CN108876033A - A kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion - Google Patents
A kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion Download PDFInfo
- Publication number
- CN108876033A CN108876033A CN201810606910.2A CN201810606910A CN108876033A CN 108876033 A CN108876033 A CN 108876033A CN 201810606910 A CN201810606910 A CN 201810606910A CN 108876033 A CN108876033 A CN 108876033A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- people
- burst point
- flow
- unit time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000004927 fusion Effects 0.000 title claims abstract description 11
- 230000011664 signaling Effects 0.000 claims abstract description 19
- 230000007306 turnover Effects 0.000 claims abstract description 17
- 230000001680 brushing effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims 2
- 229910052742 iron Inorganic materials 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 8
- 241001269238 Data Species 0.000 description 5
- 230000003321 amplification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052763 palladium Inorganic materials 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The passenger flow burst point flow of the people prediction technique based on multisource data fusion that the invention discloses a kind of, including determine passenger flow burst point coverage obtains subway station in the range, bus station, vehicle enter and leave bayonet and shared bicycle parks basic condition a little;Obtain in unit time subway, public transport, four kinds of trip modes of automobile and shared bicycle flow of the people, then increase ratio by obtaining mobile phone signaling in passenger flow burst point coverage and the food and drink place turnover, manpower amount predicted value be modified.The present invention has the value actually promoted.
Description
Technical field
It is excavated the present invention relates to multi-source heterogeneous big data and fusion field, and in particular to a kind of based on multisource data fusion
Passenger flow burst point flow of the people prediction technique.
Background technique
Traditional volume of the flow of passengers acquisition methods are all based on greatly the count mode of the discrepancy number added up in a certain closed area,
Data source is relatively simple, does not utilize and merge well the big data of various travel modals.And the present invention can melt
Close multi-source heterogeneous big data, and most of data are all based on the obtaining mode that can be detected automatically, such as subway gate data,
Bus card-reading data, automobile section detector data etc., meanwhile, the invention also provides the modes of amendment fused data, are filling
Make the volume of the flow of passengers accuracy with higher obtained while dividing using multi-source data.Finally, due to which the method for the present invention is based on
Multisource data fusion also analyzes the share ratio of each derived data (data of various modes of transportation) while obtaining the volume of the flow of passengers
Example, can provide data supporting for the passenger flow estimation under same case, have actual promotional value.
Summary of the invention
In order to overcome shortcoming and deficiency of the existing technology, the present invention provides a kind of passenger flow based on multisource data fusion
Burst point flow of the people prediction technique.
This method combines existing internet information interaction technique, instant messaging, automatic measurement technique and GPS satellite
Location technology, real-time detection and statistics arrive at the flow of the people of passenger flow point using various modes of transportation, and use other related datas
Flow of the people is modified, the statistical work of flow of the people can be greatly simplified, provides support for passenger flow estimation.
The present invention adopts the following technical scheme that:
As shown in Figure 1, a kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion, includes the following steps:
S1 determines passenger flow burst point coverage, and subway station, bus station, the vehicle obtained in the range enters and leaves bayonet and be total to
It enjoys bicycle and parks basic condition a little;
S2 obtains subway gate data in the unit time, calculates and takes the flow of the people that subway arrived at or left passenger flow burst point;
S3 obtains bus station brushing card data in the unit time, calculates and takes the stream of people that passenger flow burst point was arrived at or left in public transport
Amount;
S4 obtains unit time automobile profile data, and calculating takes bus arrival or leaves the flow of the people of passenger flow burst point;
S5 obtains unit time shared bicycle parking data, calculates shared bicycle of riding and arrives at or leave passenger flow burst point
Flow of the people;
S6 determines in passenger flow burst point flow of the people the public transport using subway, the respective institute of four kinds of trip modes of automobile and shared bicycle
The ratio accounted for;
S7 obtains mobile phone signaling and food and drink place turnover growth ratio in passenger flow burst point coverage, predicts manpower amount
Value is modified.
