D, at a time between point P1And P2The track points. The vehicle is almost impossible to drive at tWithin a time from P1Travel beyond the distance that can be achieved at the current speed per hour
Travel after reaching point D
To point P2. Therefore, whether the point D is a drift-jump point can be determined by the method of fig. 1: if theta is less than or equal to thetaAnd P is2.t-P1.t<tIf yes, then the point D can be determined as the jump drift point and deleted. Wherein theta isTo determine the angle threshold of the drift trip point, θ is P1D and DP2The included angle of (a). After filtering processing, obtaining a filtered track set S from the track set Sfilter。
S3: and acquiring a suspicious stop point set according to the filtered track data.
The longitude and latitude position information is reported once at intervals of a plurality of times periodically when the vehicle is in a normal driving state and a flameout state. The reporting time interval is generally 30-40 s under the normal driving state, and the reporting time interval is longer under the flameout state. Therefore, the current state information of the vehicle can be judged according to the two sampling points before and after the time interval. With this a priori knowledge, all possible sets of stopping points can be found after filtering the vehicle trajectory.
For example: track set S after traversing and filtering abnormal pointsfilterFinding out data with time interval greater than that of other points to obtain track point set Sstop。
S4: and performing DBSCAN clustering analysis on the suspicious stop point set to obtain a clustering point set.
Cluster analysis refers to an analytical process that groups a collection of physical or abstract objects into classes composed of similar objects. In this embodiment, the suspicious stops filtered out are clustered into a plurality of clusters according to geographical proximity.
For example: for suspicious stopping point set SstopPerforming DBSCAN clustering analysis to obtain x clustering results, and storing the x clustering results as Sgroup＝{S0,S1,…,Sx-1And the ∈ neighborhood is set as the average distance of the vehicle moving in unit time obtained by the overall track, the ∈ neighborhood is a parameter for setting the clustering radius in the DBSCAN and can be set as the distance of the moving object moving in unit time, and x is an integer greater than or equal to 1.
S5: and analyzing each clustering point set based on the semantic, acquiring a clustering center corresponding to a preset keyword, and outputting the clustering center as a result.
Specifically, the preset keyword is related to attribute information of the trajectory data, such as "gas station" corresponding to the location attribute. According to the set keywords, the clustering center determined by the semantic-based method is the result closest to the relationship of the set keywords.
For example: firstly, grouping each clustering point set: for the p-th clustering point set Sp＝{Pm,Pm+1,…,PnMember points in the page are grouped according to certain attribute, the selection of the attribute information is determined by a preset keyword, and the attribute information and the keyword have corresponding relations, such as a subordinate relation, a similar relation and the like. If the keyword is set as 'gas station', the 'gas station' corresponds to a place, and the member track points all contain the names of the places. Thus, it is possible to determine that the attribute information on which the grouping is based is "place"; the same member points are grouped by grouping.
The weights of the individual packets are calculated: the weight of the group can be in direct proportion to the number of members in the group, or the distance between each cluster member point and the refueling station point is inquired according to a hotspot to be analyzed, namely a preset keyword 'refueling station point', and the weight of the point is in inverse proportion to the distance, so that the weight of the group is obtained. The grouped set of cluster points can be represented as:
wherein groupkIs the kth group membership;
the latitude and longitude coordinates of the cluster center point can be expressed as:
wherein the weight wkSatisfies the following conditions:
l is a constant number, take
It should be noted that the weight calculation method of the present embodiment is different from the conventional average sum, which is to set wk＝1。
Example two
In a first embodiment, a dwell point analyzing system based on semantic track data is provided, which includes one or more processors and a memory, where the memory stores a computer program, and when the computer program is configured to be executed by one or more processors in the system, all the steps included in the dwell point analyzing method based on semantic track data according to the foregoing embodiment can be implemented. The specific steps are not repeated here, and for a detailed description, refer to embodiment one.
EXAMPLE III
This embodiment provides a specific application scenario corresponding to the first embodiment:
in the actual business requirements, track data of various vehicles such as taxies, school buses, tourism passenger vehicles, muck vehicles and the like including travel longitude and latitude information, time, vehicle information and POI (point of interest) of the positions of the vehicles are obtained. Finding an illegal fueling site therein is our focus, and therefore, the keyword is set to "fueling site".
In the clustering result obtained according to the first embodiment, the clustering is performed according to the data attribute 'location' corresponding to the keyword, and then the clustering weight of the data attribute 'location' containing the keyword 'gas station' in the specified location is larger; if all members of a certain cluster do not contain the character string, the most similar places in the cluster can be divided into a group, the weight is in direct proportion to the number of the group members, and finally, the stop points are clustered.
For example, an illegal gas station is located at the number of ' A area B way C ', the addresses of the stop points are scattered and distributed in the number of ' A area B way D ', the number of ' A area B way E ' and the like, but the ' A area B way ' does not contain the key words of the gas station ', at the moment, the ' A area B way ' can be used as the grouping basis, and the possibility and the accuracy of gathering the ' A area B way C number ' are higher than those of the traditional method that the output is more accurate after the longitude and latitude of all members of the class cluster are averaged.
In conclusion, the dwell point analysis method based on the semantic track data provided by the invention can be used for accurately and efficiently analyzing and obtaining the vehicle dwell point from the track data of the vehicle. Decision information can be provided for practical application; and the motion rule and the behavior mode of the vehicle can be found according to the method, so that the accurate service delivery is realized.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (7)
1. A dwell point analysis method based on semantic track data is characterized by comprising the following steps:
acquiring track data of a vehicle within a preset time length;
acquiring a suspicious stop point set according to the track data;
performing cluster analysis on the suspicious stop point set to obtain at least one cluster point set;
analyzing each clustering point set based on semantics to obtain a clustering center corresponding to a preset keyword;
the method for analyzing each cluster point set based on the semantic analysis to obtain the cluster center corresponding to a preset keyword specifically comprises the following steps:
according to a track data attribute corresponding to a preset keyword, collecting the p-th clustering point Sp＝{Pm，Pm+1，...，PnMember points in the cluster are grouped, and a grouped cluster point set is obtained
Wherein, p is an integer from 1 to X in sequence, and the groupkThe number of the members of the kth group is, and k is the number of groups in a clustering point set;
acquiring grouping weight w according to the number of member points in the group or the distance between the member points in the group and the preset keywordkThen, acquiring longitude and latitude coordinates of the clustering center point:
wherein, PWLat is PWLatitude coordinate of (P)WLon is PWBy longitude coordinate, weight wkSatisfies the following conditions:
l is a constant number, take
2. The dwell point analysis method based on semantic track data as claimed in claim 1, wherein the semantic analysis based on each cluster point set obtains a cluster center corresponding to a preset keyword, specifically:
grouping member points in each clustering point set according to attribute information of the track data, wherein the attribute information is related to a preset keyword;
acquiring grouping weight according to the number of member points in the group or the distance between the member points in the group and the preset keyword;
the highest weighted packet is obtained.
3. The method for analyzing a dwell point based on semantic track data as claimed in claim 1, further comprising:
and filtering invalid track points including drift jump points, timestamp outliers and points coincident with the building in the track data.
4. The method for analyzing a dwell point based on semantic track data as claimed in claim 1, wherein the obtaining of the suspicious dwell point set according to the track data specifically comprises:
and traversing the track data, determining suspicious stop points according to the time interval between the track points, and acquiring a suspicious stop point set.
5. The dwell point analysis method based on semantic track data according to claim 1, wherein the obtaining of the track data of the vehicle within a preset time period specifically comprises:
and acquiring track data of the vehicle including longitude and latitude, time, vehicle information and relevant information of the position of the point in a preset time.
6. The dwell point analysis method based on semantic track data according to claim 1, wherein the suspicious dwell point set is subjected to cluster analysis to obtain at least one cluster point set, specifically:
for suspicious stopping point set SstopPerforming cluster analysis to obtain x cluster point sets S stored by arraysgroup＝{S0，S1，...，Sx-1}; wherein x is an integer of 1 or more.
7. A semantic track data based stopover point analysis system comprising one or more processors and a memory, said memory storing a computer program, wherein said program, when configured to be executed by said one or more processors, is capable of carrying out the steps comprised in the semantic track data based stopover point analysis method according to any one of the preceding claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711447961.7A CN108170793B (en) | 2017-12-27 | 2017-12-27 | Vehicle semantic track data-based dwell point analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711447961.7A CN108170793B (en) | 2017-12-27 | 2017-12-27 | Vehicle semantic track data-based dwell point analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108170793A CN108170793A (en) | 2018-06-15 |
| CN108170793B true CN108170793B (en) | 2020-10-09 |
Family
ID=62518334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711447961.7A Active CN108170793B (en) | 2017-12-27 | 2017-12-27 | Vehicle semantic track data-based dwell point analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108170793B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109541654A (en) * | 2018-11-19 | 2019-03-29 | 北京金州世纪信息技术有限公司 | A kind of calculation method and device of vehicle parking point |
| CN111507364A (en) * | 2019-01-31 | 2020-08-07 | 杭州隼目信息科技有限公司 | Suspicious vehicle detection method |
