CN104835320A - Traffic flow estimation method based on mobile communication data - Google Patents

Traffic flow estimation method based on mobile communication data Download PDF

Info

Publication number
CN104835320A
CN104835320A CN201510218334.0A CN201510218334A CN104835320A CN 104835320 A CN104835320 A CN 104835320A CN 201510218334 A CN201510218334 A CN 201510218334A CN 104835320 A CN104835320 A CN 104835320A
Authority
CN
China
Prior art keywords
mobile data
traffic flow
data sample
traffic
method based
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.)
Granted
Application number
CN201510218334.0A
Other languages
Chinese (zh)
Other versions
CN104835320B (en
Inventor
杨灿
朱四民
吕建明
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.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
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 South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN201510218334.0A priority Critical patent/CN104835320B/en
Publication of CN104835320A publication Critical patent/CN104835320A/en
Application granted granted Critical
Publication of CN104835320B publication Critical patent/CN104835320B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks

Landscapes

  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a traffic flow estimation method based on mobile communication data. The method comprises following steps: S1. acquiring a mobile communication data source; S2. filtering a mobile communication data sample; S3. removing abnormal values of the mobile communication data sample; S4. estimating the traffic flow based on the mobile communication data sample; and S5. displaying the traffic flow estimation data. By employing the method, the traffic flow can be estimated when traffic condition data is less, and a current mobile communication data network is fully utilized, so that the cost of traffic network deployment can be reduced.