The S1 determines passenger flow burst point coverage, and subway station, bus station, the vehicle obtained in the range enters and leaves bayonet
And shared bicycle parks basic condition a little;
The basic condition of the subway station includes the position of the subway position and export volume, outlet in coverage
And distance of the outlet apart from passenger flow demolition point;
The basic condition of the bus station includes website quantity, distribution situation and each website and visitor in coverage
Flow the distance of demolition point;
The vehicle enters and leaves that the basic condition of bayonet includes discrepancy bayonet dividing condition in coverage and bayonet is
It is no to have wagon detector;
The shared bicycle parking data include that the shared bicycle in coverage parks quantity and the averagely amount of parking.
Subway gate data, calculating take subway and arrive at or leave in the unit time near acquisition passenger flow burst point in the S2
The flow of the people of passenger flow burst point, specially:
S2.1 defines NmFor the number for arriving at passenger flow burst point in the unit time from subway station, MiIt is i-th of subway outlet, n is
Subway station outlet sum;
S2.2 defines NmiFor number outbound from the outlet in the unit time, αiFor a proportionality coefficient, αi·NmiFor this
Export the number that destination in outbound number is passenger flow burst point;
S2.3 defines Nmi' it is the number to enter the station in the unit time from the entrance, αi' it is a proportionality coefficient, αi'·Nmi'
To enter the number that the entrance leaves from passenger flow burst point;
The number N of passenger flow burst point is arrived in the S2.4 unit time from subway stationmIt can be determined by following formula:
The S3 obtains bus station brushing card data in the unit time, and calculating takes public transport and arrives at or leave passenger flow burst point
Flow of the people;Specially:
S3.1 defines NbThe number of passenger flow burst point, B are arrived in unit time from bus stationiFor i-th near passenger flow burst point
Bus station;
S3.2 defines NbiArrival number, β are taken for the bus station in the unit timeiFor a proportionality coefficient, βi·NbiFor
In unit time, the passenger flow quantity of passenger flow burst point is gone in bus station's arrival number;
S3.3 defines Nbi' take public transport for the bus station in the unit time and leave number, βi' it is a proportionality coefficient,
βi'·Nbi' it is to go to the bus station in the unit time from passenger flow burst point and take the passenger flow quantity that public transport is left;
The number N of passenger flow burst point is arrived in the S3.4 unit time from bus stationbIt can be determined by following formula:
The S4 obtains automobile profile data in the unit time, and calculating takes bus arrival or leaves the stream of people of passenger flow burst point
Amount, specially:
S4.1 defines NcThe number of passenger flow burst point, C are arrived in unit timeiIt is entered and left for i-th of vehicle near passenger flow burst point
Bayonet;
S4.2 defines NciVehicle number is reached for the discrepancy bayonet in the unit time;
S4.3 defines Nci'Vehicle number is left for the discrepancy bayonet in the unit time;
It is 1.7 that S4.4, which takes fully loaded rate coefficient, i.e., 1.7 people is averagely taken in each car, then from bus station in the unit time
Arrive at the number N of passenger flow burst pointcIt can be determined by following formula:
It, then can will if S4.5 passenger flow burst point is open rather than closure, the i.e. not no rigid discrepancy bayonet of the point
The above method and formula apply on the section of passenger flow burst point near zone road.