| CN111666359B (en) * | 2019-03-07 | 2023-06-20 | 阿里巴巴集团控股有限公司 | POI candidate arrival point mining method, device and equipment |
| CN110489672A (en) * | 2019-08-21 | 2019-11-22 | 新疆丝路大道信息科技有限责任公司 | Automobile leasing platform user position data processing method, system and electronic equipment |
| CN110689804B (en) * | 2019-10-10 | 2022-05-17 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN111190891B (en) * | 2019-12-27 | 2023-07-25 | 武汉长江通信产业集团股份有限公司 | Multi-semantic track data segment storage method |
| CN111311784A (en) * | 2020-03-04 | 2020-06-19 | 深圳市物语智联科技有限公司 | User portrait determination method, device, computer equipment and storage medium |
| CN111881370A (en) * | 2020-05-21 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Method and system for describing contour of interest area |
| CN111680102B (en) * | 2020-05-21 | 2023-12-26 | 平安国际智慧城市科技股份有限公司 | Positioning data processing method based on artificial intelligence and related equipment |
| CN112035452B (en) * | 2020-08-26 | 2022-09-06 | 重庆长安汽车股份有限公司 | Internet vehicle user tour analysis method based on big data |
| CN112598767B (en) * | 2020-12-29 | 2024-05-10 | 厦门市美亚柏科信息股份有限公司 | Track behavior analysis method based on space-time big data, terminal equipment and storage medium |
| CN113191610A (en) * | 2021-04-22 | 2021-07-30 | 上海仙豆智能机器人有限公司 | Vehicle monitoring method, device, equipment and medium based on suspicious keywords |
| CN113191611A (en) * | 2021-04-22 | 2021-07-30 | 上海仙豆智能机器人有限公司 | Vehicle aggregation monitoring method, device, equipment and medium |
| CN113159594B (en) * | 2021-04-28 | 2024-03-08 | 中国工商银行股份有限公司 | Dispatching method and device for liquefied natural gas transport vehicle |
| CN113821735B (en) * | 2021-08-18 | 2024-02-02 | 北京中交兴路信息科技有限公司 | Method, device, equipment and storage medium for identifying illegal fueling station |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN104636443A (en) * | 2015-01-12 | 2015-05-20 | 北京中交兴路车联网科技有限公司 | Basic data model based on truck trajectory excavation POI potential information |
| JP2017033405A (en) * | 2015-08-04 | 2017-02-09 | 日本電信電話株式会社 | Residence site extraction device, method, and program |
-
2017
- 2017-12-27 CN CN201711447961.7A patent/CN108170793B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN104636443A (en) * | 2015-01-12 | 2015-05-20 | 北京中交兴路车联网科技有限公司 | Basic data model based on truck trajectory excavation POI potential information |
| JP2017033405A (en) * | 2015-08-04 | 2017-02-09 | 日本電信電話株式会社 | Residence site extraction device, method, and program |
Non-Patent Citations (2)
| Title |
|---|
| 《一种基于CFSFDP改进算法的重要地点识别方法研究》;马春来 等;《计算机应用研究》;20170131(第1期);全文 * |
| 《基于用户移动数据的可视化用户行为分析》;陈鹏;《中国优秀硕士学位论文全文数据库信息科技辑》;20170215(第02期);摘要，正文第16-18、21-24、37-40页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108170793A (en) | 2018-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108170793B (en) | Vehicle semantic track data-based dwell point analysis method and system | |
| AU2017399729B2 (en) | Trajectory analysis with mode of transport analysis | |
| Zhao et al. | A trajectory clustering approach based on decision graph and data field for detecting hotspots | |
| US11295519B2 (en) | Method for determining polygons that overlap with a candidate polygon or point | |
| US20200019815A1 (en) | Clustering for k-anonymity in location trajectory data | |
| EP3410348A1 (en) | Method and apparatus for building a parking occupancy model | |
| Xu et al. | DESTPRE: a data-driven approach to destination prediction for taxi rides | |
| US20200019585A1 (en) | Triangulation for k-anonymity in location trajectory data | |
| US11418915B2 (en) | Trajectory analysis with mode of transportation analysis | |
| US10945096B2 (en) | Mobility gene for visit data | |
| EP3992581A1 (en) | Method, apparatus, and system for estimating continuous population density change in urban areas | |
| US11317247B1 (en) | Method, apparatus, and system for data-driven evaluation of heuristics for trajectory cropping | |
| CN113899355A (en) | Map updating method and device, cloud server and shared riding equipment | |
| Garg et al. | Mining bus stops from raw GPS data of bus trajectories | |
| Stenneth et al. | Monitoring and mining GPS traces in transit space | |
| WO2018151672A1 (en) | Trajectory analysis through fusion of multiple data sources | |
| Yin et al. | A multi-task learning framework for road attribute updating via joint analysis of map data and GPS traces | |
| Li et al. | An automatic extraction method of coach operation information from historical trajectory data | |
| CN114007186B (en) | Positioning method and related product | |
| Zhuang et al. | Predicting the next turn at road junction from big traffic data | |
| Lan et al. | Inferring alighting bus stops from smart card data combined with cellular signaling data | |
| WO2018151677A1 (en) | Real time trajectory identification from communications network | |
| Phithakkitnukoon | Urban Informatics Using Mobile Network Data: Travel Behavior Research Perspectives | |
| Zhang et al. | Reconstruction of human movement from large-scale mobile phone data | |
| Sharker et al. | On Reliability of Routes Computed Based on Crowdsourced Points of Interest |
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 |