CN108230724A - A kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation - Google Patents
A kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation Download PDFInfo
- Publication number
- CN108230724A CN108230724A CN201810094908.1A CN201810094908A CN108230724A CN 108230724 A CN108230724 A CN 108230724A CN 201810094908 A CN201810094908 A CN 201810094908A CN 108230724 A CN108230724 A CN 108230724A
- Authority
- CN
- China
- Prior art keywords
- data
- card
- website
- passenger
- bus
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000001680 brushing effect Effects 0.000 claims abstract description 12
- 241001269238 Data Species 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 5
- 230000003542 behavioural effect Effects 0.000 abstract description 3
- 238000007418 data mining Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 abstract description 2
- 230000009467 reduction Effects 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract 1
- 238000002715 modification method Methods 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 8
- 208000006011 Stroke Diseases 0.000 description 7
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000005067 remediation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
- G08G1/133—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams within the vehicle ; Indicators inside the vehicles or at stops
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation, includes the following steps for there is shortage of data in the vehicle-mounted reporting station system of city bus：By analyzing the feature of missing data and the behavioral characteristic and with reference to historical data of swiping the card of bus passenger, the maximum probability estimation model using journey time as posteriority conditional parameter set is constructed, the missing data that equipment is automatically reported the bus stop in urban mass-transit system has accurately been inferred by passenger's brushing card data.Data modification method provided by the present invention; overcome is influenced in the prior art by urban architecture shadow effect; easily there is positioning failure or communication packet loss in public transport vehicle-mounted automatic station name announcing system; cause to call out the stops information imperfect the defects of seriously affecting follow-up data mining effect; the success rate of passenger's bus trip track reduction is improved, increases the effectiveness of information of city bus Trip distribution research.
Description
Technical field
The present invention relates to intelligent public transport technical fields, are related to a kind of city bus system based on maximum probability estimation
System Vehicle station name announcing missing data method for repairing and mending.
Background technology
Passenger flow distribution data are the bases of Optimizing City public transport management, are to restrict city bus management level
Key and city bus researcher concern emphasis.For a long time, manager obtains generally by national sampling survey
Limited bus trip data, it is time-consuming and laborious, with high costs.In recent years, with automatic fare collection system (Automated Fare
Collection, AFC) with the extensive use of automatic station name announcing system (Automated Vehicle Locating, AVL), city
Public transit system has accumulated a large amount of operation management data.How by data mining technology, from public transit system available data it is low into
It is local to obtain bus passenger flow information, become the emphasis of domestic and international city bus researcher concern.
In the correlative study for obtaining bus passenger flow, passenger's brushing card data of riding is converted into passenger in public transit system
Movement locus is wherein the most key link.However, design focal point is often placed on operation clearly by existing bus card-reading system
Divide functionally, and ignore and record website of swiping the card, particularly the most widely used ticket public transport at present can only record passenger's
It gets on the bus moment and license number, line number, supreme get-off stop information.Therefore, in data processing, generally require first to brush
Card record carries out time match with reference to the record of calling out the stops of GPS vehicle-running recording systems and swipes the card website of getting on the bus to infer bus passenger, then
Assumed based on shortest distance transfer, continuous Trip chain is assumed to infer the get-off stop of passenger, finally, for debarkation stop can not be found
The record of swiping the card of point attracts power method to estimate get-off stop by website.
Above-mentioned data handling procedure heavy dependence vehicle is called out the stops data, however, vehicle-mounted automatic station reporting system heavy dependence GPS
Module is obtained with 2G mobile communication modules, upload location information, which is influenced seriously, easily to go out by urban architecture shadow effect
Now positioning failure or communication packet loss, the information that causes to call out the stops are imperfect.By the public transit vehicle AVL for analyzing certain city call out the stops data,
Shift dispatches data and AFC brushing card datas, finds the missing data accounting 6.25% that is averaged in the timing statistics Duan Nei whole cities, and number
It is located at the urban population dense Region according to the high region of miss rate.Although shortage of data rate, less than 10%, subsequent public transport multiplies
Visitor's website matching result of getting on the bus shows that missing data leads to that more than 25% brushing card data website of getting on the bus can not be matched.Thus
As it can be seen that the AVL of generally existing calls out the stops shortage of data situation in urban mass-transit system, passenger is significantly affected and has gone on a journey track reduction
Process, and seriously restrict bus passenger flow mining effect.
Invention content
It is an object of the invention to be directed to the event of data loss of generally existing in city bus automatic station name announcing system, provide
A kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation.This method is lacked by analyzing
The feature of data and the behavioral characteristic of swiping the card of bus passenger, construct using journey time as the pole of posteriority conditional parameter set
Maximum probability estimates model, has accurately inferred the Vehicle station name announcing data of urban mass-transit system missing, to carry out subsequent data mining
Necessary support is provided.
In order to achieve the above object, the present invention uses following technical scheme：
A kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation of the present invention, including
Following steps：
S1, by dispatching a car each time, classified finishing is carried out to data source 2 " AVL vehicles call out the stops data ", by what is dispatched a car each time
AVL calls out the stops data according to the arrangement of public bus network station sequence：{S0,S1,S2,…,Si, wherein SiCorresponding vehicle reaches SiThe AVL of website
Information；
S2, data that certain in step S1 is once dispatched a car, the row of public bus network corresponding with data source 1 " bus dispatching data "
Station sequence is compared；
If S21, site information are complete, there is no shortage of data, without repairing；
If S22, site information are imperfect, illustrate there is a situation where AVL shortage of data, lock the station there are loss of data
Point section Sl={ S0,SL0,SL1,…,SLk,…,S1, and the journey time in the missing data section is calculated, it is denoted as tTRIP；
S3, " the passenger AFC brushing card datas " provided according to data source 3, inquiry take this stroke public transport regular bus from S0To Si
Passenger's brushing card data in way, and extract the 1st event of swiping the card in the website that passenger swipes the card by bus using thresholding method
Charge time stamp, wherein SLkFirst swiping the card for the passenger that gets on the bus of standing is denoted as constantly
S4 by historical data, is calculated respectively from S0It sets out to SL0,SL1,…,SLk, when meeting the stroke of control condition Θ
Between probability-distribution function：Preferably, Θ=tTRIP∈
[tTRIP-0.1×tTRIP,tTRIP+0.1×tTRIP]；
S5, by SlEach website S in strokeLkThe charge time stamp of 1st event of swiping the cardSubtract S0The outbound moment, obtain
To the journey time of each website, to any journey time, each station Annual distribution function obtained by S4 is substituted into, obtains probability
Value, exporting the website corresponding to the function of maximum value isThe station that moment vehicle reaches, inferred from input data are completed.
As preferred technical solution, the data source 1 " bus dispatching data " includes：A) shift is numbered；B) license plate number；
C) line number；D) frequency；E) station sequence；
The data source 2 " AVL vehicles call out the stops data " includes：A) license plate number；B) line number；C) station name；When d) entering the station
It carves；E) the outbound moment；
The data source 3 " passenger AFC brushing card datas " includes：A) license plate number；B) line number；C) station name；When d) swiping the card
It carves；E) passenger identification；F) site match state.
As preferred technical solution, step S22 is specially：
It is called out the stops data and complete public bus network driving station sequence by the AVL for comparing current train number, there are data to lose for locking
The website section of mistake marks the site number of missing, it is assumed that Sl={ S0,SL0,SL1,…,SLk,…,S1, it is this process of dispatching a car
Middle vehicle continuously across one section of website section, wherein, S0With S1For the complete website of data, SL0,SL1,…,SLkFor S0With S1
Between call out the stops the website of shortage of data.
As preferred technical solution, step S3 is specially：
Since passenger swipes the card as short interval continuous events, can setting time threshold value as dividing adjacent station Si,Si+1Passenger
Reference, that is, if the adjacent intra-record slack byte time of swiping the card is regarded as same station less than setting time, by the adjacent record of swiping the card
It swipes the card record；Otherwise latter item, which is swiped the card, is recorded as first record of swiping the card of the next stop.
As preferred technical solution, in step S4, the historical data is the history AVL data of no less than surrounding.
As preferred technical solution, in step S4, there is the unknown website S for the passenger that gets on the bus in certainLk, swipe the card for first and get on the bus
Passenger generate charge time stamp beThe then shift, enter the station moment of the bus at the station can be equivalent to
As preferred technical solution, in step S4, it is assumed thatGaussian distributed：
Then, after Θ is determined, you can all slave site S in query history AVL data0To website SLKAnd meet control condition
The stroke of Θ, the mean μ and standard deviation sigma of computation model parameter temporal.
Compared with prior art, the present invention having the following advantages that and advantageous effect：
1st, the present invention is constructed by analyzing the feature of missing data and the behavioral characteristic of swiping the card of bus passenger with stroke
Maximum probability estimation model of the time as posteriority conditional parameter set gives full play to the advantage of mass data, is particularly suitable for sample
The huge occasion of this amount.
2nd, the method that uses of the present invention, construct in a certain vehicle in use one stroke continuously across set of sites St={ S0,
SL0,SL1,...,SLK,S1, wherein SL0,SL1,...,SLKIt is data complete station S0And S1Between occur shortage of data website,
It can be adapted for the reparation of the multiple websites of consecutive miss, remediation efficiency is high.
3rd, compared to traditional method, data convert accuracy rate of the present invention is high, and the feelings equal to 8 are less than in consecutive miss website
Under condition, more than 85% reduction accuracy rate can be kept.
Description of the drawings
Fig. 1 is the overall workflow figure of the present embodiment public transit system AVL missing data method for repairing and mending.
Fig. 2 is data convert success rate under the conditions of verifying after the present embodiment difference.
Specific embodiment
With reference to embodiment and attached drawing, the present invention is described in further detail, but embodiments of the present invention are unlimited
In this.
Embodiment
With certain city bus data instance, the AVL vehicles for extracting on March 5th, 2017 are called out the stops data as basic data source, are swept
It retouches AVL to call out the stops the data of calling out the stops of each car in data, website is started with 15% probability random selection, and 8 stations after taking out
The AVL of point data of calling out the stops add in alternative test set, obtain 94750 test datas altogether.Compare number to each in alternative test set
According to except first and the last one record (S that calls out the stops0、S1) outer all records of calling out the stops enter the station add in constantly it is equally distributed random
Interfere (range：0-120s), test set is obtained.The key message field that every test data includes in test set is as shown in table 1：
The key message field of 1 test data of table
Therefore, missing data infers that task concentrates all records for sweep test, and according to its first and the last item
Call out the stops record (S0、S1) and time stamp T comprising disturbanceL0‘,TL1’,…,TLk' it is inferred to SL0,SL1,…,SLk。
The present invention provides a kind of public transit system AVL missing data method for repairing and mending based on maximum probability estimation, and flow is such as
Shown in Fig. 1, include the following steps：
The first step by dispatching a car each time, extracts its AVL data, and sort according to time order and function.
Second step, compares the driving station sequence of the circuit, and 1) if site information is complete, there is no shortage of data, without repairing
It is multiple；If 2) site information is imperfect, illustrates there is a situation where AVL shortage of data, repaired.The feelings that needs are repaired
Condition constructs Sl={ S0,SL0,SL1,…,SLk,…,S1For in the secondary stroke continuously across website section, wherein, S0With S1For
The complete website of data, SL0,SL1,…,SLkFor S0With S1Between missing call out the stops data station.
Third walk, according to data source 3 provide " passenger AFC brushing card datas ", inquiry take this stroke public transport regular bus from
S0To SiPassenger's brushing card data in way, and extract in the website that passenger swipes the card by bus the 1st using thresholding method and swipe the card
The charge time stamp of event, wherein SLkFirst swiping the card for the passenger that gets on the bus of standing is denoted as constantly
4th step by historical data, is calculated respectively from S0It sets out to SL0,SL1,…,SLk, meet the row of control condition Θ
Journey time probability distribution function：Θ=tTRIP∈
[tTRIP-0.1×tTRIP,tTRIP+0.1×tTRIP] it is tried preferred embodiment, and can flexibly be repaiied according to actual conditions
Change；Therefore Θ can be other control conditions.
5th step, by SlEach website S in strokeLkThe charge time stamp of 1st event of swiping the cardSubtract S0It is outbound when
It carves, obtains the journey time of each website, to any journey time, substitute into each station Annual distribution function obtained by S4, obtain
Probability value, it is the station that moment vehicle reaches to export the website corresponding to the function of maximum value, and inferred from input data is completed.
The data modification model performance comparison built with different control conditions is as shown in Fig. 2, the present invention is used based on row
The maximum probability estimation model of journey time, with respect to prior probability model and based on other probabilistic models such as start time, sheet
The there is provided preferred embodiment data modification best results of invention are maintained in the case where consecutive miss website number is less than or equal to 8
More than 85% reparation accuracy.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (7)
1. a kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation, which is characterized in that
Include the following steps：
S1, by dispatching a car each time, classified finishing, the AVL that will be dispatched a car each time are carried out to data source 2 " AVL vehicles call out the stops data "
Data of calling out the stops are arranged according to public bus network station sequence：{S0,S1,S2,…,Si, wherein SiCorresponding vehicle reaches SiThe AVL letters of website
Breath；
S2, data that certain in step S1 is once dispatched a car, the driving station of public bus network corresponding with data source 1 " bus dispatching data "
Sequence is compared；
If S21, site information are complete, there is no shortage of data, without repairing；
If S22, site information are imperfect, illustrate there is a situation where AVL shortage of data, lock the website area there are loss of data
Between Sl={ S0,SL0,SL1,…,SLk,…,S1, and the journey time in the missing data section is calculated, it is denoted as tTRIP；
S3, " the passenger AFC brushing card datas " provided according to data source 3, inquiry take this stroke public transport regular bus from S0To SiIn way
Passenger's brushing card data, and extract using thresholding method the brush of the 1st event of swiping the card in the website that passenger swipes the card by bus
Card timestamp, the website S of any of which missing dataLk, first swiping the card for the passenger that gets on the bus be denoted as constantly
S4 by historical data, is calculated respectively from S0It sets out to SL0,SL1,…,SLk, the journey time for meeting control condition Θ is general
Rate distribution function：Wherein, Θ=tTRIP∈[tTRIP-
0.1×tTRIP,tTRIP+0.1×tTRIP]；
S5, by SlEach website S in strokeLkThe charge time stamp of 1st event of swiping the cardSubtract S0The outbound moment, obtain every
The journey time of a website to any journey time, substitutes into each station Annual distribution function obtained by S4, obtains probability value, defeated
Going out the website corresponding to the function of maximum value isThe station that moment vehicle reaches, inferred from input data are completed.
2. the urban mass-transit system Vehicle station name announcing missing data repairing side based on maximum probability estimation according to claim 1
Method, which is characterized in that the data source 1 " bus dispatching data " includes：A) shift is numbered；B) license plate number；C) line number；D) it sends out
The vehicle moment；E) station sequence；
The data source 2 " AVL vehicles call out the stops data " includes：A) license plate number；B) line number；C) station name；D) it enters the station the moment；e)
The outbound moment；
The data source 3 " passenger AFC brushing card datas " includes：A) license plate number；B) line number；C) station name；D) it swipes the card the moment；e)
Passenger identification；F) site match state.
3. the urban mass-transit system Vehicle station name announcing missing data repairing side based on maximum probability estimation according to claim 1
Method, which is characterized in that step S22 is specially：
It is called out the stops data and complete public bus network driving station sequence by the AVL for comparing current train number, there are loss of data for locking
Website section marks the site number of missing, it is assumed that Sl={ S0,SL0,SL1,…,SLk,…,S1, vehicle during dispatching a car for this
Continuously across one section of website section, wherein, S0With S1For the complete website of data, SL0,SL1,…,SLkFor S0Between S1
It calls out the stops the website of shortage of data.
4. the urban mass-transit system Vehicle station name announcing missing data repairing side based on maximum probability estimation according to claim 1
Method, which is characterized in that step S3 is specially：
Since passenger swipes the card as short interval continuous events, can setting time threshold value as dividing adjacent station Si,Si+1The ginseng of passenger
It examines, that is, if the adjacent record of swiping the card less than setting time, is regarded as swiping the card for same station by the adjacent intra-record slack byte time of swiping the card
Record；Otherwise latter item, which is swiped the card, is recorded as first record of swiping the card of the next stop.
5. the urban mass-transit system Vehicle station name announcing missing data repairing side based on maximum probability estimation according to claim 1
Method, which is characterized in that in step S4, the historical data is the history AVL data of no less than surrounding.
6. the urban mass-transit system Vehicle station name announcing missing data repairing side based on maximum probability estimation according to claim 1
Method, which is characterized in that in step S4, certain has the unknown website S for the passenger that gets on the busLk, first is swiped the card what the passenger to get on the bus generated
Charge time stamp isThe then shift, enter the station moment of the bus at the station can be equivalent to
7. the urban mass-transit system Vehicle station name announcing missing data repairing side based on maximum probability estimation according to claim 1
Method, which is characterized in that in step S4, it is assumed thatGaussian distributed：
Then, after Θ is determined, you can all slave site S in query history AVL data0To website SLKAnd meet control condition Θ's
Stroke, the mean μ and standard deviation sigma of computation model parameter temporal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810094908.1A CN108230724B (en) | 2018-01-31 | 2018-01-31 | Urban public transport system vehicle-mounted station reporting missing data repairing method based on maximum probability estimation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810094908.1A CN108230724B (en) | 2018-01-31 | 2018-01-31 | Urban public transport system vehicle-mounted station reporting missing data repairing method based on maximum probability estimation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108230724A true CN108230724A (en) | 2018-06-29 |
| CN108230724B CN108230724B (en) | 2020-05-22 |
Family
ID=62670264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810094908.1A Expired - Fee Related CN108230724B (en) | 2018-01-31 | 2018-01-31 | Urban public transport system vehicle-mounted station reporting missing data repairing method based on maximum probability estimation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108230724B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523821A (en) * | 2018-11-30 | 2019-03-26 | 湖南智慧畅行交通科技有限公司 | It is a kind of that point calculating method leaving from station is arrived based on city bus GPS information |
| CN109615036A (en) * | 2018-11-30 | 2019-04-12 | 深圳大学 | Fine particle exposure risk assessment method based on bus IC card swiping system |
| CN109727474A (en) * | 2019-01-29 | 2019-05-07 | 苏州工业园区测绘地理信息有限公司 | A kind of bus based on fused data precise recognition method out of the station |
| CN110738845A (en) * | 2019-09-20 | 2020-01-31 | 江苏大学 | bus GPS data complement method and complement system based on abnormal data processing |
| CN112767685A (en) * | 2020-12-22 | 2021-05-07 | 荆门汇易佳信息科技有限公司 | Public transport passenger flow analysis system based on positioning and card swiping information |
| CN113344268A (en) * | 2021-06-02 | 2021-09-03 | 合肥泰瑞数创科技有限公司 | Urban traffic trip data analysis method |
| CN116611984A (en) * | 2023-07-11 | 2023-08-18 | 鹏城实验室 | Travel data processing method, system, equipment and medium under multiple modes |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574137A (en) * | 2015-12-15 | 2016-05-11 | 华南理工大学 | Public transportation multi-source data fusion based IC card swiping station matching method |
| US20160231129A1 (en) * | 2015-02-05 | 2016-08-11 | Moovit App Global Ltd | Public and ordered transportation trip planning |
| CN106448233A (en) * | 2016-08-19 | 2017-02-22 | 大连理工大学 | Big data based bus route time table collaborative optimization method |
| CN106816029A (en) * | 2016-10-15 | 2017-06-09 | 广东探金电子科技有限公司 | A kind of control system of automatic bus stop announcing |
-
2018
- 2018-01-31 CN CN201810094908.1A patent/CN108230724B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160231129A1 (en) * | 2015-02-05 | 2016-08-11 | Moovit App Global Ltd | Public and ordered transportation trip planning |
| CN105574137A (en) * | 2015-12-15 | 2016-05-11 | 华南理工大学 | Public transportation multi-source data fusion based IC card swiping station matching method |
| CN106448233A (en) * | 2016-08-19 | 2017-02-22 | 大连理工大学 | Big data based bus route time table collaborative optimization method |
| CN106816029A (en) * | 2016-10-15 | 2017-06-09 | 广东探金电子科技有限公司 | A kind of control system of automatic bus stop announcing |
Non-Patent Citations (1)
| Title |
|---|
| 胡继华等: "结合出行链的公交IC卡乘客下车站点判断概率模型", 《交通运输系统工程与信息》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523821A (en) * | 2018-11-30 | 2019-03-26 | 湖南智慧畅行交通科技有限公司 | It is a kind of that point calculating method leaving from station is arrived based on city bus GPS information |
| CN109615036A (en) * | 2018-11-30 | 2019-04-12 | 深圳大学 | Fine particle exposure risk assessment method based on bus IC card swiping system |
| CN109727474A (en) * | 2019-01-29 | 2019-05-07 | 苏州工业园区测绘地理信息有限公司 | A kind of bus based on fused data precise recognition method out of the station |
| CN110738845A (en) * | 2019-09-20 | 2020-01-31 | 江苏大学 | bus GPS data complement method and complement system based on abnormal data processing |
| CN112767685A (en) * | 2020-12-22 | 2021-05-07 | 荆门汇易佳信息科技有限公司 | Public transport passenger flow analysis system based on positioning and card swiping information |
| CN113344268A (en) * | 2021-06-02 | 2021-09-03 | 合肥泰瑞数创科技有限公司 | Urban traffic trip data analysis method |
| CN113344268B (en) * | 2021-06-02 | 2022-04-19 | 合肥泰瑞数创科技有限公司 | Urban traffic trip data analysis method |
| CN116611984A (en) * | 2023-07-11 | 2023-08-18 | 鹏城实验室 | Travel data processing method, system, equipment and medium under multiple modes |
| CN116611984B (en) * | 2023-07-11 | 2024-02-02 | 鹏城实验室 | Travel data processing method, system, equipment and medium under multiple modes |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108230724B (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108230724A (en) | A kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation | |
| CN104766473A (en) | Traffic trip feature extraction method based on multi-mode public transport data matching | |
| CN106022296A (en) | Fake plate vehicle detection method based on vehicle hot spot area probability aggregation | |
| CN109191605B (en) | Highway charging rate accuracy evaluation method considering charging path | |
| CN108806248B (en) | Vehicle travel track division method for RFID electronic license plate data | |
| CN108694858A (en) | A kind of method and its system carrying out parking management based on block chain technology | |
| CN105225476A (en) | A kind of generation of track of vehicle, polymerization and device | |
| CN105719489A (en) | Fake-licensed vehicle detection method based on bayonet vehicle flow direction probability | |
| CN107329977B (en) | A kind of false-trademark vehicle postsearch screening method based on probability distribution | |
| CN110969861B (en) | Vehicle identification method, device, equipment and computer storage medium | |
| CN109584555A (en) | Bus passenger get-off stop estimation method based on AFC data | |
| CN112925820B (en) | Method, device and system for identifying vehicle evasion toll | |
| CN108122186A (en) | Location estimation method is lived in a kind of duty based on bayonet data | |
| Wang et al. | GPS‐data‐driven dynamic destination prediction for on‐demand one‐way carsharing system | |
| Hamedmoghadam et al. | Automated extraction of origin-destination demand for public transportation from smartcard data with pattern recognition | |
| Liu et al. | Data analytics approach for train timetable performance measures using automatic train supervision data | |
| CN110164136B (en) | Fake-licensed vehicle identification method | |
| CN117196078A (en) | New energy automobile fills electric pile operation data analysis management system based on big data | |
| CN114841712A (en) | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment | |
| CN106447052A (en) | Malfunction service method for public bicycles | |
| CN108242146A (en) | Based on mass transit card data analysis passenger ride website it is timely between method and system | |
| CN116911755A (en) | Intelligent vehicle management method and system based on intelligent substation | |
| CN114407661A (en) | Data-driven electric vehicle energy consumption prediction method, system, device and medium | |
| CN111739180B (en) | Path segmentation method based on ETC portal frame | |
| CN110880244B (en) | Method and system for distinguishing whether taxi is cloned taxi |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200522 |