The S5 obtains shared bicycle parking data, calculates the stream of people that shared bicycle of riding arrived at or left passenger flow burst point
Amount, specially:
S5.1 defines NdShared bicycle of riding in unit time arrives at the number of passenger flow burst point, DiNear passenger flow burst point
I-th of shared bicycle parking area;
S5.2 defines NdiQuantity, N are parked for i-th of shared original bicycle of bicycle parking areadi' it is to be somebody's turn to do in the unit time
Shared bicycle parks bicycle a little and parks quantity;
The flow of the people that shared bicycle of riding in the S5.3 unit time goes to passenger flow burst point can be determined by following formula:
Nd=Ndi'-Ndi。
S6 determines in passenger flow burst point flow of the people the public transport using subway, the respective institute of four kinds of trip modes of automobile and shared bicycle
The ratio accounted for, specifically comprises the following steps:
Based on taking subway, take public transport, take car, four kinds of trip modes of bicycle of riding, passenger flow in the unit time
The flow of the people N of burst point can be determined by following formula:
N=Nm+Nb+Nc+Nd。
The S7 obtains mobile phone signaling and food and drink place turnover growth ratio in passenger flow burst point coverage, to manpower amount
Predicted value is modified, specially:
S7.1 is modified using mobile phone signaling data:Near the passenger flow burst point in a certain range of region, daily hand
Machine signaling data should maintain certain level, if DpFor mobile phone signaling average amount usually;Due to certain point visitor in the region
Stream explodes, and is accordingly increased using the number of mobile phone in the area, and mobile phone signaling data is consequently increased, if Dp' it is that passenger flow is sudden and violent
Mobile phone signaling data amount when increasing, the difference D of mobile phone signaling data under two statesp'-DpNumber in the region is substantially described
Increasing degree;
S7.2 is modified using food and drink place business data:Food and drink near the passenger flow burst point in a certain range of region
Place, under normal circumstances, the amount of access of the softwares such as the turnover and public comment in one day, Meituan should maintain certain level,
Since certain point passenger flow explodes in the region, going to the number that these food and drink places are had dinner also is increase accordingly, the area in the case of two kinds
The amount of access difference of the softwares such as the turnover in food and drink place and Meituan describes roughly the increasing degree of number in the region in domain, with
For the turnover, if DmFor the turnover of passenger flow burst point near zone food and drink place usually, Dm' turnover when exploding for passenger flow,
The then difference of the turnoverThe increasing degree ratio of number in the region can be described roughly;
S7.3 is positioned using social APP data:It, can be with since many APP will use the positioning function of mobile phone
Certain is obtained out of location data, and in a few days passenger flow burst point near zone uses the flow of the people of APP positioning function and flow of the people usually
Difference, which substantially describes the increasing degree of the region flow of the people, if DsIt is usually fixed using APP for passenger flow burst point near zone
Stream of people's quantity of bit function, Ds' stream of people's quantity of APP positioning function is used when exploding for passenger flow in the region, then Ds'-DsIt is used to
The increasing degree ratio of the region flow of the people is substantially described;
If after amendment data comparison, flow of the people total amount initial value within the acceptable range, i.e. flow of the people total amount initial value
Roughly the same with the amendment anti-flow of the people total amount pushed away of data, then the value is flow of the people total amount end value;If the value is not receiving model
It in enclosing, then needs to detect or correct again the flow that four kinds of modes obtain, until flow of the people total amount reaches acceptable degree.
The βiAnd βi' by going to passenger flow burst point from the website in historical data or returning to the people of the website from passenger flow burst point
Flow proportion determines.
The αiAnd αi' selected partially by the entrance of passenger flow burst point in historical data and the passenger flow of subway station point-to-point transmission disengaging
It is good to determine.
Beneficial effects of the present invention:
The passenger flow burst point flow of the people prediction technique based on multisource data fusion that the present invention provides a kind of, the method combine
Existing internet information interaction technique, instant messaging, automatic measurement technique and GPS satellite location technology, real-time detection
The flow of the people of passenger flow point is arrived at using various modes of transportation with statistics, and flow of the people is modified using other related datas,
The statistical work of flow of the people can be greatly simplified, provides support for passenger flow estimation.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention.
Specific embodiment
Below with reference to examples and drawings, the present invention is described in further detail, but embodiments of the present invention are not
It is limited to this.
Embodiment 1
In the present embodiment by taking magnificent means of agricultural production gold cultural festival admires the beauty of flowers the odd-numbered day volume of the flow of passengers as an example, this method is specifically described.
Present embodiments provide a kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion.The present embodiment is full
1. the subway station basic condition, bus station's basic condition, vehicle bayonet basic condition on magnificent agriculture periphery, shared bicycle region are basic for foot
Known to situation;2. known to the flow of the people data of various modes (source);3. known to each proportionality coefficient;4. magnificent agriculture near zone mobile phone
Known to the amount of access of the platforms such as signaling data, the food and drink place turnover and Meituan, public comment, APP positioning function usage amount.
The acquisition of S1 flow of the people,
S1.1 subway flow of the people, as shown in table 1 below
1 subway of table flow of the people details out of the station
For A subway, outbound number N in the unit timemA=17325 people, proportionality coefficient αA=0.55;Unit time
The number that inside enters the station NmAThe people of '=1500, proportionality coefficient αA'=0.44;For B subway, outbound number N in the unit timemB=
10530 people, proportionality coefficient αB=0.85;The number that enters the station in unit time NmBThe people of '=1100, proportionality coefficient αB'=0.09;For
C subway, outbound number N in the unit timemC=25052 people, proportionality coefficient αC=0.90;Enter the station number in unit time
NmCThe people of '=9800, proportionality coefficient αC'=0.26;For D subway, outbound number N in the unit timemD=6800 people, ratio
Factor alphaD=0.81;The number that enters the station in unit time NmDThe people of '=723, proportionality coefficient αD'=0.70;
Then according to formulaIt can calculate quick-fried from subway station arrival passenger flow in the unit time
The number of point Hua Nong is 45151 people.
S1.2 public transport flow of the people, as shown in table 2 below:
2 public transport of table flow of the people details out of the station
1. for bus station, arrive at a station number N in the unit timeb1=7936 people, proportionality coefficient β1=0.85;Unit time
Interior number N leaving from stationb1The people of '=4870, proportionality coefficient β1'=0.35;2. for bus station, arrive at a station number N in the unit timeb2=
5895 people, proportionality coefficient β1=0.88;Number N leaving from station in unit timeb2The people of '=3321, proportionality coefficient β1'=0.13;For
3., in the unit time bus station arrives at a station number Nb3=6870 people, proportionality coefficient β1=0.77;Number leaving from station in unit time
Nb3The people of '=3500, proportionality coefficient β3'=0.15;4. for bus station, arrive at a station number N in the unit timeb4=7030 people, than
Example factor beta4=0.75;Number N leaving from station in unit timeb4The people of '=5120, proportionality coefficient β4'=0.09;5. for bus station,
Number of arriving at a station in its unit time Nb5=9870 people, proportionality coefficient β5=0.68;Number N leaving from station in unit timeb5'=6330
People, proportionality coefficient β6'=0.05;6. for bus station, arrive at a station number N in the unit timeb6=7105 people, proportionality coefficient β6=
0.92;Number N leaving from station in unit timeb6The people of '=1050, proportionality coefficient β6'=0.10;
Then according to formulaIt can calculate in the unit time and arrive at passenger flow burst point China from bus station
The number of agriculture is 32200 people.
The flow of the people of S1.3 car, as shown in table 3 below:
3 vehicle detection section vehicles passing in and out number details of table
For section (bayonet) 1, arrival number N in the unit timec1=6800, vehicle number is left in the unit time
Nc1'=1320;For section (bayonet) 2, arrival number N in the unit timec2=7720, vehicle is left in the unit time
Number Nc2'=2500;For section (bayonet) 3, arrival number N in the unit timec3=8220, in the unit time from
Open vehicle number Nc3'=3150;
Then according to formulaIt can calculate in the unit time and take car arrival passenger flow burst point Hua Nong
Number be 15770 people.
The flow of the people that S1.4 shares bicycle is as shown in table 4.
Table 4 shares bicycle and parks details
Quantity N is parked for the original bicycle in region 1d1=25, the bicycle amount of parking N in detection timed1'=750;It is right
In region 2, original bicycle parks quantity Nd2=50, the bicycle amount of parking N in detection timed2'=662;It is original for region 3
Bicycle parks quantity Nd3=61, the bicycle amount of parking N in detection timed3'=878;Number is parked for the original bicycle in region 4
Measure Nd4=70, the bicycle amount of parking N in detection timed4'=628;Quantity N is parked for the original bicycle in region 5d5=35,
The bicycle amount of parking N in detection timed5'=531;Quantity N is parked for the original bicycle in region 6d6=95, in detection time
The bicycle amount of parking Nd6'=881;Quantity N is parked for the original bicycle in region 7d7=42, the bicycle amount of parking in detection time
Nd7'=1109;
Then according to formula Nd=Ndi'-NdiThe people that shared bicycle of riding in the unit time arrives at passenger flow burst point Hua Nong can be calculated
Number is 5052 people.
Based on the flow of the people that above four kinds of modes of transportation calculate, according to formula N=Nm+Nb+Nc+NdIt calculates in the unit time
The flow of the people of passenger flow burst point Hua Nong is 98173 people.The ratio of sharing of each section is:Pm=46%, Pb=33%, Pc=16%, Pd
=5%.
The amendment of S2 flow of the people.
2.1 mobile phone signaling datas
The mobile phone signaling data average value D of magnificent agriculture neighboring area usuallypAbout 50000/day, Zijin cultural festival work as number of days
According to amount Dp' about 145990/day, Dp'-DpAbout 95990/day are substantially consistent with calculated flow of the people.
2.2 food and drink place business datas
Since magnificent agriculture periphery food and drink place is numerous, the present embodiment randomly selects wherein several families, obtains the increasing of its turnover
Width situation, details such as the following table 5:
Table 5
There is upper table can be seen that, several selected food and drink place turnovers be averaged amplification be 188%;Hua Nong fixes people on ordinary days
Flow (i.e. floating population near Hua Nong arrives at Hua Nong without the use of the vehicles) is about 50000 person-times, then the cultural festival same day
Flow of the people amplification is 98173/50000*100%=196%, it can be seen that volume of the flow of passengers amplification is not less than food and drink
2.3 social activity APP location datas
It is about 678000 people/day that magnificent agriculture neighboring area, which usually uses the number of APP mobile phone positioning function, and Zijin cultural festival is worked as
Day, detect that the region using the number of positioning function is about 165400 people/day, increases 97600 person-times with usually compared with, this
Statistics indicate that the passenger flow increment calculated is not less than the increment using positioning function number.
Illustrate that the volume of the flow of passengers confidence level on the calculated magnificent agriculture Zijin cultural festival same day is higher by above data.The data with
And the ratio of sharing of each mode of transportation covered can be used for the passenger flow forecast of next Zijin cultural festival.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by the embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (10)
1. a kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion, which is characterized in that include the following steps:
S1 determines passenger flow burst point coverage, and subway station, bus station, the vehicle obtained in the range enters and leaves bayonet and shared list
Vehicle parks basic condition a little;
S2 obtains subway gate data in the unit time, calculates and takes the flow of the people that subway arrived at or left passenger flow burst point;
S3 obtains bus station brushing card data in the unit time, calculates and takes the flow of the people that passenger flow burst point was arrived at or left in public transport;
S4 obtains unit time automobile profile data, and calculating takes bus arrival or leaves the flow of the people of passenger flow burst point;
S5 obtains unit time shared bicycle parking data, calculates the stream of people that shared bicycle of riding arrived at or left passenger flow burst point
Amount;
S6 determines in passenger flow burst point flow of the people the public transport using subway, four kinds of trip modes of automobile and shared bicycle respectively shared by
Ratio;
S7 obtain passenger flow burst point coverage in mobile phone signaling and the food and drink place turnover increase ratio, to manpower amount predicted value into
Row amendment.
2. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that S1 determines that passenger flow burst point influences
Range obtains subway station in the range, bus station, vehicle enter and leave bayonet and shared bicycle parks basic condition a little;
The basic condition of the subway station include subway position in coverage and export volume, outlet position and go out
Distance of the mouth apart from passenger flow demolition point;
The basic condition of the bus station includes that website quantity, distribution situation and each website in coverage and passenger flow are quick-fried
The distance of fried point;
The basic condition that the vehicle enters and leaves bayonet includes whether discrepancy bayonet dividing condition in coverage and bayonet have
Standby wagon detector;
The shared bicycle parking data include that the shared bicycle in coverage parks quantity and the averagely amount of parking.
3. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that it is quick-fried to obtain passenger flow in the S2
Subway gate data in unit time near point, calculate and take the flow of the people that subway arrived at or left passenger flow burst point, specially:
S2.1 defines NmFor the number for arriving at passenger flow burst point in the unit time from subway station, MiIt is i-th of subway outlet, n is the ground
Iron station outlet sum;
S2.2 defines NmiFor number outbound from the outlet in the unit time, αiFor a proportionality coefficient, αi·NmiFor the outlet
Destination is the number of passenger flow burst point in outbound number;
S2.3 defines Nmi' it is the number to enter the station in the unit time from the entrance, αi' it is a proportionality coefficient, αi'·Nmi' for from
Passenger flow burst point enters the number that the entrance leaves;
The number N of passenger flow burst point is arrived in the S2.4 unit time from subway stationmIt can be determined by following formula:
4. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that the S3 obtains the unit time
Interior bus station brushing card data calculates and takes the flow of the people that passenger flow burst point was arrived at or left in public transport;Specially:
S3.1 defines NbThe number of passenger flow burst point, B are arrived in unit time from bus stationiFor i-th of public transport near passenger flow burst point
It stands;
S3.2 defines NbiArrival number, β are taken for the bus station in the unit timeiFor a proportionality coefficient, βi·NbiFor unit
In time, the passenger flow quantity of passenger flow burst point is gone in bus station's arrival number;
S3.3 defines Nbi' take public transport for the bus station in the unit time and leave number, βi' it is a proportionality coefficient, βi'·
Nbi' it is to go to the bus station in the unit time from passenger flow burst point and take the passenger flow quantity that public transport is left;
The number N of passenger flow burst point is arrived in the S3.4 unit time from bus stationbIt can be determined by following formula:
5. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that the S4 obtains the unit time
Interior automobile profile data, calculating take bus arrival or leave the flow of the people of passenger flow burst point, specially:
S4.1 defines NcThe number of passenger flow burst point, C are arrived in unit timeiFor i-th of vehicle access card near passenger flow burst point
Mouthful;
S4.2 defines NciVehicle number is reached for the discrepancy bayonet in the unit time;
S4.3 defines Nci'Vehicle number is left for the discrepancy bayonet in the unit time;
It is 1.7 that S4.4, which takes fully loaded rate coefficient, i.e., averagely takes 1.7 people in each car, then arrive in the unit time from bus station
The number N of passenger flow burst pointcIt can be determined by following formula:
It, then can will be above-mentioned if S4.5 passenger flow burst point is open rather than closure, the i.e. not no rigid discrepancy bayonet of the point
Method and formula apply on the section of passenger flow burst point near zone road.
6. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that S5 obtains shared bicycle and stops
Data are put, calculate the flow of the people that shared bicycle of riding arrived at or left passenger flow burst point, specially:
S5.1 defines NdShared bicycle of riding in unit time arrives at the number of passenger flow burst point, DiFor i-th near passenger flow burst point
Shared bicycle parking area;
S5.2 defines NdiQuantity, N are parked for i-th of shared original bicycle of bicycle parking areadi' it is that this is shared single in the unit time
Vehicle parks bicycle a little and parks quantity;
The flow of the people that shared bicycle of riding in the S5.3 unit time goes to passenger flow burst point can be determined by following formula:
Nd=Ndi'-Ndi。
7. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that S6 determines the passenger flow burst point stream of people
In amount use subway, public transport, four kinds of trip modes of automobile and shared bicycle respectively shared by ratio, specifically comprise the following steps:
Based on taking subway, take public transport, take car, four kinds of trip modes of bicycle of riding, passenger flow burst point in the unit time
Flow of the people N can be determined by following formula:
N=Nm+Nb+Nc+Nd。
8. passenger flow burst point flow of the people prediction technique according to claim 1, which is characterized in that the S7 obtains passenger flow burst point
Mobile phone signaling and the food and drink place turnover in coverage increase ratio, are modified to manpower amount predicted value, specially:
S7.1 is modified using mobile phone signaling data:Near the passenger flow burst point in a certain range of region, daily mobile phone letter
Enable data that should maintain certain level, if DpFor mobile phone signaling average amount usually;Since certain point passenger flow is sudden and violent in the region
Increase, is accordingly increased using the number of mobile phone in the area, mobile phone signaling data is consequently increased, if Dp' when exploding for passenger flow
Mobile phone signaling data amount, the difference D of mobile phone signaling data under two statesp'-DpThe increase of number in the region is substantially described
Amplitude;
S7.2 is modified using food and drink place business data:Food and drink field near the passenger flow burst point in a certain range of region
Institute, under normal circumstances, the amount of access of the softwares such as the turnover and public comment in one day, Meituan should maintain certain level, by
It explodes in certain point passenger flow in the region, going to the number that these food and drink places are had dinner also increase accordingly, the region in the case of two kinds
The amount of access difference of the softwares such as the turnover in interior food and drink place and Meituan describes roughly the increasing degree of number in the region, with battalion
For industry volume, if DmFor the turnover of passenger flow burst point near zone food and drink place usually, Dm' turnover when exploding for passenger flow, then
The difference of the turnoverThe increasing degree ratio of number in the region can be described roughly;
S7.3 is positioned using social APP data:It, can be from calmly since many APP will use the positioning function of mobile phone
Certain is obtained in the data of position, and in a few days passenger flow burst point near zone uses the flow of the people of APP positioning function and the difference of flow of the people usually
Value, which substantially describes the increasing degree of the region flow of the people, if DsIt is usually positioned using APP for passenger flow burst point near zone
Stream of people's quantity of function, Ds' stream of people's quantity of APP positioning function is used when exploding for passenger flow in the region, then Ds'-DsFor big
Cause the increasing degree ratio of the description region flow of the people;
If with amendment data comparison after, flow of the people total amount initial value within the acceptable range, i.e., flow of the people total amount initial value with repair
The anti-flow of the people total amount pushed away of correction data is roughly the same, then the value is flow of the people total amount end value;If the value is not receiving in range,
It then needs to detect or correct again the flow that four kinds of modes obtain, until flow of the people total amount reaches acceptable degree.
9. passenger flow burst point flow of the people prediction technique according to claim 4, which is characterized in that the βiAnd βi' by history number
Passenger flow burst point is gone to from the website in or is determined from the flow of the people proportion that passenger flow burst point returns to the website.
10. passenger flow burst point flow of the people prediction technique according to claim 3, which is characterized in that the αiAnd αi' by history
The entrance selection preference of passenger flow burst point and the passenger flow of subway station point-to-point transmission disengaging determines in data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810606910.2A CN108876033A (en) | 2018-06-13 | 2018-06-13 | A kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810606910.2A CN108876033A (en) | 2018-06-13 | 2018-06-13 | A kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108876033A true CN108876033A (en) | 2018-11-23 |
Family
ID=64338752
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810606910.2A Pending CN108876033A (en) | 2018-06-13 | 2018-06-13 | A kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108876033A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109561389A (en) * | 2018-12-28 | 2019-04-02 | 海南中智信信息技术有限公司 | A method of based on flow of the people real-time in mobile phone signaling zoning |
CN109947381A (en) * | 2019-02-28 | 2019-06-28 | 佛山星乔电子科技有限公司 | The Multi-line linkage control method and control system of a kind of subway semi-transparent display apparatus group |
CN110472999A (en) * | 2019-07-17 | 2019-11-19 | 深圳市综合交通运行指挥中心 | Passenger flow pattern analysis method and device based on subway and shared bicycle data |
CN110913345A (en) * | 2019-11-15 | 2020-03-24 | 东南大学 | Section passenger flow calculation method based on mobile phone signaling data |
CN117275243A (en) * | 2023-11-22 | 2023-12-22 | 上海随申行智慧交通科技有限公司 | Regional flow control prediction and early warning method based on multi-source traffic trip data and application |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105282523A (en) * | 2015-11-23 | 2016-01-27 | 上海赢谊电子设备有限公司 | Electronic device for estimating passenger flow and application method thereof at bus stop |
CN107180270A (en) * | 2016-03-12 | 2017-09-19 | 上海宏理信息科技有限公司 | Passenger flow forecasting and system |
CN107423742A (en) * | 2016-05-23 | 2017-12-01 | 中兴通讯股份有限公司 | The determination method and device of crowd's flow |
-
2018
- 2018-06-13 CN CN201810606910.2A patent/CN108876033A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105282523A (en) * | 2015-11-23 | 2016-01-27 | 上海赢谊电子设备有限公司 | Electronic device for estimating passenger flow and application method thereof at bus stop |
CN107180270A (en) * | 2016-03-12 | 2017-09-19 | 上海宏理信息科技有限公司 | Passenger flow forecasting and system |
CN107423742A (en) * | 2016-05-23 | 2017-12-01 | 中兴通讯股份有限公司 | The determination method and device of crowd's flow |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109561389A (en) * | 2018-12-28 | 2019-04-02 | 海南中智信信息技术有限公司 | A method of based on flow of the people real-time in mobile phone signaling zoning |
CN109947381A (en) * | 2019-02-28 | 2019-06-28 | 佛山星乔电子科技有限公司 | The Multi-line linkage control method and control system of a kind of subway semi-transparent display apparatus group |
CN109947381B (en) * | 2019-02-28 | 2023-08-25 | 佛山星乔电子科技有限公司 | Multi-line linkage control method and control system for subway semitransparent display device group |
CN110472999A (en) * | 2019-07-17 | 2019-11-19 | 深圳市综合交通运行指挥中心 | Passenger flow pattern analysis method and device based on subway and shared bicycle data |
CN110472999B (en) * | 2019-07-17 | 2024-01-23 | 深圳市综合交通运行指挥中心 | Passenger flow mode analysis method and device based on subway and shared bicycle data |
CN110913345A (en) * | 2019-11-15 | 2020-03-24 | 东南大学 | Section passenger flow calculation method based on mobile phone signaling data |
CN110913345B (en) * | 2019-11-15 | 2021-01-05 | 东南大学 | Section passenger flow calculation method based on mobile phone signaling data |
CN117275243A (en) * | 2023-11-22 | 2023-12-22 | 上海随申行智慧交通科技有限公司 | Regional flow control prediction and early warning method based on multi-source traffic trip data and application |
CN117275243B (en) * | 2023-11-22 | 2024-02-02 | 上海随申行智慧交通科技有限公司 | Regional flow control prediction and early warning method based on multi-source traffic trip data and application |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108876033A (en) | A kind of passenger flow burst point flow of the people prediction technique based on multisource data fusion | |
US11859988B2 (en) | Detecting the number of vehicle passengers | |
CN106504516B (en) | A kind of multi-form bus dynamic dispatching method based on bus station informationization | |
Krizek et al. | Assessing options to enhance bicycle and transit integration | |
CN104217129B (en) | A kind of urban rail road network passenger flow evaluation method | |
US8791838B2 (en) | Parking resource management | |
CN103198565A (en) | Charge and passenger flow information acquisition method for bus IC (integrated circuit) cards | |
CN107844943A (en) | A kind of single-point, across shop take-away allocator and system | |
CN105702035B (en) | A kind of method for complexity of being ridden using history public transport data assessment | |
CN108038637A (en) | Logistic information management system based on cloud platform | |
EP2836792A2 (en) | Parking based route navigation | |
CN103699982A (en) | Logistics distribution control method with soft time windows | |
CN102324128A (en) | Method for predicting OD (Origin-Destination) passenger flow among bus stations on basis of IC (Integrated Circuit)-card record and device | |
Shramenko et al. | The principles of the choice of management decisions based on fuzzy logic for cargo delivery of grain to the seaport | |
CN109598448B (en) | Artificial ski field operation management system and management method | |
CN111324853B (en) | Method and system for calculating passage capacity of channel type high-speed railway | |
CN102324121B (en) | Method for detecting crowdedness degree in bus | |
CN107862493A (en) | A kind of goods stock matching travels on the way the numerical value determination methods of goods nearby | |
CN110009131A (en) | A kind of net about vehicle worksheet processing method considering multifactor impact | |
Pei et al. | Real-time optimal scheduling model for transit system with flexible bus line length | |
Shahbazov | Baku-Tbilisi-Kars Railway to Become Central Asia's Gateway to Europe | |
CN107590694A (en) | A kind of data trade determines method and device | |
CN109242154A (en) | Cargo transport route planning method | |
CN113053156B (en) | Intelligent bus station addressing method based on bus radius method | |
Rahimi et al. | Inventory routing problem for perishable products by considering social issue |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |