CN106897420B - Mobile phone signaling data-based user travel resident behavior identification method - Google Patents

Mobile phone signaling data-based user travel resident behavior identification method Download PDF

Info

Publication number
CN106897420B
CN106897420B CN201710101688.6A CN201710101688A CN106897420B CN 106897420 B CN106897420 B CN 106897420B CN 201710101688 A CN201710101688 A CN 201710101688A CN 106897420 B CN106897420 B CN 106897420B
Authority
CN
China
Prior art keywords
residence
signaling data
clustering
points
time
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
Application number
CN201710101688.6A
Other languages
Chinese (zh)
Other versions
CN106897420A (en
Inventor
刘志成
余锦斌
韦煜
王宇然
陆建
王桥
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.)
Southeast University
Original Assignee
Southeast 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 Southeast University filed Critical Southeast University
Priority to CN201710101688.6A priority Critical patent/CN106897420B/en
Publication of CN106897420A publication Critical patent/CN106897420A/en
Application granted granted Critical
Publication of CN106897420B publication Critical patent/CN106897420B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • 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
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a method for identifying a user travel resident behavior based on mobile phone signaling data, which comprises the following steps: (1) cleaning, converting and dividing the mobile phone signaling data; (2) setting a plurality of clustering numbers by using an unsupervised classification method, clustering space points in the signaling data unit, and evaluating each clustering result through a clustering score index, wherein the highest score is the best cluster; (3) obtaining information sets of all candidate residence points and relevant time in the signaling data unit according to the optimal clustering; (4) and calculating and screening the residence time of the candidate residence points according to the time threshold and the information set of each candidate residence point, and outputting the spatial position, the arrival time and the residence time of each residence point of each user every day. The method is simple and convenient to use, has good expandability, avoids interference caused by artificial subjective judgment, and avoids the compromise phenomenon of identification accuracy rate caused by the characteristic of uneven distribution of urban and suburban base stations.

Description

Mobile phone signaling data-based user travel resident behavior identification method
Technical Field
The invention relates to the technical field of big data, in particular to a user travel resident behavior identification method based on mobile phone signaling data.
Background
The understanding of the travel condition of urban residents is an important consideration link for urban planners and traffic planners in urban layout and road network planning, and the important consideration link comprises residence points of the urban residents in travel, arrival time and residence time corresponding to the residence points. The traditional method for acquiring the citizen's travel condition is mainly a manual method for issuing questionnaires. The traditional method has the main defects of high investigation cost, small obtained sample amount, high accuracy rate influenced by human factors and low information updating frequency, so that a planner cannot accurately and timely know the travel demands of urban residents.
With the popularization of informatization and big data technology, technical means such as acquiring the travel conditions of urban residents through mobile phone signaling data and the like begin to appear. Compared with the traditional manual survey data, the mobile phone signaling data has the advantages of low acquisition cost, complete samples, capability of reflecting the travel demand change of citizens in time and the like. However, the existing method for extracting the user travel condition through the mobile phone signaling data has the following disadvantages: (1) due to the non-uniform distribution characteristic of the mobile phone communication base station in the geographic space, the existing method needs to set a spatial threshold value in a mode of artificial repeated adjustment and observation experiment so as to identify the residence point of a user; (2) considering that the distribution densities of the mobile phone communication base stations in urban areas and suburban areas are different, setting a uniform spatial threshold causes a compromise phenomenon in the identification accuracy of the residence points of suburban trip and urban trip. The defects make the existing method difficult to be directly used by users such as planners, increase the learning difficulty and unnecessary workload for the users to analyze the traveling conditions of citizens through mobile phone signaling data, and make the residence point identification accuracy of the traveling in the urban and suburban areas not compatible.
Disclosure of Invention
The invention aims to solve the technical problem of providing a user travel resident behavior identification method based on mobile phone signaling data, which can realize distributed deployment on a large-scale computing cluster and efficiently process mass mobile phone signaling data.
In order to solve the technical problem, the invention provides a method for identifying a user travel resident behavior based on mobile phone signaling data, which comprises the following steps:
(1) cleaning, converting and dividing the mobile phone signaling data;
(2) setting a plurality of clustering numbers by using an unsupervised classification method, clustering space points in the signaling data unit, and evaluating each clustering result through a clustering score index, wherein the highest score is the best cluster;
(3) obtaining information sets of all candidate residence points and relevant time in the signaling data unit according to the optimal clustering;
(4) and calculating and screening the residence time of the candidate residence points according to the time threshold and the information set of each candidate residence point, and outputting the spatial position, the arrival time and the residence time of each residence point of each user every day.
Preferably, in the step (1), the washing step specifically comprises: after mobile phone signaling data in a certain period of a city are acquired, record items with incomplete time and space information in the mobile phone signaling data are removed; the conversion steps are specifically as follows: after the cleaned signaling data is obtained, replacing the base station number in the signaling record with the corresponding base station space coordinate, and if the base station space coordinate is a longitude and latitude coordinate, converting the longitude and latitude coordinate into a projection coordinate; the segmentation steps are specifically as follows: after the cleaned and converted signaling data are obtained, the signaling data are divided according to the day, then the data are divided according to the users, so that all signaling record items of all users in each day are obtained, all signaling data of one user in each day are taken as a signaling data unit and are marked as a DataUnit, and each unit is calculated according to the following steps.
Preferably, in the step (2), an unsupervised clustering method is utilized, the clustering numbers are set to be 2,3,4, … … and 30 in sequence, the spatial points in the DataUnit are clustered, each clustering result is evaluated through a clustering score index, and the highest score is the best clustering; for one DataUnit, taking the space coordinate of the base station in each signaling record in the DataUnit as a space point, clustering all the space points in the signaling data unit by using a k-means unsupervised clustering method, and calculating different points if the space points with the same coordinate exist; in the clustering process, setting k to be 2,3, … and 30 in sequence, and for each k value, using a Dunn index to score the clustering result, wherein the highest k value is the best k value, and the corresponding clustering result is the best clustering result.
Preferably, the step (3) specifically comprises the following steps:
(31) generating an information set InfoSet of the candidate residence point: after the optimal clustering result of the space points in the DataUnit is obtained through the step (2), arranging the record items in the DataUnit according to the time sequence, and taking the class where the space point of each record item is as the class of the record item; merging the record entries which are adjacent and homogeneous in time sequence into a set as an information set InfoSet of a candidate residence point, namely:
Figure BDA0001231900090000021
wherein L isiRepresenting the spatial position, t, of the ith information pointiThe recording time of the ith information point is represented, and the information point I represents the number of the information points in the resident point information set;
(32) calculating candidate stay point related parameters: for the information set InfoSet of a candidate dwell point, the average position of the spatial points in the set is calculated as the spatial position of the candidate dwell point, that is:
Figure BDA0001231900090000022
taking the earliest time of record items in the set as the arrival time t of the candidate residence pointarrTaking the latest time of the record entry in the set as the leaving time t of the candidate residence pointdepUsing the departure time minus the arrival time of the candidate residence point as the residence time t of the candidate residence pointdurNamely:
tarr＝t1
tdep＝t|InfoSet|
tdur＝tdep-tarr。
preferably, the step (4) specifically comprises the following steps:
(41) screening candidate residence points according to a time threshold: for all candidate residence points in one DataUnit obtained in the stage 3, removing the candidate residence points with residence time less than 15 minutes, and taking the remaining candidate residence points as the residence points output by the DataUnit;
(42) outputting a recognition result: the spatial positions of all the dwell points of the DataUnit and their corresponding arrival times and dwell durations are combined, i.e., (L)InfoSet,tarr,tdur) And arranging according to the sequence of arrival time, namely obtaining the final recognition result of the travel resident behavior of the corresponding user in a certain day, namely:
Figure BDA0001231900090000031
wherein, | Result(user,day)And | represents the number of actual travel residence points recognized by the corresponding user in a corresponding day.
The invention has the beneficial effects that: the method is simple and convenient to use, the user does not need to repeatedly adjust parameters, each user travel resident behavior in each day can be obtained after mobile phone signaling data are obtained, a planner does not need to determine a spatial threshold value through repeated adjustment and observation experiments, and interference caused by artificial subjective judgment is avoided; the method can adapt to the characteristic of uneven distribution of base stations, and spatial clustering is carried out through the self characteristic of a user signaling track, so that the compromise phenomenon of identification accuracy rate caused by the characteristic of uneven distribution of base stations in urban areas and suburban areas is avoided; the method has good expandability, can realize distributed deployment on a large-scale computing cluster, and efficiently processes mass mobile phone signaling data.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of the principle of the present invention.
FIG. 3 is a schematic diagram of an embodiment of the present invention.
Detailed Description
As shown in fig. 1, a method for identifying a user travel resident behavior based on mobile phone signaling data includes the following steps:
(1) and cleaning, converting and dividing the mobile phone signaling data.
Cleaning: after mobile phone signaling data in a certain period of the city are acquired, record entries with incomplete time and space information are removed.
Conversion: and after the cleaned signaling data is obtained, replacing the base station number in the signaling record with the corresponding base station space coordinate. If the base station space coordinate is a longitude and latitude coordinate, the longitude and latitude coordinate is also required to be converted into a projection coordinate. The patent does not have any dependency on a projection coordinate system, and can select an international general projection method, such as: mercator projection, Gauss-Kruger projection, Lambert projection, and the like.
And (3) dividing: after the cleaned and converted signaling data are obtained, the signaling data are divided according to the day, and then the data are divided according to the users, so that all signaling record items of all the users in each day are obtained. All signaling data of a user in a day are taken as a signaling data unit and are marked as a DataUnit, and calculation is carried out on each unit according to the following steps.
(2) And (3) clustering the spatial points in the DataUnit by using an unsupervised clustering method and setting the clustering numbers to be 2,3,4, … … and 30 in sequence, and evaluating each clustering result through a clustering score index, wherein the highest score is the best cluster.
For one DataUnit, the spatial coordinates of the base station in each signaling record in the DataUnit are taken as a spatial point, and all the spatial points in the signaling data unit are clustered by using a k-means unsupervised clustering method. If there are spatial points with the same coordinates, all the spatial points are calculated as different points. In the clustering process, k is set to 2,3, … and 30 in sequence, and for each k value, the clustering result is scored by using the Dunn index. The highest k value is the best k value, and the corresponding clustering result is the best clustering result. As shown in fig. 2, the ordinate in the figure is used to briefly represent the spatial coordinates, and the spatial axis shows the best clustering result of all spatial points in one DataUnit, i.e. 3 categories displayed on the ordinate axis.
(3) And obtaining information sets of all candidate residence points and relevant time in the DataUnit according to the optimal clustering.
(31) Generating an information set InfoSet of the candidate residence point: after the optimal clustering result of the space points in the DataUnit is obtained through the stage 2, the record items in the DataUnit are arranged according to the time sequence, and the class where the space point of each record item is located is used as the class of the record item. Merging the record entries which are adjacent and homogeneous in time sequence into a set as an information set InfoSet of a candidate residence point, namely:
Figure BDA0001231900090000041
wherein L isiRepresenting the spatial position, t, of the ith information pointiThe recording time of the ith information point is shown, and | InfoSet | shows the number of information points in the dwell point information set.
As shown in fig. 2, the abscissa of the graph represents the time coordinate, and infosets of all candidate residing points in one DataUnit are circled by the dashed line in the graph.
(32) Calculating candidate stay point related parameters: for the information set InfoSet of a candidate dwell point, the average position of the spatial points in the set is calculated as the spatial position of the candidate dwell point, that is:
Figure BDA0001231900090000051
taking the earliest time of record items in the set as the arrival time t of the candidate residence pointarrTaking the latest time of the record entry in the set as the leaving time t of the candidate residence pointdepUsing the departure time minus the arrival time of the candidate residence point as the residence time t of the candidate residence pointdur. Namely:
tarr＝t1
tdep＝t|InfoSet|
tdur＝tdep-tarr
as shown in FIG. 2, the dwell time t of each candidate dwell point is marked on the abscissadur。
(4) According to the time threshold and the information set of each candidate residence point, waitingSelecting residence time of residence point to calculate and filter, and outputting space position L of each residence point every day for each userInfoSetTime of arrival tarrAnd a dwell time tdur。
(41) Screening candidate residence points according to a time threshold: for all candidate residence points in one DataUnit obtained through stage 3, the candidate residence points with residence time less than 15 minutes are removed, and the remaining candidate residence points are the residence points output by the DataUnit. As shown in FIG. 2, candidate stay point 2 is removed since the stay duration is less than 15 minutes, and the stay durations of the remaining candidate stay points are retained and taken as stay points for longer than 15 minutes.
(42) Outputting a recognition result: the spatial positions of all the dwell points of the DataUnit and their corresponding arrival times and dwell durations are combined, i.e., (L)InfoSet,tarr,tdur) And arranging according to the sequence of arrival time, namely obtaining the final recognition result of the travel resident behavior of the corresponding user in a certain day, namely:
Figure BDA0001231900090000052
wherein, | Result(user,day)And | represents the number of actual travel residence points recognized by the corresponding user in a corresponding day.
Fig. 3 shows an example of the resident behavior identified by the DataUnit through the user travel resident behavior identification method of the present invention. The five-pointed star represents the identified user dwell point location, and the identified arrival time and dwell time are shown in the information box next to each dwell point.
While the invention has been shown and described with respect to the preferred embodiments, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the scope of the invention as defined in the following claims.

Claims (4)

1. A method for identifying a user travel resident behavior based on mobile phone signaling data is characterized by comprising the following steps:
(1) cleaning, converting and dividing the mobile phone signaling data;
(2) setting a plurality of clustering numbers by using an unsupervised classification method, clustering space points in the signaling data unit, and evaluating each clustering result through a clustering score index, wherein the highest score is the best cluster; clustering spatial points in the DataUnit by using an unsupervised clustering method and setting the clustering number to be 2,3,4, … … and 30 in sequence, and evaluating each clustering result through a clustering score index, wherein the highest score is the best cluster; for one DataUnit, taking the space coordinate of the base station in each signaling record in the DataUnit as a space point, clustering all the space points in the signaling data unit by using a k-means unsupervised clustering method, and calculating different points if the space points with the same coordinate exist; in the clustering process, setting k to be 2,3, … and 30 in sequence, and for each k value, using a Dunn index to score a clustering result, wherein the highest k value is the best k value, and the corresponding clustering result is the best clustering result;
(3) obtaining information sets of all candidate residence points and relevant time in the signaling data unit according to the optimal clustering;
(4) and calculating and screening the residence time of the candidate residence points according to the time threshold and the information set of each candidate residence point, and outputting the spatial position, the arrival time and the residence time of each residence point of each user every day.
2. The method for identifying a user travel resident behavior based on mobile phone signaling data as claimed in claim 1, wherein in the step (1), the step of cleaning specifically comprises: after mobile phone signaling data in a certain period of a city are acquired, record items with incomplete time and space information in the mobile phone signaling data are removed; the conversion steps are specifically as follows: after the cleaned signaling data is obtained, replacing the base station number in the signaling record with the corresponding base station space coordinate, and if the base station space coordinate is a longitude and latitude coordinate, converting the longitude and latitude coordinate into a projection coordinate; the segmentation steps are specifically as follows: after the cleaned and converted signaling data are obtained, the signaling data are divided according to the day, then the data are divided according to the users, so that all signaling record items of all users in each day are obtained, all signaling data of one user in each day are taken as a signaling data unit and are marked as a DataUnit, and each unit is calculated according to the following steps.
3. The method for identifying a user travel residence behavior based on mobile phone signaling data as claimed in claim 1, wherein step (3) specifically comprises the following steps:
(31) generating an information set InfoSet of the candidate residence point: after the optimal clustering result of the space points in the DataUnit is obtained through the step (2), arranging the record items in the DataUnit according to the time sequence, and taking the class where the space point of each record item is as the class of the record item; merging the record entries which are adjacent and homogeneous in time sequence into a set as an information set InfoSet of a candidate residence point, namely:
Figure FDA0002415486070000021
wherein L isiRepresenting the spatial position, t, of the ith information pointiThe recording time of the ith information point is represented, and the information point I represents the number of the information points in the resident point information set;
(32) calculating candidate stay point related parameters: for the information set InfoSet of a candidate dwell point, the average position of the spatial points in the set is calculated as the spatial position of the candidate dwell point, that is:
Figure FDA0002415486070000022
taking the earliest time of record items in the set as the arrival time t of the candidate residence pointarrTaking the latest time of the record entry in the set as the leaving time t of the candidate residence pointdepUsing the departure time minus the arrival time of the candidate residence point as the residence time t of the candidate residence pointdurNamely:
tarr＝t1
tdep＝t|InfoSet|
tdur＝tdep-tarr。
4. the method for identifying a user travel residence behavior based on mobile phone signaling data as claimed in claim 3, wherein the step (4) specifically comprises the following steps:
(41) screening candidate residence points according to a time threshold: for all candidate residence points in one DataUnit obtained in the stage 3, removing the candidate residence points with residence time less than 15 minutes, and taking the remaining candidate residence points as the residence points output by the DataUnit;
(42) outputting a recognition result: the spatial positions of all the dwell points of the DataUnit and their corresponding arrival times and dwell durations are combined, i.e., (L)InfoSet,tarr,tdur) And arranging according to the sequence of arrival time, namely obtaining the final recognition result of the travel resident behavior of the corresponding user in a certain day, namely:
Figure FDA0002415486070000023
wherein, | Result(user,day)And | represents the number of actual travel residence points recognized by the corresponding user in a corresponding day.
CN201710101688.6A 2017-02-24 2017-02-24 Mobile phone signaling data-based user travel resident behavior identification method Active CN106897420B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710101688.6A CN106897420B (en) 2017-02-24 2017-02-24 Mobile phone signaling data-based user travel resident behavior identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710101688.6A CN106897420B (en) 2017-02-24 2017-02-24 Mobile phone signaling data-based user travel resident behavior identification method

Publications (2)

Publication Number Publication Date
CN106897420A CN106897420A (en) 2017-06-27
CN106897420B true CN106897420B (en) 2020-10-02

Family

ID=59185106

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710101688.6A Active CN106897420B (en) 2017-02-24 2017-02-24 Mobile phone signaling data-based user travel resident behavior identification method

Country Status (1)

Country Link
CN (1) CN106897420B (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657572A (en) * 2017-09-13 2018-02-02 北京城建设计发展集团股份有限公司 Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency
CN107729418B (en) * 2017-09-27 2020-11-17 海南中智信信息技术有限公司 SPARK and DBSCAN-based distributed visitor identification type method
CN109121094B (en) * 2018-07-27 2021-04-06 北京交通发展研究院 Pseudo code signaling data preprocessing and trip chain identification method
CN109284773A (en) * 2018-08-15 2019-01-29 西南交通大学 Traffic trip endpoint recognition methods based on multilayer Agglomerative Hierarchical Clustering algorithm
CN109561386A (en) * 2018-11-23 2019-04-02 东南大学 A kind of Urban Residential Trip activity pattern acquisition methods based on multi-source location data
CN110324787B (en) * 2019-06-06 2020-10-02 东南大学 Method for acquiring occupational sites of mobile phone signaling data
CN110351664B (en) * 2019-07-12 2021-07-20 重庆市交通规划研究院 User activity space identification method based on mobile phone signaling
CN111090642B (en) * 2019-12-02 2023-07-14 杭州诚智天扬科技有限公司 Method for cleaning signaling data of mobile phone
CN111182445B (en) * 2019-12-27 2021-10-19 南京中新赛克科技有限责任公司 Method and system for analyzing aggregated groups based on mobile phone signaling data
CN111182530B (en) * 2019-12-27 2022-05-13 南京中新赛克科技有限责任公司 Method and system for analyzing target new mobile phone number based on mobile phone signaling data
CN112070295B (en) * 2020-09-02 2021-06-18 智慧足迹数据科技有限公司 Travel statistical method and device, computer equipment and readable storage medium
CN112434225B (en) * 2020-12-13 2022-06-21 天津市赛英工程建设咨询管理有限公司 Mobile phone signaling resident point extraction method based on process clustering
CN112541551B (en) * 2020-12-16 2023-11-24 中国联合网络通信集团有限公司 Method, device and server for processing user information of gas station
CN113613174A (en) * 2021-07-09 2021-11-05 中山大学 Method, device and storage medium for identifying occupational sites based on mobile phone signaling data
CN114501419B (en) * 2021-12-30 2023-05-12 中国联合网络通信集团有限公司 Signaling data processing method, apparatus and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105682024A (en) * 2016-01-05 2016-06-15 重庆邮电大学 City hot spot identification method based on mobile signaling data
CN105682025A (en) * 2016-01-05 2016-06-15 重庆邮电大学 User residing location identification method based on mobile signaling data
CN105740904A (en) * 2016-01-29 2016-07-06 东南大学 Travel and activity mode identification method based on DBSCAN clustering algorithm
CN106197458A (en) * 2016-08-10 2016-12-07 重庆邮电大学 A kind of cellphone subscriber's trip mode recognition methods based on mobile phone signaling data and navigation route data
CN106407277A (en) * 2016-08-26 2017-02-15 北京车网互联科技有限公司 Internet of vehicles data-based attribute analysis method for vehicle owner parking point after being clustered

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011142225A1 (en) * 2010-05-12 2011-11-17 日本電気株式会社 Feature-point detection system, feature-point detection method, and program

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105682024A (en) * 2016-01-05 2016-06-15 重庆邮电大学 City hot spot identification method based on mobile signaling data
CN105682025A (en) * 2016-01-05 2016-06-15 重庆邮电大学 User residing location identification method based on mobile signaling data
CN105740904A (en) * 2016-01-29 2016-07-06 东南大学 Travel and activity mode identification method based on DBSCAN clustering algorithm
CN106197458A (en) * 2016-08-10 2016-12-07 重庆邮电大学 A kind of cellphone subscriber's trip mode recognition methods based on mobile phone signaling data and navigation route data
CN106407277A (en) * 2016-08-26 2017-02-15 北京车网互联科技有限公司 Internet of vehicles data-based attribute analysis method for vehicle owner parking point after being clustered

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Understanding individual human mobility patterns;Gonzalez, M. C.等;《Nature》;20080630;第453卷(第5期);779–782 *
Using mobile phone data to explore spatial-temporal evolution of home-based daily mobility patterns in Shanghai;Zhicheng Liu等;《 2016 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC)》;20161113;1-6 *

Also Published As

Publication number Publication date
CN106897420A (en) 2017-06-27

Similar Documents

Publication Publication Date Title
CN106897420B (en) Mobile phone signaling data-based user travel resident behavior identification method
CN110264709B (en) Method for predicting traffic flow of road based on graph convolution network
CN110879989B (en) Ads-b signal target identification method based on small sample local machine learning model
CN107766808B (en) Method and system for clustering moving tracks of vehicle objects in road network space
Xu et al. A hybrid machine learning model for demand prediction of edge-computing-based bike-sharing system using Internet of Things
Lim et al. Understanding the linkages of smart-city technologies and applications: Key lessons from a text mining approach and a call for future research
CN104318324B (en) Shuttle Bus website and route planning method based on taxi GPS records
CN104796481B (en) Intelligent audio and video selection method
CN108256590B (en) A kind of similar traveler recognition methods based on compound first path
CN109002492B (en) Performance point prediction method based on LightGBM
US20230215272A1 (en) Information processing method and apparatus, computer device and storage medium
CN112668375B (en) Tourist distribution analysis system and method in scenic spot
CN111598333B (en) Passenger flow data prediction method and device
CN106846082A (en) Tourism cold start-up consumer products commending system and method based on hardware information
CN112651546B (en) Bus route optimization method and system
CN108898244B (en) Digital signage position recommendation method coupled with multi-source elements
CN111784022A (en) Short-time adjacent fog prediction method based on combination of Wrapper method and SVM method
Ma et al. Public transportation big data mining and analysis
CN111833224A (en) Urban main and auxiliary center boundary identification method based on population grid data
Pramanik et al. Modeling traffic congestion in developing countries using *** maps data
CN112101132B (en) Traffic condition prediction method based on graph embedding model and metric learning
CN111678531B (en) Subway path planning method based on LightGBM
CN111414719B (en) Method and device for extracting peripheral features of subway station and estimating traffic demand
CN113420059A (en) Method and device for actively treating citizen hot line problem
CN114329240A (en) Site selection feature screening method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant