CN106779196A - A kind of tourist flow prediction and peak value regulation and control method based on tourism big data - Google Patents
A kind of tourist flow prediction and peak value regulation and control method based on tourism big data Download PDFInfo
- Publication number
- CN106779196A CN106779196A CN201611105518.7A CN201611105518A CN106779196A CN 106779196 A CN106779196 A CN 106779196A CN 201611105518 A CN201611105518 A CN 201611105518A CN 106779196 A CN106779196 A CN 106779196A
- Authority
- CN
- China
- Prior art keywords
- scenic spot
- regulation
- control
- peak value
- visitor
- 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
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The present invention relates to a kind of tourist flow Forecasting Methodology based on tourism big data, including：Collection tourism big data, sets up forecast sample；Passenger flow forecast model is set up, and the parameter in the passenger flow forecast model is asked for based on the forecast sample；The prediction initial value of tourist flow is calculated by passenger flow forecast model；Weather forecast according to scenic spot in prediction day corrects the predicted value of tourist flow.
Description
Technical field
It is more particularly to a kind of based on the tourist flow prediction of tourism big data and peak the present invention relates to big data prediction field
Value regulation and control method.
Background technology
Ended for the end of the year 2015, China's domestic travel number more than 4,100,000,000 person-times, the trillion yuan of the tourist earnings about 4.13, tourist industry
Comprehensive contribution to GDP exceedes education, bank, automobile industry, and accounting is up to 10.51%.Announced according to National Tourism Administration
National Day holiday tour market information in 2016, visitor 5.93 hundred million is received in the whole nation altogether only during golden week on National Day.Tourist market
It is flourishing that requirement higher is proposed to scenic spot and tourist city while promoting travel industry to develop, how to have using data
Effect obtains tourist flow data prediction, it is proactive carry out visitor dredge regulation and control, so as to improve the service quality at scenic spot, carry
Rise the Tourist Experience of visitor.
At present, to solve the above problems, National Tourism Administration has given notice and has required that scenic spot tourist flow is established and improve in various regions
Controlling mechanism.But from the point of view of current tourism development situation in all parts of the country, scenic spot and tourist city still lack perfect trip
Passenger flow forecast and peak value regulatory mechanism.Traditional tourist flow prediction is only started with from ticket sales mostly, and data source is single,
The tourism big data for not making full use of tourism wisdomization to produce, statistics has one-sidedness, and statistical accuracy is not enough.Lack
Effective tourist flow prediction and warning data supporting so that visitor's regulation and control method of scenic spot and tourist city remains in broadcast and carries
Show, traffic control, consumption price regulation and control etc. are in legacy paths, do not make full use of internet means, realizes online and offline
Interaction, carries out the guiding of tourist flow, regulates and controls scenic spot peak value visitor's quantity.
The content of the invention
It is an object of the invention to overcome tourist flow Forecasting Methodology of the prior art to lack data supporting, statistics
The defects such as accuracy deficiency, so as to provide a kind of tourist flow prediction based on tourism big data and peak value regulation and control method.
To achieve these goals, the invention provides a kind of tourist flow Forecasting Methodology based on tourism big data, bag
Include：
Step 101), collection tourism big data, set up forecast sample；Wherein,
The tourism big data includes history passenger flow data y1, social networks heating power data y2, OTA browse data y3, periphery
City visitor's data y4, traffic flow data y5；The prediction model includes the tourism big data in one or more time periods；
Step 102), set up passenger flow forecast model, and the passenger flow forecast model is asked for based on the forecast sample
In parameter；Wherein, the passenger flow forecast model is：
Z therein is passenger flow forecast amount, αkIt is the calculating parameter of correspondence sample data, αkIt is prediction revision constant, e is
Except the random error after influence, ykIt is the data in prediction model；αk、αkIt is the parameter to be asked in the passenger flow forecast model；
Step 103), by step 102) obtained by passenger flow forecast model calculate tourist flow prediction initial value；
Step 104), according to scenic spot prediction day weather forecast correct tourist flow predicted value.
In above-mentioned technical proposal, in described step 102) in, institute is asked for using the least square method of multiple linear regression
State the parameter in passenger flow forecast model.
In above-mentioned technical proposal, the step 104) include：
First according to the weather forecast at prediction scenic spot, Body Comfort Index is calculated, the computing formula of the index is as follows：
Ssd=(1.818t+18.18) (0.88+0.002f)+(t-32)/(45-t) -3.2v+18.2；
Wherein, t is temperature on average, and f is relative humidity, and v is wind speed；
Then according to ssd value correction parameters β；Specifically include：If 50<ssd<76, β=1.25, if 25<ssd<51 or 75<
ssd<86, β=1；If ssd<26 or ssd>85, β=0.85；
It is last prediction initial value is corrected after correction parameter β is obtained, obtain the scenic spot passenger flow forecast amount after correction
Zβ：
Zβ=β Z；
Z is prediction initial value.
Present invention also offers a kind of tourist flow peak value regulation and control method, including：
Step 201), by it is described based on tourism big data tourist flow Forecasting Methodology obtained by a certain scenic spot visitor
Traffic prediction value is compared with reception visitor's ability at the scenic spot, according to comparative result by the scenic spot division for peak value regulates and controls scape
Area or surplus abundance scenic spot；Wherein,
The peak value regulation and control scenic spot is reception visitor ability of the tourist flow predicted value more than scenic spot, the surplus abundance scape
Area is reception visitor ability of the tourist flow predicted value less than scenic spot；
Step 202), calculate peak value regulation and control scenic spot and surplus abundance scenic spot between monomer regulation and control resistance coefficient；Wherein, institute
It is that the dimensionless for weighing regulation and control visitor's difficulty between peak value regulation and control scenic spot and surplus abundance scenic spot refers to state monomer regulation and control resistance coefficient
Mark, is together decided on by consuming difference, scenic spot attraction ratio between scape zone distance, scenic spot；
Step 203), based on step 202) monomer that obtains regulation and control resistance coefficient builds peak value regulation and control computation model；Wherein,
The drag overall that the peak value regulation and control computation model wants peaking visitor to regulate and control is minimum, and its expression formula is：
Wherein C is total regulation and control resistance, cijIt is to regulate and control scenic spot p from peak valueiDispatch visitor to surplus abundance scenic spot vjList
Body regulates and controls resistance coefficient, xijIt is to regulate and control scenic spot p from peak valueiDispatch visitor to surplus abundance scenic spot vjDomestic visitors；
Step 204), based on step 203) peak value set up regulation and control computation model, calculate estimated bus traveler assignment situation, really
Determine the corresponding surplus abundance scenic spot in visitor's peak value regulation and control scenic spot；
Step 205), based on step 204) result carry out visitor's induction.
In above-mentioned technical proposal, the step 202) include：
Step 202-1), peak value regulation and control scenic spot piWith surplus scenic spot vjBetween be scheduled, calculate two scenic spots between monomer
Regulation and control traffic consumption tij；Wherein,dijIt is the distance between scenic spot,It is local car rental cost average unit price；
Step 202-2), calculate peak value regulation and control scenic spot pi, surplus scenic spot vjBetween estimated visitor consumption difference；Wherein,
Estimated visitor's consumption differenceRespectively peak value regulation and control scenic spot pi, surplus scenic spot vjIt is estimated
Visitor consumes average value；
Step 202-3), calculate scenic spot attraction index ratio；If peak value regulates and controls scenic spot pi, surplus scenic spot vjScenic spot OTA nets
Network scoring is respectively si、sj, then scenic spot attraction index ratio is sij=si/sj；
Step 202-4), to monomer regulation and control traffic consumption tij, estimated visitor's consumption difference wijCarry out at data normalization
Reason：
Step 202-5), the monomer regulation and control traffic consumption t according to before between two scenic spots that are calculatedij, two scenic spots it
Between estimated visitor consumption difference wij, scenic spot attraction index compare sij, calculate the monomer regulation and control degree-of-difficulty factor between two scenic spots：
In above-mentioned technical proposal, the step 204) include：All of monomer in traversal peak value regulation and control computation model is adjusted
Control resistance coefficient cij, find the minimum paths of regulation and control consumption and preferentially distribute, take xij=min (pi, vj)；Move in circles, directly
To all of xijValue is completed, that is, obtains peak value scenic spot visitor regulation and control destination and estimated receiving number.
In above-mentioned technical proposal, in the step 205) in visitor's induction is carried out using three-level regulation and control model, including：
Given threshold x1、x2, work as xij<x1When, regulated and controled using one-level induction pattern, lured in modes such as broadcast near scenic spot
The transfer of guide passenger origin destination scenic spot；
Work as x1<xij<x2When, regulated and controled using two grades of induction patterns, outside carrying out broadcast induction near scenic spot, leading to scape
The intensive traffic section in area carries out Traffic Announcement, the control of regional signal lamp, and guiding vehicle flowrate is shifted as destination scenic spot；
Work as xij>x2When, regulated and controled using three-level induction pattern, the whole networkization issue visitor's induction information, two before giving full play to
While level induction means, news release is carried out using wechat public platform, WEB websites, mobile APP, OTA, since before row
Carry out visitor's induction regulating controlling.
The advantage of the invention is that：
The passenger flow forecast of integrated multi-channel of the present invention can effectively lift the degree of accuracy and have that scenic spot controlled the volume of the flow of passengers
Effect property, peak value regulation and control are carried out on the basis of prediction according to regulation and control resistance coefficient, can effectively alleviate the government pressure at scenic spot, are carried
Efficiency of operation high, so as to preferably service visitor, discharges the management and control pressure at scenic spot.
Brief description of the drawings
Fig. 1 is the flow chart of the tourist flow Forecasting Methodology based on tourism big data of the invention；
Fig. 2 is the flow chart that tourist flow peak value of the invention regulates and controls method；
Fig. 3 is the structural representation of passenger flow estimation sample；
Fig. 4 is the schematic diagram of peak value regulation-control model；
Fig. 5 is the schematic diagram of the factor of influence of monomer regulation and control resistance coefficient.
Specific embodiment
In conjunction with accompanying drawing, the invention will be further described.
With reference to Fig. 1, the tourist flow Forecasting Methodology based on tourism big data of the invention includes：
The first step：Tourism big data is read, forecast sample is set up.
With reference to Fig. 3, the tourism big data that the present invention is used includes history passenger flow data y1, social networks heating power data y2、
OTA browses data y3, surrounding cities visitor's data y4, traffic flow data y5.These data collectively form forecast sample, i.e., certain
The forecast sample of its passenger flow data is Y { y1,y2,y3,y4,y5}。
Second step：Based on the forecast sample, passenger flow forecast model is set up.
Passenger flow forecast amount Z is pressedFormula is calculated.Wherein, αkIt is the calculating ginseng of correspondence sample data
Number, α0It is prediction revision constant, e is the random error after removal influence.
According to the above-mentioned computing formula of passenger flow forecast amount Z, in n group forecast sample data { Y1,Y2,…,YnOn the basis of,
Set up passenger flow forecast model { Z1,Z2,…,Zn, it is represented by：
Wherein, the parameter value α in the passenger flow forecast modelik(i=1,2 ..., n；K=1,2 ..., 5) for unknown
Value, it is calculated in subsequent step.
3rd step：Parameter in the passenger flow forecast model is solved, so as to obtain passenger flow forecast model.
During parametric solution, the least square method of multiple linear regression is employed, i.e.,：Make the deviation between volume of the flow of passengers actual value and predicted value
Quadratic sum is minimum, carries out parameter initialization calculating：
In above-mentioned computing formula, yk(k=1,2,3,4,5) can obtain from foregoing n group forecast sample data, be
Given value；Z can be obtained by the true passenger flow data of history, be given value；Six parameter alphas0,α1,α2,α3,α4,α5It is unknown-value,
By above-mentioned six groups of relational expressions, six values of parameter can be calculated.
Can be n/6 calculating group by n group forecast sample data random combine when realizing, by above-mentioned six groups of relational expressions,
Obtain n/6 groups α0,α1,α2,α3,α4,α5, last parameter value α is averagely determined finally by taking0,α1,α2,α3,α4,α5。
4th step：Calculate prediction initial value.
According to the tourist flows Prediction Parameters that the 3rd step is tried to achieve, substitute intoCalculating is tried to achieve prediction day and is worked as
The initial value of day volume of the flow of passengers Z.
5th step：The predicted value on correction prediction same day day volume of the flow of passengers Z.
When predicted value is corrected, first according to the weather forecast at prediction scenic spot, Body Comfort Index is calculated, the index
Computing formula is as follows：
Ssd=(1.818t+18.18) (0.88+0.002f)+(t-32)/(45-t) -3.2v+18.2；
Wherein, t is temperature on average, and f is relative humidity, and v is wind speed.
With ssd values correspondence correction parameter β, 50<ssd<76, β=1.25,25<ssd<51 or 75<ssd<86, β=1, ssd<
26 or ssd>85, β=0.85.
After correction parameter β is obtained, prediction initial value is corrected, obtains the scenic spot passenger flow forecast amount after correction：
Zβ=β Z.
On the basis of scenic spot passenger flow forecast value obtained by tourist flow Forecasting Methodology of the invention, visitor of the invention
Peak flow regulation and control method can regulate and control to tourist flow, as shown in Fig. 2 the method includes：
6th step：By scenic spot passenger flow forecast value ZβVisitor's ability Z is received with scenic spotmaxDifference comparing is carried out, if Zβ＞ ZmaxThen
Regulation and control state, domestic visitors p=Z to be regulated and controled are treated in peak value in scenic spotβ-Zmax；If Zβ＜ ZmaxThen scenic spot is in surplus abundance state,
Visitor's surplus v=Z can be receivedmax-Zβ。
7th step：Scenic spot division.
Predicted according to tourist flow, be that peak value regulates and controls scenic spot collection and surplus abundance scenic spot collection by scenic spot division.Peak value regulates and controls
Scenic spot collection includes m scenic spot to be regulated and controled, and is designated as P1,P2…Pm, its domestic visitors to be regulated and controled is p1、p2…pm.Surplus abundance scenic spot collection
Visitor scenic spot can be balanced comprising n, V is designated as1,V2…Vn, its visitor's carrying capacity is v1、v2…vn。
8th step：Calculate the monomer regulation and control resistance coefficient between peak value regulation and control scenic spot and surplus abundance scenic spot.Wherein, it is described
Monomer regulation and control resistance coefficient is to weigh the dimensionless index for regulating and controlling visitor's difficulty between peak value regulation and control scenic spot and surplus abundance scenic spot,
As shown in figure 5, being together decided on by consuming difference, scenic spot attraction ratio between scape zone distance, scenic spot.The step is specifically included：
Peak value regulates and controls scenic spot piWith surplus scenic spot vjBetween be scheduled, the regulation and control traffic consumption of monomer between two scenic spots
tij, the distance between scenic spot is dij, local car rental cost average unit price isThen
Calculate the estimated visitor consumption difference between two scenic spots, pi、vjThe estimated visitor's consumption average value in scenic spot is respectively
Scenic spot attraction index ratio is calculated, if pi、vjScenic spot OTA network scorings are respectively si、sj, then scenic spot attraction refer to
Number is than being sij=si/sj。
To tij、wijCarry out data normalization treatment：
According to the monomer regulation and control traffic consumption t between two scenic spots being calculated beforeij, estimated visitor between two scenic spots
Consumption difference wij, scenic spot attraction index compare sij, calculate the monomer regulation and control degree-of-difficulty factor between two scenic spots：
9th step：Build peak value regulation and control computation model.
It is assumed that the expression formula of the drag overall of peak value visitor regulation and control is：In regulation process
Make every effort to its regulation and control resistance minimum.I.e.：
Wherein C is total regulation and control resistance, cijIt is to regulate and control scenic spot p from peak valueiDispatch visitor to surplus abundance scenic spot vjList
Body regulates and controls resistance coefficient, xijIt is to regulate and control scenic spot p from peak valueiDispatch visitor to surplus abundance scenic spot vjDomestic visitors.
Tenth step：Estimated bus traveler assignment situation is calculated, the corresponding surplus abundance scenic spot in visitor's peak value regulation and control scenic spot is determined.
In this step, all of monomer regulation and control resistance coefficient c is traveled throughij, find the minimum paths of regulation and control consumption excellent
First distribute, take xij=min (pi, vj).So circulation, until all of xijComplete value.Peak value scenic spot visitor is obtained to adjust
Control destination and estimated receiving number.
11st step：Result according to the tenth step carries out visitor's induction, and volume of the flow of passengers setting three-level regulation and control are regulated and controled according to expectation
Pattern.Given threshold x1、x2, xij<x1When, regulated and controled using one-level induction pattern, visitor is induced in modes such as broadcast near scenic spot
Shifted to destination scenic spot.x1<xij<x2When, regulated and controled using two grades of induction patterns, outside carrying out broadcast induction near scenic spot,
Traffic Announcement, the control of regional signal lamp are carried out in the intensive traffic section for leading to scenic spot, guiding vehicle flowrate is shifted as destination scenic spot.xij
>x2When, regulated and controled using three-level induction pattern, the whole networkization issue visitor's induction information, the two-stage induction means before giving full play to
Meanwhile, news release is carried out using wechat public platform, WEB websites, mobile APP, OTA, visitor's induction is proceeded by from before row
Regulation and control.
Synthesis usage history passenger flow data of the invention, social networks heating power data, OTA browse data, surrounding cities visitor
Data, traffic flow data set up multivariate regression models, carry out parameter fitting, and the scheduled date is carried out after obtaining parameter fitting value
Prediction.After the completion of initial predicted, according to Weather information, initial prediction is revised.To scenic spot on the basis of passenger flow estimation
Classified, scenic spot division is calculated by the regulation and control between scenic spot for peak value regulates and controls scenic spot and surplus restructuring scenic spot according to predicted value
Resistance coefficient, distribution model is regulated and controled using visitor, is calculated solution and is obtained visitor's regulation and control distribution numerical value, according to distribution numerical value to each tune
Different control measures are implemented at control scenic spot, and visitor's scheduling is carried out between two class scenic spots, to realize the flat of the volume of the flow of passengers between scenic spot
Weighing apparatus distribution.The passenger flow forecast of integrated multi-channel can effectively lift the degree of accuracy and the validity that scenic spot is controlled the volume of the flow of passengers,
Peak value regulation and control are carried out according to regulation and control resistance coefficient on the basis of prediction, can effectively alleviate the government pressure at scenic spot, improve operation
Efficiency, so as to preferably service visitor, discharges the management and control pressure at scenic spot.
It should be noted last that, the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted.Although ginseng
The present invention has been described in detail according to embodiment, it will be understood by those within the art that, to technical side of the invention
Case is modified or equivalent, and without departure from the spirit and scope of technical solution of the present invention, it all should cover in the present invention
Right in the middle of.
Claims (7)
1. it is a kind of based on tourism big data tourist flow Forecasting Methodology, including：
Step 101), collection tourism big data, set up forecast sample；Wherein,
The tourism big data includes history passenger flow data y1, social networks heating power data y2, OTA browse data y3, surrounding cities
Visitor's data y4, traffic flow data y5；The prediction model includes the tourism big data in one or more time periods；
Step 102), set up passenger flow forecast model, and the passenger flow forecast model asked for based on the forecast sample
Parameter；Wherein, the passenger flow forecast model is：
Z therein is passenger flow forecast amount, αkIt is the calculating parameter of correspondence sample data, αkIt is prediction revision constant, e is removal shadow
Random error after sound, ykIt is the data in prediction model；αk、αkIt is the parameter to be asked in the passenger flow forecast model；
Step 103), by step 102) obtained by passenger flow forecast model calculate tourist flow prediction initial value；
Step 104), according to scenic spot prediction day weather forecast correct tourist flow predicted value.
2. it is according to claim 1 based on tourism big data tourist flow Forecasting Methodology, it is characterised in that described
Step 102) in, the parameter in the passenger flow forecast model is asked for using the least square method of multiple linear regression.
3. it is according to claim 1 based on tourism big data tourist flow Forecasting Methodology, it is characterised in that the step
104) include：
First according to the weather forecast at prediction scenic spot, Body Comfort Index is calculated, the computing formula of the index is as follows：
Ssd=(1.818t+18.18) (0.88+0.002f)+(t-32)/(45-t) -3.2v+18.2；
Wherein, t is temperature on average, and f is relative humidity, and v is wind speed；
Then according to ssd value correction parameters β；Specifically include：If 50<ssd<76, β=1.25, if 25<ssd<51 or 75<ssd<
86, β=1；If ssd<26 or ssd>85, β=0.85；
It is last prediction initial value is corrected after correction parameter β is obtained, obtain the scenic spot passenger flow forecast amount Z after correctionβ：
Zβ=β Z；
Z is prediction initial value.
4. a kind of tourist flow peak value regulates and controls method, including：
Step 201), will described in one of claim 1-3 based on tourism big data tourist flow Forecasting Methodology obtained by
The tourist flow predicted value at a certain scenic spot is compared with reception visitor's ability at the scenic spot, is drawn the scenic spot according to comparative result
It is divided into peak value regulation and control scenic spot or surplus abundance scenic spot；Wherein,
The peak value regulation and control scenic spot is reception visitor ability of the tourist flow predicted value more than scenic spot, and the surplus abundance scenic spot is
Reception visitor ability of the tourist flow predicted value less than scenic spot；
Step 202), calculate peak value regulation and control scenic spot and surplus abundance scenic spot between monomer regulation and control resistance coefficient；Wherein, the list
Body regulation and control resistance coefficient is to weigh the dimensionless index for regulating and controlling visitor's difficulty between peak value regulation and control scenic spot and surplus abundance scenic spot, by
Difference, scenic spot attraction ratio is consumed between scape zone distance, scenic spot to together decide on；
Step 203), based on step 202) monomer that obtains regulation and control resistance coefficient builds peak value regulation and control computation model；Wherein, it is described
Peak value regulation and control computation model wants the drag overall that peaking visitor regulates and controls minimum, and its expression formula is：
Wherein C is total regulation and control resistance, cijIt is to regulate and control scenic spot p from peak valueiDispatch visitor to surplus abundance scenic spot vjMonomer regulation and control
Resistance coefficient, xijIt is to regulate and control scenic spot p from peak valueiDispatch visitor to surplus abundance scenic spot vjDomestic visitors；
Step 204), based on step 203) peak value set up regulation and control computation model, estimated bus traveler assignment situation is calculated, it is determined that trip
Objective peak value regulates and controls the corresponding surplus abundance scenic spot in scenic spot；
Step 205), based on step 204) result carry out visitor's induction.
5. tourist flow peak value according to claim 4 regulates and controls method, it is characterised in that the step 202) include：
Step 202-1), peak value regulation and control scenic spot piWith surplus scenic spot vjBetween be scheduled, calculate two scenic spots between monomer regulation and control
T is consumed in trafficij；Wherein,dijIt is the distance between scenic spot,It is local car rental cost average unit price；
Step 202-2), calculate peak value regulation and control scenic spot pi, surplus scenic spot vjBetween estimated visitor consumption difference；Wherein,
Estimated visitor's consumption difference Respectively peak value regulation and control scenic spot pi, surplus scenic spot vjEstimated visitor disappears
Take average value；
Step 202-3), calculate scenic spot attraction index ratio；If peak value regulates and controls scenic spot pi, surplus scenic spot vjScenic spot OTA networks comment
It is respectively si、sj, then scenic spot attraction index ratio is sij=si/sj；
Step 202-4), to monomer regulation and control traffic consumption tij, estimated visitor's consumption difference wijCarry out data normalization treatment：
Step 202-5), the monomer regulation and control traffic consumption t according to before between two scenic spots that are calculatedij, between two scenic spots
Estimated visitor's consumption difference wij, scenic spot attraction index compare sij, calculate the monomer regulation and control degree-of-difficulty factor between two scenic spots：
6. tourist flow peak value according to claim 4 regulates and controls method, it is characterised in that the step 204) include：Time
The all of monomer regulation and control resistance coefficient c gone through in peak value regulation and control computation modelij, find the minimum paths of regulation and control consumption preferential
Distribution, takes xij=min (pi, vj)；Move in circles, until all of xijValue is completed, that is, obtains peak value scenic spot visitor regulation and control
Destination and estimated receiving number.
7. tourist flow peak value according to claim 4 regulates and controls method, it is characterised in that in the step 205) middle use
Three-level regulation and control model carries out visitor's induction, including：
Given threshold x1、x2, work as xij<x1When, regulated and controled using one-level induction pattern, trip is induced in modes such as broadcast near scenic spot
Shift at passenger origin destination scenic spot；
Work as x1<xij<x2When, regulated and controled using two grades of induction patterns, outside carrying out broadcast induction near scenic spot, leading to scenic spot
The intensive traffic section carries out Traffic Announcement, the control of regional signal lamp, and guiding vehicle flowrate is shifted as destination scenic spot；
Work as xij>x2When, regulating and controlling using three-level induction pattern, the whole networkization issue visitor's induction information, two-stage is lured before giving full play to
While leading means, news release is carried out using wechat public platform, WEB websites, mobile APP, OTA, proceeded by from before row
Visitor's induction regulating controlling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611105518.7A CN106779196A (en) | 2016-12-05 | 2016-12-05 | A kind of tourist flow prediction and peak value regulation and control method based on tourism big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611105518.7A CN106779196A (en) | 2016-12-05 | 2016-12-05 | A kind of tourist flow prediction and peak value regulation and control method based on tourism big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106779196A true CN106779196A (en) | 2017-05-31 |
Family
ID=58874209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611105518.7A Pending CN106779196A (en) | 2016-12-05 | 2016-12-05 | A kind of tourist flow prediction and peak value regulation and control method based on tourism big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779196A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833161A (en) * | 2017-10-10 | 2018-03-23 | 东南大学 | A kind of tourist communications management system based on big data |
| CN108053153A (en) * | 2018-02-22 | 2018-05-18 | 海南师范大学 | A kind of ecotourism environment bearing capacity early warning system |
| CN108305459A (en) * | 2018-02-05 | 2018-07-20 | 北京交通大学 | A kind of road network operation index forecasting method based on data-driven |
| CN110099089A (en) * | 2018-01-31 | 2019-08-06 | Sap欧洲公司 | The self-tuing on line of multiple data flows in sensor network |
| CN110175690A (en) * | 2019-04-04 | 2019-08-27 | 中兴飞流信息科技有限公司 | A kind of method, apparatus, server and the storage medium of scenic spot passenger flow forecast |
| CN110675176A (en) * | 2018-07-03 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating an attribute prediction model |
| CN110796301A (en) * | 2019-10-23 | 2020-02-14 | 广东岭南通股份有限公司 | Passenger flow prediction method and device based on IC card data |
| CN110852529A (en) * | 2019-11-20 | 2020-02-28 | 软通动力信息技术有限公司 | Urban component risk prediction method, device, server and storage medium |
| CN110929926A (en) * | 2019-11-18 | 2020-03-27 | 西北工业大学 | Short-term explosion passenger flow prediction method based on long and short-term memory network and random forest |
| CN110956089A (en) * | 2019-11-04 | 2020-04-03 | 李苗裔 | Historical block walking performance measuring method based on ICT technology |
| CN111091196A (en) * | 2019-11-15 | 2020-05-01 | 佳都新太科技股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN111178633A (en) * | 2019-12-31 | 2020-05-19 | 上饶市中科院云计算中心大数据研究院 | Method and device for predicting scenic spot passenger flow based on random forest algorithm |
| CN111798027A (en) * | 2020-05-27 | 2020-10-20 | 山东任性网络科技有限公司 | Tourist flow prediction and peak value regulation and control method based on tourism big data |
| CN112365638A (en) * | 2020-11-16 | 2021-02-12 | 成都中科大旗软件股份有限公司 | Scenic spot passenger flow early warning system |
| CN113222299A (en) * | 2021-06-10 | 2021-08-06 | 湘南学院 | Intelligent vehicle scheduling system and method for scenic spot |
| CN114219114A (en) * | 2021-12-24 | 2022-03-22 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
| CN114529034A (en) * | 2021-12-28 | 2022-05-24 | 浙江中测新图地理信息技术有限公司 | Intelligent scheduling method for scenic spot pleasure boats based on real-time passenger flow volume |
| CN116739838A (en) * | 2023-05-06 | 2023-09-12 | 广州圈量网络信息科技有限公司 | Passenger flow volume distribution system for intelligent analysis of geographic position |
| CN117591919A (en) * | 2024-01-17 | 2024-02-23 | 北京工业大学 | Passenger flow prediction method, passenger flow prediction device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11165637A (en) * | 1997-12-01 | 1999-06-22 | Hitachi Ltd | Passenger flow estimating system |
| CN102737284A (en) * | 2012-05-25 | 2012-10-17 | 苏州博远容天信息科技有限公司 | Application of multiple linear regression method in passenger flow forecast based on SAS (Sequence Retrieval System) |
| CN104899650A (en) * | 2015-05-26 | 2015-09-09 | 成都中科大旗软件有限公司 | Method for predicting tourist flow volume of tourist attraction on basis of multi-source data analysis |
| CN104951845A (en) * | 2015-05-29 | 2015-09-30 | 华南理工大学 | Tourist attraction saturation pre-warning method with function of passenger flow volume fitting on basis of network attention |
-
2016
- 2016-12-05 CN CN201611105518.7A patent/CN106779196A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11165637A (en) * | 1997-12-01 | 1999-06-22 | Hitachi Ltd | Passenger flow estimating system |
| CN102737284A (en) * | 2012-05-25 | 2012-10-17 | 苏州博远容天信息科技有限公司 | Application of multiple linear regression method in passenger flow forecast based on SAS (Sequence Retrieval System) |
| CN104899650A (en) * | 2015-05-26 | 2015-09-09 | 成都中科大旗软件有限公司 | Method for predicting tourist flow volume of tourist attraction on basis of multi-source data analysis |
| CN104951845A (en) * | 2015-05-29 | 2015-09-30 | 华南理工大学 | Tourist attraction saturation pre-warning method with function of passenger flow volume fitting on basis of network attention |
Non-Patent Citations (1)
| Title |
|---|
| 林锉云等: "《多目标优化的方法与理论》", 31 August 1992, 吉林教育出版社 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833161A (en) * | 2017-10-10 | 2018-03-23 | 东南大学 | A kind of tourist communications management system based on big data |
| CN110099089A (en) * | 2018-01-31 | 2019-08-06 | Sap欧洲公司 | The self-tuing on line of multiple data flows in sensor network |
| CN108305459A (en) * | 2018-02-05 | 2018-07-20 | 北京交通大学 | A kind of road network operation index forecasting method based on data-driven |
| CN108053153A (en) * | 2018-02-22 | 2018-05-18 | 海南师范大学 | A kind of ecotourism environment bearing capacity early warning system |
| CN110675176B (en) * | 2018-07-03 | 2023-03-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating an attribute prediction model |
| CN110675176A (en) * | 2018-07-03 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating an attribute prediction model |
| CN110175690A (en) * | 2019-04-04 | 2019-08-27 | 中兴飞流信息科技有限公司 | A kind of method, apparatus, server and the storage medium of scenic spot passenger flow forecast |
| CN110796301A (en) * | 2019-10-23 | 2020-02-14 | 广东岭南通股份有限公司 | Passenger flow prediction method and device based on IC card data |
| CN110796301B (en) * | 2019-10-23 | 2022-11-11 | 广东岭南通股份有限公司 | Passenger flow prediction method and device based on IC card data |
| CN110956089A (en) * | 2019-11-04 | 2020-04-03 | 李苗裔 | Historical block walking performance measuring method based on ICT technology |
| CN110956089B (en) * | 2019-11-04 | 2023-05-23 | 李苗裔 | ICT technology-based historical block walking measurement method |
| CN111091196A (en) * | 2019-11-15 | 2020-05-01 | 佳都新太科技股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN111091196B (en) * | 2019-11-15 | 2022-08-02 | 佳都科技集团股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN110929926A (en) * | 2019-11-18 | 2020-03-27 | 西北工业大学 | Short-term explosion passenger flow prediction method based on long and short-term memory network and random forest |
| CN110852529A (en) * | 2019-11-20 | 2020-02-28 | 软通动力信息技术有限公司 | Urban component risk prediction method, device, server and storage medium |
| CN111178633A (en) * | 2019-12-31 | 2020-05-19 | 上饶市中科院云计算中心大数据研究院 | Method and device for predicting scenic spot passenger flow based on random forest algorithm |
| CN111798027A (en) * | 2020-05-27 | 2020-10-20 | 山东任性网络科技有限公司 | Tourist flow prediction and peak value regulation and control method based on tourism big data |
| CN112365638A (en) * | 2020-11-16 | 2021-02-12 | 成都中科大旗软件股份有限公司 | Scenic spot passenger flow early warning system |
| CN113222299A (en) * | 2021-06-10 | 2021-08-06 | 湘南学院 | Intelligent vehicle scheduling system and method for scenic spot |
| CN114219114B (en) * | 2021-12-24 | 2022-08-26 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
| CN114219114A (en) * | 2021-12-24 | 2022-03-22 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
| CN114529034A (en) * | 2021-12-28 | 2022-05-24 | 浙江中测新图地理信息技术有限公司 | Intelligent scheduling method for scenic spot pleasure boats based on real-time passenger flow volume |
| CN114529034B (en) * | 2021-12-28 | 2023-11-24 | 浙江中测时空科技有限公司 | Scenic spot pleasure boat intelligent scheduling method based on real-time passenger flow |
| CN116739838A (en) * | 2023-05-06 | 2023-09-12 | 广州圈量网络信息科技有限公司 | Passenger flow volume distribution system for intelligent analysis of geographic position |
| CN116739838B (en) * | 2023-05-06 | 2024-03-08 | 广州圈量网络信息科技有限公司 | Passenger flow volume distribution system for intelligent analysis of geographic position |
| CN117591919A (en) * | 2024-01-17 | 2024-02-23 | 北京工业大学 | Passenger flow prediction method, passenger flow prediction device, electronic equipment and storage medium |
| CN117591919B (en) * | 2024-01-17 | 2024-03-26 | 北京工业大学 | Passenger flow prediction method, passenger flow prediction device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779196A (en) | A kind of tourist flow prediction and peak value regulation and control method based on tourism big data | |
| CN104134105B (en) | A kind of public transport network lays optimization method | |
| CN102360522B (en) | Highway optimization control method | |
| CN104616076B (en) | A kind of optimization method and system of the multi-thread collaboration Management plan of urban track traffic | |
| CN105096004A (en) | Real-time scheduling method for reservoir group water supply and transfer system | |
| WO2020098728A1 (en) | Cluster load prediction method and apparatus, and storage medium | |
| CN104504280B (en) | