CN108171970A - A kind of method and device for obtaining passenger on public transport track - Google Patents
A kind of method and device for obtaining passenger on public transport track Download PDFInfo
- Publication number
- CN108171970A CN108171970A CN201711311511.5A CN201711311511A CN108171970A CN 108171970 A CN108171970 A CN 108171970A CN 201711311511 A CN201711311511 A CN 201711311511A CN 108171970 A CN108171970 A CN 108171970A
- Authority
- CN
- China
- Prior art keywords
- bus
- passenger
- station
- getting
- record
- 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.)
- Pending
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
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0265—Vehicular advertisement
Abstract
The present invention provides a kind of method and device for obtaining passenger on public transport track, this method includes:Intelligent bus card data SCT is collected, is recorded by bus from Intelligent bus card extracting data is a plurality of;Processing analysis is carried out to a plurality of record by bus of extraction, calculates the station logical number of getting on or off the bus of passenger, station logical number of getting on or off the bus is corresponded with bus stop;Station logical number of getting on or off the bus according to passenger determines passenger by way of Station XXX sequence, so as to obtain passenger on public transport track data.The big data information that the embodiment of the present invention can easily get related passenger and ride by collecting Intelligent bus card data.Also, the passenger trajectory data of a large amount of passengers is further calculated using Intelligent bus card data, additionally aids and in depth understands passenger and take pubic transport the custom of route, and excavate the information such as the space-time mobility of passenger, the volume of the flow of passengers.
Description
Technical field
The present invention relates to data mining technology field, more particularly to a kind of method and dress for obtaining passenger on public transport track
It puts.
Background technology
In each big city, a large amount of residents can select public transit system to go on a journey, as Beijing has more than 10,000,000 persons daily
Select bus commuting.Crowd is wide, region is big because it is covered for advertising bus, therefore with more significant excellent compared with static advertising
Gesture has become outdoor advertising dominant form.
There are mainly three types of methods for the recommendation of the circuit of public transport body advertisement dispensing at present:1st, it rule of thumb, with reference to history launches
Circuit is launched in scheme, artificial selection;2nd, the passengers quantity and line length of all public bus networks are assessed, selects passengers quantity most
Or the longest public bus network of line length;3rd, it using data digging methods such as correlation rules, is extracted from public traffic network automatically
Optimum line.By analyze existing scheme it is found that the prior art there are a common faults, i.e., be all with ridership greatly sole criterion
Select public bus network, however public bus network and passenger have respective feature, and feature all has space-time dynamic characteristic, it is existing
There is technology not capture and analyze this feature, lead to not advertizing to most appropriate audient, it is wide so as to ensure
The dispensing effect of announcement.
For example, some public bus networks cover more commercial office area, some public bus networks cover more tourist attraction, this two
The psychological condition of passenger audient and passenger when taking pubic transport on kind circuit is different.Therefore, passenger is to inhomogeneity
The susceptibility of type advertisement and repercussion are different.In addition, due in city, the throwing of public transport body advertisement especially is being widely used
In the large- and-medium size cities put, public bus network numerous and complicated, artificial selection launch circuit method efficiency it is low, scalability, can stretch
Contracting and operability are poor, and advertisement delivery effect can not be estimated.
To sum up, the prior art is generally without analysis public bus network, the space-time dynamic characteristic of passenger's feature and passenger's feature,
So as to be difficult that public transport body advertisement is made to play maximum effect.
Invention content
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least partly
State the method and device for obtaining passenger on public transport track of problem.
According to an aspect of the present invention, a kind of method for obtaining passenger on public transport track is provided, including:
Intelligent bus card data SCT is collected, is recorded by bus from the Intelligent bus card extracting data is a plurality of;
Processing analysis is carried out to a plurality of record by bus of extraction, calculates the station logical number of getting on or off the bus of passenger, it is described
Station logical number of getting on or off the bus is corresponded with bus stop;
Station logical number of getting on or off the bus according to passenger determines that passenger by way of Station XXX sequence, multiplies so as to obtain bus
Objective track data.
Optionally, processing analysis is carried out to a plurality of record by bus of extraction, the station logic of getting on or off the bus for calculating passenger is compiled
Number, including:
Each passenger getting on/off Station XXX and corresponding passenger getting on/off time are extracted from a plurality of record by bus;
Based on passenger getting on/off time and the passenger getting on/off Station XXX, the passenger in a plurality of record by bus is calculated
It gets on or off the bus station logical number.
Optionally, processing analysis is carried out to a plurality of record by bus of extraction, the station logic of getting on or off the bus for calculating passenger is compiled
Number, including:
The corresponding record by bus of any bus is obtained from a plurality of record by bus of extraction;
Each passenger getting on/off Station XXX and corresponding passenger getting on/off time are extracted from the record by bus of the bus,
And passenger getting on/off Station XXX is denoted as station charge number;
Based on the passenger getting on/off time and passenger getting on/off station charge number, any bus is calculated
Passenger getting on/off station logical number in recording by bus.
Optionally, based on passenger getting on/off time and passenger getting on/off station charge number, any public transport is calculated
Passenger loading station logical number in the corresponding record by bus of vehicle, including:
It is ranked up according to the different mass transit card ID affiliated passenger loading times, recording by bus after being sorted;
Record by bus after sequence is grouped, by the passenger loading station charge number in the record by bus after sequence
Identical is divided into one group;
Each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is as station charge number pair
The practical station number answered;
Passenger loading time average is calculated for the record by bus in each cluster;
Multiple clusters according to pick-up time average value are ranked up, and remembering by bus in each cluster is determined according to sequence
Passenger loading station logical number in record.
Optionally, based on passenger getting on/off time and passenger getting on/off station charge number, any public transport is calculated
Passenger getting off car station logical number in the corresponding record by bus of vehicle, including:
It is ranked up according to the different mass transit card ID affiliated passenger getting off car times, recording by bus after being sorted;
Record by bus after sequence is grouped, by the passenger getting off car station charge number in the record by bus after sequence
Identical is divided into one group;
Each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is as station charge number pair
The practical station number answered;
Passenger getting off car time average is calculated for the record by bus in each cluster;
Multiple clusters according to time getting off average value are ranked up, and remembering by bus in each cluster is determined according to sequence
Passenger getting off car station logical number in record.
Optionally, passenger is determined by way of Station XXX sequence according to the station logical number of getting on or off the bus of passenger, so as to obtain
Passenger on public transport track data, including:
Passenger is determined by way of Station XXX sequence according to the passenger getting on/off station logical number being calculated, with reference to by bus
Public bus network number in record, passenger getting on/off time obtain passenger on public transport track data.
Optionally, the method further includes:
Collect the public transport for including map datum, bus stop data, public bus network data and user interest point POI data
Vehicle related data;
The track data of the bus related data and passenger is handled, excavates the multidimensional category of each bus stop
Property.
Optionally, the track data of the bus related data and passenger is handled, excavates each bus stop
Multidimensional property, including:
According to the hinge degree for calculating each bus stop in the track data of passenger by way of station sequence, hinge degree is used to measure
Quantity of the bus stop as transfer station;
According to the bus stop data acquisition bus stop geographical location information, based on bus stop geographical location information
And its POI data within the distance to a declared goal of periphery, calculate the function theme distribution of each bus stop;
According to the geographical location information and map datum of the bus stop, determine that the administrative area of each bus stop is incorporated into
Belong to.
Optionally, according to the hinge degree for calculating each bus stop in the track data of passenger by way of station sequence, including:
Sequence of the length more than n is excavated based on the passenger trajectory data, is denoted as target sequence, n is positive integer;
Passenger transportation quantity identical with each sequence in target sequence is counted, and as the weights of corresponding sequence;
Based on the weights of sequence each in target sequence, the sequence comprising identical station is merged, obtains connection mode
Network;
According to connection-mode network, the hinge degree of each bus stop on public bus network is calculated.
Optionally, it based on the POI data within bus stop geographical location information and its periphery distance to a declared goal, calculates each
The function theme distribution of bus stop, including:
Geographical location information in geographical location information and POI data based on bus stop, for each bus
It stands, obtains all POI datas within its periphery distance to a declared goal;
Description information in all POI datas is extracted, and is merged into a document;Document based on merging, makes
The function theme distribution of each bus stop is analyzed with theme distribution model LDA;
The determining function theme for needing to retain, counts the reservation that suits the requirements within the distance to a declared goal of each bus stop periphery
The POI quantity of function theme, so as to obtain the function theme distribution of final each bus stop.
Optionally, the method further includes:
According to the bus stop data acquisition bus stop geographical location information;
According to the bus stop geographical location information, the arbitrary bus stop for being smaller than distance to a declared goal is closed
And and by the POI data merging within the bus stop distance to a declared goal of merging, the POI data after merging merges as corresponding
The POI data at station.
Optionally, according to the bus stop data acquisition bus stop geographical location information, including:
According to the bus stop data, the geographical of bus stop is obtained from preset map API by JavaScript and is sat
Mark latitude and longitude information.
Optionally, the method further includes:
Obtain the bus stop that public bus network and each public bus network in specified region are covered;
It determines that scene is launched in advertisement, advertisement dispensing scene is matched with the multidimensional property of each bus stop, acquisition
The bus stop multidimensional property matched;
Bus stop multidimensional property according to matching chooses at least one public bus network, and conduct in each public bus network
The advertisement dispensing public bus network that scene is launched in the advertisement is recommended.
Optionally, advertisement dispensing scene with the multidimensional property of each bus stop is matched, obtains matched bus
It stands multidimensional property, including:
If it is wide-scale distribution scene that scene is launched in advertisement, according to wide-scale distribution scene from each bus stop multidimensional property
The multidimensional property allotted is the hinge degree of each bus stop;
If it is orientating function subject scenes that scene is launched in advertisement, according to orientating function subject scenes from each bus stop multidimensional
The multidimensional property matched in attribute is the function theme distribution of each bus stop;
If advertisement launches scene as orientation administrative region scene, according to orientation administrative region scene from each bus stop multidimensional
The multidimensional property matched in attribute is the administrative division ownership of each bus stop.
Another aspect according to the present invention additionally provides a kind of device for obtaining passenger on public transport track, including:
Collection module, it is a plurality of by bus from the Intelligent bus card extracting data suitable for collecting Intelligent bus card data SCT
Record;
Computing module carries out processing analysis suitable for a plurality of record by bus to extraction, calculates the station of getting on or off the bus of passenger
Logical number, the station logical number of getting on or off the bus are corresponded with bus stop;
Determining module, suitable for determining passenger by way of Station XXX sequence according to the station logical number of getting on or off the bus of passenger, from
And obtain passenger on public transport track data.
Optionally, the computing module is further adapted for:
Each passenger getting on/off Station XXX and corresponding passenger getting on/off time are extracted from a plurality of record by bus;
Based on passenger getting on/off time and the passenger getting on/off Station XXX, the passenger in a plurality of record by bus is calculated
It gets on or off the bus station logical number.
Optionally, the computing module is further adapted for:
The corresponding record by bus of any bus is obtained from the record by bus of extraction;
Each passenger getting on/off Station XXX and corresponding passenger getting on/off time are extracted from the record by bus of the bus,
And passenger getting on/off Station XXX is denoted as station charge number;
Based on the passenger getting on/off time and passenger getting on/off station charge number, any bus pair is calculated
Passenger getting on/off station logical number in the record by bus answered.
Optionally, the computing module is further adapted for:
It is ranked up according to the different mass transit card ID affiliated passenger loading times, recording by bus after being sorted;
Record by bus after sequence is grouped, by the passenger loading station charge number in the record by bus after sequence
Identical is divided into one group;
Each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is as station charge number pair
The practical station number answered;
Passenger loading time average is calculated for the record by bus in each cluster;
Multiple clusters according to pick-up time average value are ranked up, and remembering by bus in each cluster is determined according to sequence
Passenger loading station logical number in record.
Optionally, the computing module is further adapted for:
It is ranked up according to the different mass transit card ID affiliated passenger getting off car times, recording by bus after being sorted;
Record by bus after sequence is grouped, by the passenger getting off car station charge number in the record by bus after sequence
Identical is divided into one group;
Each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is as station charge number pair
The practical station number answered;
Passenger getting off car time average is calculated for the record by bus in each cluster;
Multiple clusters according to time getting off average value are ranked up, and determine to record by bus in each cluster according to sequence
Passenger getting off car station logical number.
Optionally, the determining module is further adapted for:
Passenger is determined by way of Station XXX sequence according to the passenger getting on/off station logical number being calculated, with reference to by bus
Public bus network number in record, passenger getting on/off time obtain passenger on public transport track data.
Optionally, described device further includes excavation module, is suitable for:
Collect the public transport for including map datum, bus stop data, public bus network data and user interest point POI data
Vehicle related data;
The track data of the bus related data and passenger is handled, excavates the multidimensional category of each bus stop
Property.
Optionally, the excavation module is further adapted for:
According to the hinge degree for calculating each bus stop in the track data of passenger by way of station sequence, hinge degree is used to measure
Quantity of the bus stop as transfer station;
According to the bus stop data acquisition bus stop geographical location information, based on bus stop geographical location information
And its POI data within the distance to a declared goal of periphery, calculate the function theme distribution of each bus stop;
According to the geographical location information and map datum of the bus stop, determine that the administrative area of each bus stop is incorporated into
Belong to.
Optionally, the excavation module is further adapted for:
Sequence of the length more than n is excavated based on the passenger trajectory data, is denoted as target sequence, n is positive integer;
Passenger transportation quantity identical with each sequence in target sequence is counted, and as the weights of corresponding sequence;
Based on the weights of sequence each in target sequence, the sequence comprising identical station is merged, obtains connection mode
Network;
According to connection-mode network, the hinge degree of each bus stop on public bus network is calculated.
Optionally, the excavation module is further adapted for:
Geographical location information in geographical location information and POI data based on bus stop, for each bus
It stands, obtains all POI datas within its periphery distance to a declared goal;
Description information in all POI datas is extracted, and is merged into a document;Document based on merging, makes
The function theme distribution of each bus stop is analyzed with theme distribution model LDA;
The determining function theme for needing to retain, counts the reservation that suits the requirements within the distance to a declared goal of each bus stop periphery
The POI quantity of function theme, so as to obtain the function theme distribution of final each bus stop.
Optionally, described device further includes merging module, is suitable for:
According to the bus stop data acquisition bus stop geographical location information;
According to the bus stop geographical location information, the arbitrary bus stop for being smaller than distance to a declared goal is closed
And and by the POI data merging within the bus stop distance to a declared goal of merging, the POI data after merging merges as corresponding
The POI data at station.
Optionally, according to the bus stop data acquisition bus stop geographical location information, including:
According to the bus stop data, the geographical of bus stop is obtained from preset map API by JavaScript and is sat
Mark latitude and longitude information.
Optionally, described device further includes recommending module, is suitable for:
Obtain the bus stop that public bus network and each public bus network in specified region are covered;
It determines that scene is launched in advertisement, advertisement dispensing scene is matched with the multidimensional property of each bus stop, acquisition
The bus stop multidimensional property matched;
Bus stop multidimensional property according to matching chooses at least one public bus network, and conduct in each public bus network
The advertisement dispensing public bus network that scene is launched in the advertisement is recommended.
Optionally, the recommending module is further adapted for:
If it is wide-scale distribution scene that scene is launched in advertisement, according to wide-scale distribution scene from each bus stop multidimensional property
The multidimensional property allotted is the hinge degree of each bus stop;
If it is orientating function subject scenes that scene is launched in advertisement, according to orientating function subject scenes from each bus stop multidimensional
The multidimensional property matched in attribute is the function theme distribution of each bus stop;
If advertisement launches scene as orientation administrative region scene, according to orientation administrative region scene from each bus stop multidimensional
The multidimensional property matched in attribute is the administrative division ownership of each bus stop.
Another aspect according to the present invention, additionally provides a kind of electronic equipment, including:
Processor;And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the place when executed
The method for managing the acquisition passenger on public transport track that device is performed according to any embodiment above.
Another aspect according to the present invention additionally provides a kind of computer storage media, wherein, the computer can
The one or more programs of storage medium storage are read, one or more of programs are when the electronic equipment for being included multiple application programs
During execution so that the electronic equipment performs the method for obtaining passenger on public transport track according to any embodiment above.
In embodiments of the present invention, first, collection Intelligent bus card data SCT is more from Intelligent bus card extracting data
Item records by bus.Then, processing analysis is carried out to a plurality of record by bus of extraction, the station logic of getting on or off the bus for calculating passenger is compiled
Number, station logical number of getting on or off the bus is corresponded with bus stop.Finally, it is determined according to the station logical number of getting on or off the bus of passenger
Passenger is by way of Station XXX sequence, so as to obtain passenger on public transport track data.It is held due to including in Intelligent bus card data
The record that card person takes bus includes a large amount of passenger's riding information.It therefore, can by collecting Intelligent bus card data
Easily to get the big data information that related passenger rides.Also, it is further calculated using Intelligent bus card data
To the passenger trajectory data of a large amount of passengers, additionally aid and in depth understand passenger and take pubic transport the custom of route, and excavate and start a work shift
Space-time mobility, the information such as the volume of the flow of passengers of visitor.Further, the embodiment of the present invention is by analyzing the track data of passenger, so as to
Advertising bus can be reasonably launched on suitable public bus network, so that maximum dispensing effect has been given play in the advertisement launched.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific embodiment for lifting the present invention.
According to the accompanying drawings to the detailed description of the specific embodiment of the invention, those skilled in the art will be brighter
The above and other objects, advantages and features of the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows the flow diagram of the method for acquisition passenger on public transport track according to an embodiment of the invention;
Fig. 2 shows each Station XXX schematic diagrames of Beijing No. 510 bus according to an embodiment of the invention;
Fig. 3 shows that Ads on Vehicles public bus network according to an embodiment of the invention recommends the flow diagram of method;
Fig. 4 shows the structure diagram of the device of acquisition passenger on public transport track according to an embodiment of the invention;
Fig. 5 shows the structural representation of the device of acquisition passenger on public transport track in accordance with another embodiment of the present invention
Figure;
Fig. 6 show for perform acquisition passenger on public transport track according to the present invention method computing device frame
Figure;And
Fig. 7 shows to keep or carry the journey for realizing the method according to the present invention for obtaining passenger on public transport track
The storage unit of sequence code.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
In order to solve the above technical problems, an embodiment of the present invention provides a kind of methods for obtaining passenger on public transport track.Fig. 1
Show the flow diagram of the method for acquisition passenger on public transport track according to an embodiment of the invention.Referring to Fig. 1, the party
Method includes at least step S102 to step S106.
Step S102 collects Intelligent bus card data (SCT, Smart Card Transaction), from Intelligent bus card
Extracting data is a plurality of to be recorded by bus.
In the step, Intelligent bus card data are the record that card holder takes bus.One record includes card holder one
It is secondary by bus record, specifically can include mass transit card ID, public transport Card Type, record be inserted into the time, public bus network ID, bus ID,
Passenger loading time, passenger getting off car time, passenger loading station ID, passenger getting off car station ID etc..
Step S104 carries out processing analysis to a plurality of record by bus of extraction, calculates the station logic of getting on or off the bus of passenger
Number, station logical number of getting on or off the bus are corresponded with bus stop.
In the step, since Station XXX of (getting on the bus and get off) in the prior art, in Intelligent bus card data is station
Charge number.Therefore there are problems that multiple stations share same number.This can lead to not each station of Accurate Analysis
The problem of volume of the flow of passengers and hinge are spent, it is therefore desirable to which the charge number at station is mapped as practical logical number.Will have hereinafter
How body introduction, which numbers the charge at station, is mapped as practical logical number.
Step S106, the station logical number of getting on or off the bus according to passenger determines passenger by way of Station XXX sequence, so as to obtain
To passenger on public transport track data.
In this step, public bus network can be included in the passenger on public transport track data obtained to number, above and below passenger
Vehicle time, passenger are by way of Station XXX sequence etc..
The big data information that can easily get related passenger by collecting Intelligent bus card data and ride.Also,
The passenger trajectory data of a large amount of passengers is further calculated using Intelligent bus card data, additionally aids in depth understanding and multiplies
Visitor takes pubic transport the custom of route, and excavates the information such as the space-time mobility of passenger, the volume of the flow of passengers.Further, the present invention is real
Example is applied by analyzing the track data of passenger, so as to reasonably launch advertising bus on suitable public bus network, so that
Maximum dispensing effect has been given play in the advertisement of dispensing.
Step S104 is seen above, in an embodiment of the present invention, processing analysis is carried out to a plurality of record by bus of extraction,
Calculate passenger get on or off the bus station logical number when, specifically can first from it is a plurality of by bus record in extract each passenger getting on/off vehicle
Number of standing and corresponding passenger getting on/off time, then, based on passenger getting on/off time and passenger getting on/off Station XXX, meter
Calculate the passenger getting on/off station logical number in a plurality of record by bus.Passenger getting on/off Station XXX described herein is actually
The charge number at bus station.
Below by taking a plurality of record by bus of same public transport as an example, the calculating process of analysis bus station logical number.
First, from record by bus a plurality of based on Intelligent bus card extracting data, it is corresponding to obtain any one bus
It records by bus.For example, with reference to Fig. 2, obtain a plurality of of Beijing's No. 510 bus and record by bus.
Then, each passenger getting on/off Station XXX and corresponding passenger getting on/off are extracted from the record by bus of the bus
Time, and passenger getting on/off Station XXX is denoted as station charge number.
For example, extract different passengers from No. 510 buses, such as passenger A, passenger B, passenger C, passenger D, passenger E, passenger F,
Its corresponding Station XXX difference 1 of getting on the bus (practical corresponding " Shuan Quan forts east "), 4 (practical corresponding " subway woods extraction bridge stations "), 4
(practical corresponding " capital garden north gate "), 5 (reality is corresponding " Australia woods spring cells "), 5 (practical corresponding " Lin Cui crossings north "), 5 are (in fact
Border corresponds in " Lin Cui crossings north "), corresponding pick-up time is respectively 7:55,8:00,8:10,8:30,8:20,8:22.
And then based on passenger getting on/off time and passenger getting on/off station charge number, calculate multiplying for any bus
Passenger getting on/off station logical number in vehicle record.
For calculating passenger loading station logical number, specific calculating process is, according to belonging to different mass transit card ID
The passenger loading time is ranked up, recording by bus after being sorted.In the embodiment, it is recorded as multiplying by bus after being sorted
Objective A records, passenger B records, passenger C records, passenger E records, passenger F records, passenger D records.
Next, the record by bus after sequence is grouped, by the passenger loading station in the record by bus after sequence
Charge, which is numbered, identical is divided into one group.For example, it is first group that passenger A, which is divided, C points of passenger B and passenger are second group, passenger D, are multiplied
F points of objective E and passenger are third group.
Then, each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is charged as station
Number corresponding practical station number.In the step, K-Means algorithms may be used, each group of Intelligent bus card data are carried out
Cluster.Certainly other clustering algorithms can also be used, the embodiment of the present invention is not specifically limited this.
For example, after the corresponding Intelligent bus card data clusters of first group of passenger, obtained cluster number is 1.
After the corresponding Intelligent bus card data clusters of second group of passenger, obtained cluster number is 2.
After the corresponding Intelligent bus card data clusters of third group passenger, since passenger E and the corresponding pick-up times of passenger F are non-
It is often close, and the corresponding Station XXX of getting on the bus of the two is all 5, it is believed that therefore vehicle of two people on same station, is calculated
Cluster number for 2, i.e. passenger D is a cluster, passenger E and passenger F for a cluster.
Finally, in each cluster by bus record calculate passenger loading time average, and by it is multiple cluster according to
Pick-up time average value is ranked up, and according to the logic volume in passenger loading station in recording of riding in the determining each cluster of sequence
Number.
In first group of each cluster, passenger loading time average is 7:55.
In second group of 2 clusters, passenger loading time average is respectively 8:00,8:10.
In 2 clusters of third group, passenger loading time average is respectively 8:30,8:21.
After multiple clusters are ranked up according to pick-up time average value, the obtained time is respectively 7:55、8:00、8:
10、8:21、8:30 (each time, corresponding station logical number was 1,2,3,4,5, and the logical number is unique).Thus, it is possible to
To passenger A, passenger B, passenger C, passenger D, passenger E, passenger F, corresponding station logical number of getting on the bus is respectively 1,2,3,5,4,
4.That is, the station of each passenger loading is respectively " Shuan Quan forts east ", " subway woods extraction bridge station ", " capital garden north gate ", " Australia woods spring is small
Area " " Lin Cui crossings north " and " Lin Cui crossings north ".
Above-described embodiment is only schematical, which does not cover all vehicles of Beijing's No. 510 bus
It stands.The embodiment does not cause the embodiment of the present invention any restriction.
Similarly, the mode of passenger loading station logical number is calculated according to foregoing embodiments, passenger can also be calculated
Alighting stop's logical number.Specifically, it first, is ranked up, is arranged according to the different mass transit card ID affiliated passenger getting off car times
Recording by bus after sequence.Then, the record by bus after sequence is grouped, by the passenger getting off car in the record by bus after sequence
Station charge, which is numbered, identical is divided into one group.Then, each group is recorded by bus and is clustered using clustering algorithm, what is obtained is poly-
Class number numbers corresponding practical station number as station charge.Finally, it calculates and multiplies for the record by bus in each cluster
Objective time getting off average value, and multiple clusters are ranked up according to time getting off average value, and each gather is determined according to sequence
Passenger getting off car station logical number in record by bus in class.
Step S106 is seen above, the station logical number of getting on or off the bus according to passenger determines passenger by way of Station XXX sequence
Row, during so as to obtain passenger on public transport track data, can also the passenger getting on/off station logical number that is calculated of foundation it is true
Passenger is determined by way of Station XXX sequence, and then the public bus network combined in record by bus is numbered, the passenger getting on/off time obtains public affairs
Hand over vehicle passenger trajectory data.
It in an embodiment of the present invention, can be with after passenger on public transport track data is obtained according to foregoing embodiments
The multidimensional property of each bus stop is further excavated using the track data of passenger.
In the embodiment, hinge degree, function theme distribution and administrative area that multidimensional property includes each bus stop are incorporated into
Belong to etc..Wherein, hinge degree is for measuring quantity of the bus stop as transfer station, and station bus quantity is more, transfer people
Number is bigger, then hinge degree is bigger, while can also measure the bus stop volume of the flow of passengers.Function theme distribution refers to there is certain spy
The region of point, such as school district, scenic spot, residential quarter.Administrative division ownership refers to administration area, Dongcheng District such as Beijing,
Xicheng District, Haidian District etc..
How lower mask body introduction excavates the multidimensional property of each bus stop.
First, it collects and includes map datum, bus stop data, public bus network data and user interest point POI data
Bus related data.Then, the track data of bus related data and passenger is handled, excavates each bus stop
Multidimensional property.
When the hinge of each bus stop excavated from bus related data spending, according in the track data of passenger by way of vehicle
Sequence of standing calculates the hinge degree of each bus stop, and hinge degree is used to measure quantity of the bus stop as transfer station.
When the function theme distribution of each bus stop is excavated from bus related data, according to bus stop data acquisition
Bus stop geographical location information, based on the POI data within bus stop geographical location information and its periphery distance to a declared goal, meter
Calculate the function theme distribution of each bus stop.
When the administrative division ownership of each bus stop is excavated from bus related data, according to the geographical position of bus stop
Confidence ceases and map datum, determines the administrative division ownership of each bus stop.
Now respectively to excavating the administration of the hinge degree of each bus stop, the function theme distribution, bus stop of bus stop
The detailed process of zoning ownership is introduced.
The mining process of hinge degree.
The embodiment of the present invention may be used Temproal-IdeaGraph algorithms and excavate bus stop hinge degree attribute, the calculation
Method can be in mining data sequence and each element main body between relational network.Fig. 5 is calculated for Temproal-IdeaGraph
The flow diagram of method, referring to Fig. 5, which may include steps of:
Step 1: sequential mode mining, sequence of the length more than n (n is positive integer) is excavated based on passenger trajectory data,
And the sequence is denoted as target sequence.Passenger transportation quantity identical with each sequence in target sequence is counted, and is used as corresponding sequence
The weights of row.In the embodiment, all sequences set is denoted as P, certain sequence is denoted as p, and the weights of sequence p are denoted as w (p);
Step 2: sequence pattern merges, based on the weights of sequence each in target sequence, by the sequence comprising identical station into
Row merges, and obtains connection-mode network.
Step 3: hinge station is found, according to connection-mode network, the pivot of each bus stop on public bus network is calculated
Knob degree.The calculation formula of hinge degree is as shown in formula 1-1:
The calculating of each parameter in above-mentioned formula 1 is referring to equation below 1-2 to 1-5:
Wherein, in above-mentioned formula, siFor station i, H (si) it is station siHinge degree, LstartiIt is s for starting stationiSequence
Row set, LendiIt is s to terminate stationiArrangement set, Ii→jIt is s for station in facti, termination station be sjSequence.
The mining process of function theme distribution.
First, the geographical location information in the geographical location information based on bus stop and POI data, for each public affairs
Station is handed over, obtains all POI datas within its periphery distance to a declared goal.For example, for each bus stop, its periphery is obtained
All POI datas within 1km distances.Distance to a declared goal can also be other numerical value, and the embodiment of the present invention does not do this specific limit
It is fixed.
Then, the description information in all POI datas is extracted, and is merged into a document;Text based on merging
Shelves analyze the function theme of each bus stop using theme distribution model LDA (Latent Dirichlet Allocation)
Distribution;
Finally, it determines the function theme for needing to retain, counts and suit the requirements within the distance to a declared goal of each bus stop periphery
The POI quantity of the function theme of reservation, so as to obtain the function theme distribution of final each bus stop.It for example, can root
According to advertisement promotion field common sense, removal unrelated subject matter merges similar topic, it is assumed that final reservation private residence, household, is done tourism
10 public room, company, automobile, shopping, education, market, consulate themes.So, to being directed to each reservation theme statistics public transport
Station nearby meets the POI quantity of the theme, so as to obtain the theme distribution of bus stop:Its
In, s is bus stop,For i-th of theme POI quantity of bus stop s, i ∈ 1,2 ..., 10.
The mining process of administrative division ownership.
Relative to the hinge degree of bus stop above and the mining process of function theme distribution, the administrative division of bus stop
The excavation of ownership is relatively simple, you can with directly according to the latitude and longitude coordinates in bus stop geographical location, and by map datum
Determine the administrative division attribute of bus stop.Map datum can be obtained using JavaScript technologies from preset map API
It takes.
In an embodiment of the present invention, since the distance of some bus stops is close, their attribute is under normal circumstances
It is roughly the same, in order in the follow-up process can more convenient multidimensional property by analyzing each bus stop, to close
Advertising bus is reasonably launched on suitable public bus network.Therefore, bus stop closer to the distance can be merged, so as to right
Their attribute merges.
Specific merging mode is, according to bus stop data acquisition bus stop geographical location information.According to bus
It stands geographical location information, the arbitrary bus stop for being smaller than distance to a declared goal (such as 100 meters, 200 meters) is merged, and will
POI data within the bus stop distance to a declared goal of merging merges, and the POI data after merging is as corresponding merging station
POI data.Wherein, distance to a declared goal can be determined according to actual conditions, and the embodiment of the present invention is not specifically limited.
In this embodiment, when obtaining bus stop geographical location information, can be passed through according to bus stop data
JavaScript obtains the geographical coordinate latitude and longitude information of bus stop from preset map API.
Based on the excavation of the above-mentioned multidimensional property to each bus stop, now introduce the multidimensional property that combines each bus stop and
Scene is launched in advertisement, and the method that scene carries out Ads on Vehicles public bus network recommendation is launched to respective advertisement.Referring to Fig. 3, this method
Including at least step S302 to step S306.
Step S302 obtains the bus stop that public bus network and each public bus network in specified region are covered.
In the step, specified region can be given city (such as Beijing, Shijiazhuang City), specified province (such as Hebei
Province, Shandong Province etc.), a certain administrative region (such as Haidian District Beijing, Chaoyang District Beijing) in given city etc., the present invention is right
Specific restriction is not done in specified region.
Step S304 determines that scene is launched in advertisement, and advertisement dispensing scene with the multidimensional property of each bus stop is matched, is obtained
Take matched bus stop multidimensional property.
It also needs first to obtain the multidimensional property of each bus stop obtained by foregoing embodiments before this step.
In the step, the dispensing for being intended to include not differentiating between the dispensing intention, tendency function theme of commercial audience is launched in advertisement
It is intended to, is inclined to dispensing intention of administrative division etc..Advertisement launches scene and includes wide-scale distribution scene, orientating function Emperor Moth & MoCADA
Scape, orientation administrative region scene etc..
Step S306 chooses at least one public transport line according to the bus stop multidimensional property matched in each public bus network
Road, and the advertisement as advertisement dispensing scene is launched public bus network and is recommended.
Step S304 is seen above, in an embodiment of the present invention, can be launched and be intended to according to the advertisement of advertisement putting person
It determines that scene is launched in advertisement, is intended to determine that advertisement launches scene and is situated between to how to be launched according to the advertisement of advertisement putting person below
It continues.
Wide-scale distribution scene, it is ensured that public bus network scheme covers widest passenger transportation, i.e. commercial audience is most.
For example, the advertisement launched is travel resort advertisement, this series advertisements does not differentiate between audient, and the wider spread scope the better, therefore chooses
Wide-scale distribution scene.As a result, when advertisement, which is launched, to be intended to not differentiate between commercial audience, it may be determined that advertisement launches scene to pass extensively
Broadcast scene.
Orientating function subject scenes, the advertisement suitable for dispensing have apparent theme to be inclined to, can be directed to corresponding audient
It is propagated, so as to greatly promote the effect of advertisement and cost performance.For example, recruitment website advertisement, should launch more by quotient
On the public bus network of industry and Office Area.As a result, when advertisement, which is launched, to be intended to have function subject attribute, determine that scene is launched in advertisement
For orientating function subject scenes.
Administrative region scene is oriented, the advertisement suitable for dispensing has apparent administrative region to be inclined to, and needs just for correlation
The audient in region is propagated.For example, the market advertisement in core city, should focus on to launch the public affairs in core city (rather than suburb)
Intersection road.As a result, when advertisement, which is launched, to be intended to have administrative division attribute, determine that advertisement launches scene as orientation administrative region
Scene.
Based on the introduction for launching scene to advertisement above, now advertisement is launched the multidimensional property of scene and each bus stop into
Row matching, the process of bus stop multidimensional property matched are introduced.
Specifically, it is wide-scale distribution scene that if scene is launched in advertisement, according to wide-scale distribution scene from each bus stop multidimensional
The multidimensional property matched in attribute is the hinge degree of each bus stop.If it is orientating function subject scenes that scene is launched in advertisement,
The multidimensional property matched is the function theme distribution of each bus stop.If advertisement launches scene as orientation administrative region scene,
The multidimensional property matched belongs to for the administrative division of each bus stop.
Step S306 is seen above, the bus stop multidimensional property matched is different, and public transport is chosen in each public bus network
The foundation of circuit is different, so as to which the public bus network recommended is also different.Now to according to the different multidimensional properties of bus stop in each public affairs
At least one public bus network is chosen in intersection road, and the advertisement as advertisement dispensing scene launches what public bus network was recommended
Process is introduced respectively.
First, with a specific embodiment under wide-scale distribution scene, launching the mistake that public bus network is recommended to advertisement
Journey is specifically introduced.The specified region of the embodiment is Beijing.The embodiment measures the hinge degree of each bus stop, pivot
Knob degree is bigger, and the station volume of the flow of passengers is bigger, and the commercial audience by way of this station is more.This method is named as Hub-KRQ, specific steps
It is as follows:
Step 1-1 has selected public bus network set and has been set as empty, has been denoted as BRresult;The setting of passenger transportation set is covered
For sky, it is denoted as Trajcovered;
Step 1-2 using all public bus networks in Beijing as candidate line set, is denoted as BRcan;
Step 1-3 extracts BR according to public bus network datacanAll bus stops covered, and form candidate station collection
It closes, is denoted as Scan;
Step 1-4 traverses passenger trajectory data, if including S in passenger transportation sequencecanIn arbitrary station, then extraction multiply
Objective track data, and candidate tracks set is formed, it is denoted as Trajcan;
Step 1-5 calculates Traj according to formula 2-1 and 2-2canIn all tracks for BRcanIn all circuits weight w
(traj;br):
w(traj;Br)=∑s∈itsH (s) formula 2-1;Its=Its[traj]∩Irs[br] formula 2-2
Wherein, Irs[br] is that the bus stop of public bus network br coverings is gathered, Its[traj] is the public affairs of track traj coverings
Station set is handed over, its is the public bus network intersection of public bus network br and track traj coverings, and H (s) is bus stop hinge degree;
Step 1-6 traverses BRcanIn all public bus networks, to arbitrary public bus network br, in ScanMiddle its covering of extraction
All bus stop set, are denoted as Sbr, in TrajcanMiddle extraction SbrThe passenger transportation of covering, is denoted as trajbr, to TrajbrMiddle institute
There is passenger transportation to sum circuit weight, obtain the coverage C of public bus network brbr, equation below 2-3:
Wherein, Irs[br] is the bus stop set S for extracting br coveringsbr, Ist[Irs[br]] to extract SbrCovering multiplies
Objective track set Trajbr;
Step 1-7 selects BRcanThe public bus network br of middle coverage maximummax, add it to and chosen public bus network collection
Close BRresult, and from candidate public bus network set BRcanMiddle removal;
Step 1-8 extracts BR according to public bus network datacanAll bus stops covered, and form candidate station collection
It closes, is denoted as Scan;
Step 1-9, by brmaxThe passenger transportation Traj of coveringbrmaxFrom candidate tracks set TrajcanMiddle removal;
Step 1-10 repeats step 1-6 to 1-9, until selecting public bus network set BRresultMiddle public bus network quantity expires
The requirement of sufficient advertisement putting person.Sequencing of the embodiment of the present invention between step each in the above process does not do specific limit
It is fixed.
Then, with a specific embodiment under orientating function subject scenes, launching public bus network to advertisement and recommending
Process be specifically introduced.The specified region of the embodiment is Beijing.It is orientating function theme that if scene is launched in advertisement
Scene, public bus network recommend method to consider theme feature of the passenger transportation by way of terrestrial reference, and this method is named as Topic-KRQ, has
Body step is as follows:
Step 2-1 sets advertising objective function theme, is denoted as set Trajtargrt;
Step 2-2 has selected public bus network set and has been set as empty, has been denoted as BRresult;The setting of passenger transportation set is covered
For sky, it is denoted as Trajcovered;
Step 2-3 using all public bus networks in Beijing as candidate line set, is denoted as BRcan;
Step 2-4 extracts BR according to public bus network datacanAll bus stops covered, and form candidate station collection
It closes, is denoted as Scan;
Step 2-5 calculates S according to equation 3 below -1canIn each bus stop objective function topic weights:
Wherein, TDs[t] is bus stop s and the relevant POI quantity of theme t;
Step 2-6 traverses passenger trajectory data, if including S in passenger transportation sequencecanIn arbitrary bus stop, then carry
Passenger transportation candidate data is taken, and forms candidate tracks set, is denoted as Trajcan;
Step 2-7 calculates Traj according to equation 3 below -2 and 3-3canIn all passenger transportations for BRcanMiddle institute is wired
Weight w (the traj on road;br):
w(traj;Br)=∑s∈itswtarget(s) formula 3-2;
Its=Its[traj]∩Irs[br] formula 3-3;
Wherein, Irs[br] is that the bus stop of public bus network br coverings is gathered, Its[traj] is the public affairs of track traj coverings
Station set is handed over, its is the public bus network intersection of public bus network br and track traj coverings;
Step 2-8 traverses BRcanIn all public bus networks, to arbitrary public bus network br, in ScanThe institute of middle its covering of extraction
There is bus stop set, be denoted as Sbr, in TrajcanMiddle extraction SbrThe passenger transportation of covering, is denoted as Trajbr, to TrajbrIn own
Track sums for circuit weight, obtains the coverage C of public bus network brbr, 3-4 as the following formula:
Wherein Irs[br] is the bus stop set S for extracting br coveringsbr, Ist[Irs[br]] to extract SbrThe passenger of covering
Track set Trajbr;
Step 2-9 selects BRcanThe public bus network br of middle coverage maximummax, add it to and chosen public bus network collection
Close BRresult, and from candidate public bus network and and BRcanMiddle removal;
Step 2-10 extracts BR according to public bus network datacanAll bus stops covered, and form candidate station
Set remembers Scan;
Step 2-11, by brmaxThe passenger transportation Traj of coveringbrmaxFrom candidate tracks set TrajcanMiddle removal;
Step 2-12 repeats 2-6 to 2-11, until selecting public bus network set BRresultMiddle public bus network quantity meets wide
Accuse the requirement of putting person.
Finally, with a specific embodiment in the case where orienting administrative region scene, launching public bus network to advertisement and recommending
Process be specifically introduced.The specified region of the embodiment is Beijing.If advertisement launches scene as orientation administrative region
Scene, public bus network recommend method to consider administrative region feature of the passenger transportation by way of terrestrial reference, and this method is named as District-
KRQ is as follows:
Step 3-1, setting advertising objective administrative region, is denoted as set DTarget;
Step 3-2 has selected public bus network set and has been set as empty, has been denoted as BRresult;The setting of passenger transportation set is covered
For sky, it is denoted as Trajcovered;
Step 3-3 using all public bus networks in Beijing as candidate line set, is denoted as BRcan;
Step 3-4 extracts BR according to public bus network datacanAll bus stops covered, and form candidate station collection
It closes, is denoted as Scan;
Step 3-5 calculates ScanIn each bus stop target administrative region weight, if administrative belonging to bus stop
Region is target administrative region, then weight is 1, and otherwise weight is 0:It is denoted as wTarget(s);
Step 3-6 traverses passenger trajectory data, if including S in passenger transportation sequencecanIn arbitrary bus stop, then carry
Passenger transportation candidate data is taken, and forms candidate tracks set, is denoted as Trajcan;
Step 3-7 calculates Traj according to equation 4 below -1 and 4-2canIn all passenger transportations for BRcanMiddle institute is wired
Weight w (the traj on road;br):
w(traj;Br)=∑s∈itsWtarget(s) formula 4-1;
Its=Its[traj]∩Irs[br] formula 4-2;
Wherein, Irs[br] is that the bus stop of public bus network br coverings is gathered, Its[traj] is the public affairs of track traj coverings
Station set is handed over, its is the public bus network intersection of public bus network br and track traj coverings;
Step 3-8 traverses BRcanIn all public bus networks, to arbitrary public bus network br, in ScanThe institute of middle its covering of extraction
There is bus stop set, be denoted as Sbr, in TrajcanMiddle extraction SbrThe passenger transportation of covering, is denoted as Trajbr, to TrajbrIn own
Track sums for circuit weight, obtains the coverage C of public bus network brbr, equation below 4-3:
Wherein, Irs[br] is the bus stop set S for extracting br coveringsbr, Ist[Irs[br]] to extract SbrCovering multiplies
Objective track set Trajbr;
Step 3-9 selects BRcanThe public bus network br of middle coverage maximummax, add it to and chosen public bus network collection
Close BRresult, and from candidate public bus network and and BRcanMiddle removal;
Step 3-10 extracts BR according to public bus network datacanAll bus stops covered, and form candidate station
Set, is denoted as Scan;
Step 3-11, by brmaxThe passenger transportation Traj of coveringbrmaxFrom candidate tracks set TrajcanMiddle removal;
Step 3-12 repeats 3-6 to 3-11, until selecting public bus network set BRresultMiddle public bus network quantity meets wide
Accuse the requirement of putting person.
Certainly, no matter for any advertisement dispensing scene, in the multidimensional property according to bus stop in each public bus network
It is middle selection at least one public bus network when, it is also necessary to consider the dispensing demand of advertisement putting person, as release time range (specific to
Hour), public bus network quantity (such as 2-3 circuit, 4 circuits), public bus network length range (such as 5000m, 3000 meters)
With public bus network volume of the flow of passengers range etc., so as to combine dispensing demand in the multidimensional property according to bus stop in each public bus network
At least one public bus network of middle selection, and the advertisement as advertisement dispensing scene is launched public bus network and is recommended.
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of device for obtaining passenger on public transport track, Fig. 4
Show the structure diagram of the device of acquisition passenger on public transport track according to an embodiment of the invention.Referring to Fig. 4, obtain
The device 400 of passenger on public transport track includes at least collection module 410, computing module 420 and determining module 430.
Now introduce each composition of the device 400 for obtaining passenger on public transport track of the embodiment of the present invention or the function of device with
And the connection relation between each section:
Collection module 410, it is a plurality of by bus from Intelligent bus card extracting data suitable for collecting Intelligent bus card data SCT
Record;
Computing module 420 is coupled with collection module 410, is carried out processing analysis suitable for a plurality of record by bus to extraction, is counted
The station logical number of getting on or off the bus of passenger is calculated, station logical number of getting on or off the bus is corresponded with bus stop;
Determining module 430 is coupled with computing module 420, determines to multiply suitable for the station logical number of getting on or off the bus according to passenger
Visitor is by way of Station XXX sequence, so as to obtain passenger on public transport track data.
In an embodiment of the present invention, computing module 420 is further adapted for, and each passenger getting on/off is extracted from a plurality of record by bus
Station XXX and corresponding passenger getting on/off time, and based on passenger getting on/off time and passenger getting on/off Station XXX, meter
Calculate the passenger getting on/off station logical number in a plurality of record by bus.
In an alternative embodiment of the invention, computing module 420 is further adapted for, and any public transport is obtained from the record by bus of extraction
Vehicle is corresponding to be recorded by bus.And extract each passenger getting on/off Station XXX and corresponding passenger from the record by bus of the bus
It gets on or off the bus the time, and passenger getting on/off Station XXX is denoted as station charge number.Based on passenger getting on/off time and passenger
Station charge of getting on or off the bus is numbered, and calculates the passenger getting on/off station logical number in the corresponding record by bus of any bus.
In an alternative embodiment of the invention, computing module 420 is further adapted for calculating passenger loading station logical number, first,
It is ranked up according to the different mass transit card ID affiliated passenger loading times, recording by bus after being sorted.Secondly, after sequence
Record is grouped by bus, and the passenger loading station charge in recording by bus after sequence is numbered and identical is divided into one group.So
Afterwards, each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is corresponding as station charge number
Practical station number.Finally, passenger loading time average is calculated, and by multiple clusters for the record by bus in each cluster
It is ranked up according to pick-up time average value, and is patrolled according to the passenger loading station in recording of riding in the determining each cluster of sequence
Collect number.
In an alternative embodiment of the invention, computing module 420 is further adapted for calculating passenger getting off car station logical number, first,
It is ranked up according to the different mass transit card ID affiliated passenger getting off car times, recording by bus after being sorted.Secondly, after sequence
Record is grouped by bus, and the passenger getting off car station charge in recording by bus after sequence is numbered and identical is divided into one group.So
Afterwards, each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is corresponding as station charge number
Practical station number.Finally, passenger getting off car time average is calculated, and by multiple clusters for the record by bus in each cluster
It is ranked up according to time getting off average value, and according to the passenger getting off car station logic for record of riding in the determining each cluster of sequence
Number.
In an embodiment of the present invention, determining module 430 is further adapted for, according to the passenger getting on/off station logic being calculated
Number determines passenger by way of Station XXX sequence, with reference to the public bus network in recording by bus is numbered, the passenger getting on/off time obtains
Passenger on public transport track data.
The embodiment of the present invention additionally provides another device for obtaining passenger on public transport track, and Fig. 5 is shown according to this hair
The structure diagram of the device for obtaining passenger on public transport track of another bright embodiment.Referring to Fig. 5, passenger on public transport rail is obtained
The device 400 of mark can also include excavating module 440, merging module 450 and recommend mould other than comprising above-mentioned each module
Block 460.
Module 440 is excavated, is coupled with determining module 430, includes map datum, bus stop data, public transport suitable for collecting
The bus related data of track data and user interest point POI data, and to the track of bus related data and passenger
Data are handled, and excavate the multidimensional property of each bus stop.
Merging module 450 is coupled with excavating module 440, suitable for according to bus stop data acquisition bus stop geography position
Confidence ceases, and according to bus stop geographical location information, and the arbitrary bus stop for being smaller than distance to a declared goal is merged, and
POI data within the bus stop distance to a declared goal of merging is merged, the POI data after merging is as corresponding merging station
POI data.
Recommending module 460 is coupled with excavating module 440, suitable for obtaining public bus network and each public transport line in specified region
The bus stop that road is covered, and determine that scene is launched in advertisement, scene and the multidimensional property of each bus stop are launched into advertisement
Match, obtain matched bus stop multidimensional property.And then according to the bus stop multidimensional property matched in each public bus network
At least one public bus network is chosen, and the advertisement as advertisement dispensing scene is launched public bus network and recommended.
In an embodiment of the present invention, excavate module 440 be further adapted for, according in the track data of passenger by way of station sequence
The hinge degree of each bus stop is calculated, hinge degree is used to measure quantity of the bus stop as transfer station.According to bus stop
Data acquisition bus stop geographical location information, within bus stop geographical location information and its periphery distance to a declared goal
POI data calculates the function theme distribution of each bus stop.According to the geographical location information of bus stop and map number
According to, determine each bus stop administrative division ownership.
In an embodiment of the present invention, it excavates module 440 to be further adapted for, length is excavated more than n based on passenger trajectory data
Sequence, be denoted as target sequence, n is positive integer.Count passenger transportation quantity identical with each sequence in target sequence, and conduct
The weights of corresponding sequence.Based on the weights of sequence each in target sequence, the sequence comprising identical station is merged, is connected
Mode network is connect, and according to connection-mode network, calculates the hinge degree of each bus stop on public bus network.
In an embodiment of the present invention, module 440 is excavated to be further adapted for, geographical location information based on bus stop and
Geographical location information in POI data for each bus stop, obtains all POI datas within its periphery distance to a declared goal,
And the description information in all POI datas is extracted, and be merged into a document.Document based on merging, uses theme
Distributed model LDA analyzes the function theme distribution of each bus stop.The determining function theme for needing to retain, counts each public transport
Suit the requirements within the distance to a declared goal of station periphery reservation function theme POI quantity, so as to obtain final each bus
The function theme distribution stood.
In an embodiment of the present invention, merging module 450 is further adapted for according to bus stop data, by JavaScript from
Preset map API obtains the geographical coordinate latitude and longitude information of bus stop.
In an embodiment of the present invention, recommending module 460 is further adapted for, if advertisement launches scene as wide-scale distribution scene, root
The multidimensional property matched from each bus stop multidimensional property according to wide-scale distribution scene is the hinge degree of each bus stop.If
It is orientating function subject scenes that scene is launched in advertisement, is matched from each bus stop multidimensional property according to orientating function subject scenes
The multidimensional property gone out is the function theme distribution of each bus stop.If advertisement launches scene as orientation administrative region scene, according to
The multidimensional property that orientation administrative region scene is matched from each bus stop multidimensional property is the administrative division of each bus stop
Ownership.
According to the combination of any one above-mentioned preferred embodiment or multiple preferred embodiments, the embodiment of the present invention can reach
Following advantageous effect:
In embodiments of the present invention, first, collection Intelligent bus card data SCT is more from Intelligent bus card extracting data
Item records by bus.Then, processing analysis is carried out to a plurality of record by bus of extraction, the station logic of getting on or off the bus for calculating passenger is compiled
Number, station logical number of getting on or off the bus is corresponded with bus stop.Finally, it is determined according to the station logical number of getting on or off the bus of passenger
Passenger is by way of Station XXX sequence, so as to obtain passenger on public transport track data.It is held due to including in Intelligent bus card data
The record that card person takes bus includes a large amount of passenger's riding information.It therefore, can by collecting Intelligent bus card data
Easily to get the big data information that related passenger rides.Also, it is further calculated using Intelligent bus card data
To the passenger trajectory data of a large amount of passengers, additionally aid and in depth understand passenger and take pubic transport the custom of route, and excavate and start a work shift
Space-time mobility, the information such as the volume of the flow of passengers of visitor.Further, the embodiment of the present invention is by analyzing the track data of passenger, so as to
Advertising bus can be reasonably launched on suitable public bus network, so that maximum dispensing effect has been given play in the advertisement launched.
In the specification provided in this place, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:I.e. required guarantor
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Profit requirement, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of arbitrary
It mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization or to be run on one or more processor
Software module realize or realized with combination thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize the dress for obtaining passenger on public transport track according to embodiments of the present invention
The some or all functions of some or all components in putting.The present invention is also implemented as described here for performing
Some or all equipment of method or program of device (for example, computer program and computer program product).This
The program of the realization present invention of sample can may be stored on the computer-readable medium or can have one or more signal
Form.Such signal can be downloaded from internet website to be obtained either providing or with any other on carrier signal
Form provides.
The embodiment of the present invention additionally provides a kind of electronic equipment, including processor and be arranged to storage computer can
The memory of execute instruction, executable instruction make processor perform the acquisition public affairs according to any one embodiment above when executed
The method for handing over vehicle passenger transportation.
The embodiment of the present invention additionally provides a kind of computer storage media, wherein, computer-readable recording medium storage one
A or multiple programs, one or more programs by the electronic equipment including multiple application programs when being performed so that electronic equipment
Perform the method for obtaining passenger on public transport track of any embodiment above.
For example, Fig. 6 shows the computing device that can realize the method for obtaining passenger on public transport track.The computing device passes
Include the computer program product or computer-readable medium of 620 form of processor 610 and memory on system.Memory 620
Can be that the electronics of such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk or ROM etc is deposited
Reservoir.Memory 620 has storage for performing the memory space of the program code 631 of any method and step in the above method
630.For example, the memory space 630 of storage program code can include being respectively used to realize the various steps in above method
Each program code 631.These program codes can read or be written from one or more computer program product
Into this one or more computer program product.These computer program products include such as hard disk, and compact-disc (CD) is deposited
The program code carrier of card storage or floppy disk etc.Such computer program product is usually for example shown in Fig. 7 portable
Or static memory cell.The storage unit can have the storage with 620 similar arrangement of memory in the computing device of Fig. 6
Section, memory space etc..Program code can for example be compressed in a suitable form.In general, storage unit includes performing sheet
The computer-readable code 631 ' of the method and step of invention, you can with the code read by such as 610 etc processor, when this
When a little codes are run by computing device, the computing device is caused to perform each step in method described above.
It should be noted that the present invention will be described rather than limits the invention, and ability for above-described embodiment
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and run after fame
Claim.
So far, although those skilled in the art will appreciate that detailed herein have shown and described multiple showing for the present invention
Example property embodiment, still, without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or derive many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (10)
1. a kind of method for obtaining passenger on public transport track, including:
Intelligent bus card data SCT is collected, is recorded by bus from the Intelligent bus card extracting data is a plurality of;
Processing analysis is carried out to a plurality of record by bus of extraction, calculates the station logical number of getting on or off the bus of passenger, it is described upper and lower
Vehicle station logical number is corresponded with bus stop;
Station logical number of getting on or off the bus according to passenger determines passenger by way of Station XXX sequence, so as to obtain passenger on public transport rail
Mark data.
2. according to the method described in claim 1, wherein, processing analysis is carried out to a plurality of record by bus of extraction, calculating is started a work shift
The station logical number of getting on or off the bus of visitor, including:
Each passenger getting on/off Station XXX and corresponding passenger getting on/off time are extracted from a plurality of record by bus;
Based on passenger getting on/off time and the passenger getting on/off Station XXX, calculate above and below the passenger in a plurality of record by bus
Vehicle station logical number.
3. method according to claim 1 or 2, wherein, processing analysis is carried out to a plurality of record by bus of extraction, is calculated
The station logical number of getting on or off the bus of passenger, including:
The corresponding record by bus of any bus is obtained from a plurality of record by bus of extraction;
It is extracted each passenger getting on/off Station XXX and corresponding passenger getting on/off time, and will from the record by bus of the bus
Passenger getting on/off Station XXX is denoted as station charge number;
Based on the passenger getting on/off time and passenger getting on/off station charge number, riding for any bus is calculated
Passenger getting on/off station logical number in record.
4. according to claim 1-3 any one of them methods, wherein, based on passenger getting on/off time and passenger getting on/off vehicle
Charge of standing is numbered, and calculates the passenger loading station logical number in the corresponding record by bus of any bus, including:
It is ranked up according to the different mass transit card ID affiliated passenger loading times, recording by bus after being sorted;
Record by bus after sequence is grouped, the passenger loading station charge number in the record by bus after sequence is identical
Be divided into one group;
Each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is corresponding as station charge number
Practical station number;
Passenger loading time average is calculated for the record by bus in each cluster;
Multiple clusters are ranked up according to pick-up time average value, and according in the record by bus in determining each to cluster that sorts
Passenger loading station logical number.
5. according to claim 1-4 any one of them methods, wherein, based on passenger getting on/off time and passenger getting on/off vehicle
Charge of standing is numbered, and calculates the passenger getting off car station logical number in the corresponding record by bus of any bus, including:
It is ranked up according to the different mass transit card ID affiliated passenger getting off car times, recording by bus after being sorted;
Record by bus after sequence is grouped, the passenger getting off car station charge number in the record by bus after sequence is identical
Be divided into one group;
Each group is recorded by bus and is clustered using clustering algorithm, obtained cluster number is corresponding as station charge number
Practical station number;
Passenger getting off car time average is calculated for the record by bus in each cluster;
Multiple clusters are ranked up according to time getting off average value, and according in the record by bus in determining each to cluster that sorts
Passenger getting off car station logical number.
6. according to claim 1-5 any one of them methods, wherein, the station logical number of getting on or off the bus according to passenger determines to multiply
Visitor is by way of Station XXX sequence, so as to obtain passenger on public transport track data, including:
Passenger is determined by way of Station XXX sequence according to the passenger getting on/off station logical number being calculated, with reference to record by bus
In public bus network number, the passenger getting on/off time obtain passenger on public transport track data.
7. according to claim 1-6 any one of them methods, wherein, it further includes:
Collect the bus phase for including map datum, bus stop data, public bus network data and user interest point POI data
Close data;
The track data of the bus related data and passenger is handled, excavates the multidimensional property of each bus stop.
8. a kind of device for obtaining passenger on public transport track, including:
Collection module suitable for collecting Intelligent bus card data SCT, is remembered by bus from the Intelligent bus card extracting data is a plurality of
Record;
Computing module carries out processing analysis suitable for a plurality of record by bus to extraction, calculates the station logic of getting on or off the bus of passenger
Number, the station logical number of getting on or off the bus are corresponded with bus stop;
Determining module, suitable for determining passenger by way of Station XXX sequence according to the station logical number of getting on or off the bus of passenger, so as to obtain
To passenger on public transport track data.
9. a kind of electronic equipment, including:
Processor;And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the processor when executed
Perform the method that passenger on public transport track is obtained according to claim 1-7 any one of them.
10. a kind of computer storage media, wherein, the computer-readable recording medium storage one or more program is described
One or more programs by the electronic equipment including multiple application programs when being performed so that the electronic equipment is performed according to power
Profit requires the method that 1-7 any one of them obtains passenger on public transport track.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711311511.5A CN108171970A (en) | 2017-12-11 | 2017-12-11 | A kind of method and device for obtaining passenger on public transport track |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711311511.5A CN108171970A (en) | 2017-12-11 | 2017-12-11 | A kind of method and device for obtaining passenger on public transport track |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108171970A true CN108171970A (en) | 2018-06-15 |
Family
ID=62524936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711311511.5A Pending CN108171970A (en) | 2017-12-11 | 2017-12-11 | A kind of method and device for obtaining passenger on public transport track |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108171970A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020666A (en) * | 2019-02-21 | 2019-07-16 | 华南理工大学 | A kind of public transport advertisement placement method and system based on passenger behavior mode |
CN111836202A (en) * | 2020-06-17 | 2020-10-27 | 广州通达汽车电气股份有限公司 | Method and device for carrying out personnel positioning early warning based on public transport vehicle |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140067537A1 (en) * | 2012-08-29 | 2014-03-06 | Te-Sheng Chen | Bus stop board and server for advertising |
CN104134343A (en) * | 2014-06-23 | 2014-11-05 | 上海城市交通设计院有限公司 | Passenger boarding and deboarding time and position obtaining method based on traffic card data |
CN105405292A (en) * | 2015-12-13 | 2016-03-16 | 北京工业大学 | Method for counting time when passenger gets on bus by use of bus double swiping data |
CN105550789A (en) * | 2016-02-19 | 2016-05-04 | 上海果路交通科技有限公司 | Method for predicting bus taking passenger flow |
CN105956885A (en) * | 2016-05-16 | 2016-09-21 | 温州市鹿城区中津先进科技研究院 | Method and device for calculating vehicle advertisement putting pricing reference value |
CN107067707A (en) * | 2017-03-23 | 2017-08-18 | 重庆交通大学 | A kind of bus operation and passenger's trip optimization system |
-
2017
- 2017-12-11 CN CN201711311511.5A patent/CN108171970A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140067537A1 (en) * | 2012-08-29 | 2014-03-06 | Te-Sheng Chen | Bus stop board and server for advertising |
CN104134343A (en) * | 2014-06-23 | 2014-11-05 | 上海城市交通设计院有限公司 | Passenger boarding and deboarding time and position obtaining method based on traffic card data |
CN105405292A (en) * | 2015-12-13 | 2016-03-16 | 北京工业大学 | Method for counting time when passenger gets on bus by use of bus double swiping data |
CN105550789A (en) * | 2016-02-19 | 2016-05-04 | 上海果路交通科技有限公司 | Method for predicting bus taking passenger flow |
CN105956885A (en) * | 2016-05-16 | 2016-09-21 | 温州市鹿城区中津先进科技研究院 | Method and device for calculating vehicle advertisement putting pricing reference value |
CN107067707A (en) * | 2017-03-23 | 2017-08-18 | 重庆交通大学 | A kind of bus operation and passenger's trip optimization system |
Non-Patent Citations (1)
Title |
---|
徐广静: "《郑州市公交车广告传播策略研究》", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020666A (en) * | 2019-02-21 | 2019-07-16 | 华南理工大学 | A kind of public transport advertisement placement method and system based on passenger behavior mode |
CN111836202A (en) * | 2020-06-17 | 2020-10-27 | 广州通达汽车电气股份有限公司 | Method and device for carrying out personnel positioning early warning based on public transport vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhong et al. | Inferring building functions from a probabilistic model using public transportation data | |
CN108053240B (en) | Method and device for generating vehicle-mounted advertisement delivery bus route scheme | |
CN104965920B (en) | Method and apparatus for determining destination address | |
CN105183870B (en) | A kind of urban function region detection method and system using microblogging location information | |
CN108427965A (en) | A kind of hot spot region method for digging based on road network cluster | |
CN104881472B (en) | A kind of travelling route sight spot combined recommendation method based on network data collection | |
CN108876475A (en) | A kind of urban function region recognition methods, server and storage medium based on point of interest acquisition | |
CN109727057A (en) | Candidate locations evaluation system and candidate locations evaluation method | |
CN105335795B (en) | A kind of subway Public Transport Transfer problem automatic diagnosis method based on IC card data | |
CN109101559A (en) | A kind of urban function region recognition methods based on POI and bus card-reading data | |
CN107220308A (en) | POI rational detection method and device, equipment and computer-readable recording medium | |
CN110009379A (en) | A kind of building of site selection model and site selecting method, device and equipment | |
CN105912659A (en) | Map generation method and electronic device | |
CN108154387B (en) | Method and device for evaluating bus body advertisement delivery route scheme | |
CN108182593B (en) | Method and device for customizing bus body advertisement delivery route based on map data | |
CN108182592A (en) | Public bus network multidimensional feature attribute method for digging, device and electronic equipment | |
CN110472999A (en) | Passenger flow pattern analysis method and device based on subway and shared bicycle data | |
CN111866776A (en) | Population measurement and calculation method and device based on mobile phone signaling data | |
CN107133689B (en) | Position marking method | |
CN114297532A (en) | High-definition city functional area identification method and system based on crowd movement track | |
CN108108997B (en) | Method and device for selecting bus route for vehicle-mounted advertisement delivery | |
CN108171970A (en) | A kind of method and device for obtaining passenger on public transport track | |
CN108228593A (en) | Point of interest importance measuring method and device | |
Wu et al. | Modeling shopping center location choice: shopper preference–based competitive location model | |
CN108171534B (en) | Vehicle-mounted advertisement bus route recommendation method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |
|
RJ01 | Rejection of invention patent application after publication |