Description

A kind of traffic flow evaluation method based on mobile data
Technical field
The present invention relates to a kind of traffic flow estimation and detection technique, particularly a kind of traffic flow evaluation method based on mobile data.
Background technology
Along with Chinese society expanding economy, road capacity can not meet the growing needs of the volume of traffic, and traffic congestion, the choking phenomenon of surge are on the rise, the concern that traffic pollution and accident more and more cause society general.Through for a long time, widely, research and experience and lessons prove, many countries are own through determining to build more road by mainly relying on, expand road network scale and solve growing traffic needs, transferred to and utilized the modem technology such as electronics, computing machine, communication to transform existing road.The projects such as such as break in traffic rules and regulations automatic checkout system, intelligent bus dispatching system, highway electric Fare Collection System.Based on the basis of these projects, existing multiple navigation application (such as, Baidu's map, high moral map etc.) is obtained the information of current traffic condition by GPS location and information is supplied to user.
The source obtained about current traffic condition information has two kinds, and a kind of is the observation manually provided, and another is the traffic sensor network disposed in the urban area that some are large-scale.But all there is certain defect in these two kinds sources.The information that the observation such as manually provided provides lacks the enough details being enough to use usually.And for traffic sensor network design, dispose being limited in scope on the one hand, may accuracy problem be there is in the data provided on the other hand.And the communication data between mobile device and base station can make up the deficiency of this respect, the present embodiment estimates the situation of traffic flow based on mobile data.
Summary of the invention
The object of the invention is to overcome the shortcoming of prior art and deficiency, a kind of traffic flow evaluation method based on mobile data is provided, this evaluation method overcomes the deficiency that observation that existing utilization manually provides or the traffic related information that traffic sensor network provides detect traffic flow, solve the technical matters that Traffic flow detecting accuracy rate is comparatively low in the imperfect situation of traffic related information, be a kind of completely newly by based on mobile data, utilize the evaluation method of data mining technology implementation traffic flow, this evaluation method not only effectively can solve the deficiency of existing Traffic flow detecting technology, and accuracy and the reliability of existing Traffic flow detecting technology can be improved.
Object of the present invention is achieved through the following technical solutions: based on the communication data between mobile device and cellular basestation, detects the situation of change of traffic flow.Each cellular basestation can be mapped on road, is therefore in number of users in cellular basestation and vehicle flowrate has certain relation.Along with the movement of vehicle can change, the number of users difference in adjacent cellular base stations also can change along with the time.To the analysis of above-mentioned number of users difference, by data mining technology, the traffic flow situation of change of road can be estimated, thus it is not enough to compensate for the detection of the existing magnitude of traffic flow.
Specifically, the technical solution adopted in the present invention is as follows: a kind of traffic flow evaluation method based on mobile data, comprises following steps:
The acquisition of S1, mobile data;
S2, mobile data sample filter;
S3, mobile data sample exceptional value are removed;
S4, mobile data sample flow estimation;
S5, traffic flow data show.
Step S1 is specially: in an embodiment, and other mobile devices that mobile data source comprises computing equipment and the user that road travels and cellular basestation communicate mutually and produce.Data sample includes the information such as timestamp, cellular address and status identifier.
Step S2 is specially: according to the cellular address in mobile data sample, is associated by data sample with road section in interested geographic area.Utilize the cellular address of each data sample to determine whether this data sample is the interested road segment segment of user, thus filter such mobile data sample, so that not to they modelings.
Step S3 is specially: in determined mobile data sample group, by adding up the number of users in other groups in each honeycomb, calculating mean value and standard deviation determine the deviation of this group data, the mobile data sample large when deviation ratio predetermined threshold will be identified as exception record, therefore can abandon this mobile data record.
Step S4 is specially: the journey time of the customer volume and the magnitude of traffic flow and section that are arranged in certain honeycomb has close relationship, and the relation of its inherence also more complicated.The present embodiment, by filtering and remove the mobile data of exceptional value, is estimated by the mode arranging weighted value.
Step S5 is specially: input interested section according to user, inquires about the cellular basestation of section coupling therewith, the traffic related information in this section is passed to user, as by UI interface display.
The present invention has following advantage and effect relative to prior art: the present invention utilizes mobile data to estimate traffic flow, thus the real-time traffic feeding back to user's present stage, comprise the filtration to mobile data and adjustment, and set up appraising model based on adjacent cell Distance geometry temporal information, traffic flow is estimated.Thus the situation of the traffic related information deficiency provided in the observation manually provided or traffic sensor network is provided.
Accompanying drawing explanation
Fig. 1 is method block scheme of the present invention.
Fig. 2 is that mobile data sample filters schematic diagram.
Fig. 3 is that mobile data sample exceptional value removes process flow diagram.
Fig. 4 is based on mobile data estimation magnitude of traffic flow process flow diagram.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited thereto.
Embodiment
As shown in Figure 1, a kind of traffic flow evaluation method based on mobile data, comprises following key step:
The acquisition of S1, mobile data;
S2, mobile data sample filter;
S3, mobile data sample exceptional value are removed;
S4, mobile data sample flow estimation;
S5, traffic flow data show.
The concrete implementation method of abovementioned steps S1 is: mainly obtain from database.The mismatch of reading and writing speed may be there is to the acquisition of mobile data.Such as, in the process of carrying out Data Analysis Services, even if network condition normal table, but the own processing speed of background system or unstable.In order to head it off can introduce the concept of message pool, as transmission of messages buffering between system module, this message pool does not carry out any process to message, only completes the function accepting and send, plays an effect of forming a connecting link at intermodule.
The concrete implementation method of abovementioned steps S2 is: idiographic flow is as Fig. 2.In S201, user inputs interested time period and road segment segment, from storing mobile communications database, read data sample; S202 to be associated with road segment segment according to the cellular address in the data sample read in S201 and to map; The data sample of the uninterested road segment segment of S203 filter user; S204 judges whether according to cellular address filtering data sample, and this step of S205 mainly in order to better filtering data, thus obtains the larger mobile data sample of correlativity.Mobile data sample after S206 stored filter is with doing further process later; S207 judges whether enough mobile data samples, is, stops filtering, otherwise turns back to S201.
The concrete implementation method of abovementioned steps S3 is: as shown in Figure 3, to the mobile data sample after filtration, removes the exception record in data sample.
Step S301, receives filtered data sample in step S2, and sets the threshold value of exceptional value, be designated as: c;
Step S302, S303, S304, S305, associate with given road segment segment within a period of time, for each group, add up each in by cellular address counting user number.Such as group i, have n honeycomb, then the number of users in each honeycomb is designated as U ij, j ∈ [1, n].Adjacent two honeycombs are designated as k, k+1, (k ∈ [1, n)), then the absolute value of the difference of the number of users in adjacent cell is diff_u, then:
diff_u m＝|U ik-U i(k+1)|,(k∈[1,n),m∈[1,n-1])；
If the data sample of honeycomb k is removed,
Wherein, for n honeycomb, the mean value of the absolute value diff_u of the number of users difference in adjacent cell, is designated as then:
diff _ u ‾ = Σ i = 1 n - 1 diff _ u i n - 1 ;
Wherein, for group i, have n honeycomb, the standard deviation of the absolute value diff_u of the number of users difference in adjacent cell, is:
∂ = 1 n - 1 Σ m = 1 n - 1 ( diff _ u m - diff _ u ‾ ) i 2
Step S306 preserves and removes data sample after exceptional value and often organize
Step S307 judges that whether data sample number is enough, is remove exceptional value course and terminate, otherwise return S301.
The specific implementation method of abovementioned steps S4 is: as shown in Figure 4, to removing abnormal data sample, carries out the estimation of magnitude of traffic flow change.
Step S401, the mobile data sample obtaining from abovementioned steps 3 and handle well;
Step S402, whether above-mentioned data volume presets the data-quantity threshold for estimating traffic flow; If then enter S403, otherwise enter S404;
Step S404, maps mutually with user's road segment segment interested according to the cellular location information in the mobile data sample in step S401 and timestamp, and adds up qualified honeycomb quantity.
Step S405, calculates the absolute value diff_u of each adjacent cell user data difference according to above-mentioned steps 3 ij, diff_u ijbe different in different road segment segment and time period, thus the crowd that to react in certain region is along with the change of time.Its computing formula is as follows:
diff_u ij＝|U i-U j|,(i,j∈[1,n],i≠j)
Wherein U i, represent the number of users in honeycomb i.
Step S405, arranges the weights { w of adjacent cell position ij, wherein { w ij, represent the weights that honeycomb i is adjacent with honeycomb j; Its set-up mode has multiple, such as the present embodiment, arranges { w according to the adjacent cell Distance geometry time period ij, the shorter weights of distance are larger, at { the w of different time periods ijdifferent, { the w of the peak period that is such as on duty ijthan { the w of period after morning ijwant large.
Step S406, the fluctuations in discharge situation of estimation user's interested time period and road segment segment; The evaluation method of the present embodiment is:
Σ i = 1 n - 1 w ij diff _ u ij / ( n - 1 ) ( t 2 - t 1 ) , ( i , j ∈ [ 1 , n ] , i ≠ j ) .
Above-described embodiment is the present invention's preferably embodiment; but embodiments of the present invention are not restricted to the described embodiments; change, the modification done under other any does not deviate from Spirit Essence of the present invention and principle, substitute, combine, simplify; all should be the substitute mode of equivalence, be included within protection scope of the present invention.

Claims (6)

1., based on a traffic flow evaluation method for mobile data, it is characterized in that: the method includes the steps of:
Step S1, mobile data source;
The filtration of step S2, mobile data sample;
Step S3, mobile data sample exceptional value are removed;
Step S4, mobile data sample flow estimation;
Step S5, traffic flow data show.
2. a kind of traffic flow evaluation method based on mobile data according to claim 1, is characterized in that: in step sl, introduces the concept of data pool, solves communication data and reads and store mismatch problem.
3. a kind of traffic flow evaluation method based on mobile data according to claim 1, it is characterized in that: in step s 2, according to the road section information of user's input, by mobile data sample and road segment segment phase mapping association, filter uninterested data sample.
4. a kind of traffic flow evaluation method based on mobile data according to claim 1, it is characterized in that: in step s3, data sample after filtering by above-mentioned 3, calculate the change of customer flow in adjacent honeycomb, removing abnormal mobile data record by calculating standard deviation statistics analysis, again calculating the changing value of user data traffic in adjacent honeycomb.
5. a kind of traffic flow evaluation method based on mobile data according to claim 1, it is characterized in that: in step s 4 which, using customer flow change in the mobile data and above-mentioned 4 after filtration as the input of traffic flow appraising model, by calculating and analyzing, estimate current telecommunication flow information.
6. a kind of traffic flow evaluation method based on mobile data according to claim 1, it is characterized in that: in step s 5, the result of output processes, and feeds back to user by UI interface or some application program.
CN201510218334.0A 2015-04-30 2015-04-30 A kind of traffic flow evaluation method based on mobile data Active CN104835320B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510218334.0A CN104835320B (en) 2015-04-30 2015-04-30 A kind of traffic flow evaluation method based on mobile data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510218334.0A CN104835320B (en) 2015-04-30 2015-04-30 A kind of traffic flow evaluation method based on mobile data

Publications (2)

Publication Number Publication Date
CN104835320A true CN104835320A (en) 2015-08-12
CN104835320B CN104835320B (en) 2017-08-25

Family

ID=53813180

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510218334.0A Active CN104835320B (en) 2015-04-30 2015-04-30 A kind of traffic flow evaluation method based on mobile data

Country Status (1)

Country Link
CN (1) CN104835320B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945501A (en) * 2017-11-14 2018-04-20 北京摩拜科技有限公司 Vehicle parking control method, device, system and vehicle
EP3839917A1 (en) 2019-12-18 2021-06-23 Telefónica Iot & Big Data Tech, S.A. Method, system and computer programs for traffic estimation using passive network data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030100990A1 (en) * 2001-11-28 2003-05-29 Clapper Edward O. Using cellular network to estimate traffic flow
WO2009080105A1 (en) * 2007-12-20 2009-07-02 Telecom Italia S.P.A. Method and system for estimating road traffic
CN103325247A (en) * 2012-03-19 2013-09-25 ***通信集团辽宁有限公司 Method and system for processing traffic information

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030100990A1 (en) * 2001-11-28 2003-05-29 Clapper Edward O. Using cellular network to estimate traffic flow
WO2009080105A1 (en) * 2007-12-20 2009-07-02 Telecom Italia S.P.A. Method and system for estimating road traffic
CN103325247A (en) * 2012-03-19 2013-09-25 ***通信集团辽宁有限公司 Method and system for processing traffic information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
李辉等: "《基于***网络的实时交通信息采集技术》", 《第六届中国智能交通年会暨第七届国际节能与新能源汽车创新发展论坛优秀论文集（上册）——智能交通》 *
黄嘉庚: "《基于移动互联网的交通信息采集技术的研究》", 《科技与创新》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945501A (en) * 2017-11-14 2018-04-20 北京摩拜科技有限公司 Vehicle parking control method, device, system and vehicle
EP3839917A1 (en) 2019-12-18 2021-06-23 Telefónica Iot & Big Data Tech, S.A. Method, system and computer programs for traffic estimation using passive network data

Also Published As

Publication number Publication date
CN104835320B (en) 2017-08-25

Similar Documents

Publication Publication Date Title
CN107038168A (en) A kind of user's commuting track management method, apparatus and system
CN104299415B (en) Based on distributed traffic condition detecting system and the method thereof of Bluetooth technology
CN101127158B (en) Predictive traffic information creating method, predictive traffic information creating apparatus, and traffic information display terminal
CN100568293C (en) The method of GPS locating information and electronic map charging section coupling
CN101976505A (en) Traffic evaluation method and system
CN107040894A (en) A kind of resident trip OD acquisition methods based on mobile phone signaling data
CN109151168A (en) The switching method of code, device, mobile terminal and readable storage medium storing program for executing by bus
CN106021584B (en) The carrying based reminding method and device of article
CN104331422A (en) Road section type presumption method
CN104240500A (en) Road condition information predicting method and system
CN105509758A (en) Route planning method and system based on mobile terminal and mobile terminal
CN104978858A (en) Highway real-time traffic monitoring method based on mobile phone signaling
CN102034285B (en) Method, system and device for monitoring operation regions of vehicles
US20140011484A1 (en) Method and system for estimating traffic information by using integration of location update events and call events
CN104933884A (en) Handset positioning information-based real-time road traffic condition navigation system
CN105634854A (en) User attribute analyzing method and device
CN106790646A (en) Recommend method, system and the client of the shared vehicles
CN106023582A (en) BRT passenger traveling information acquisition and guiding scheme publishing system and method
CN112738729B (en) Method and system for discriminating visiting and returning tourists through mobile phone signaling data
CN106504524B (en) A method of express highway section is divided based on mobile signaling protocol dynamic
CN107403550A (en) Transit network collecting method, device and terminal device
CN104966397A (en) Method and system for generating road condition information
CN104835320A (en) Traffic flow estimation method based on mobile communication data
CN103454653B (en) A kind of outlier replacement method based on gps system and device
CN202648721U (en) Vehicle fuel consumption monitoring system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant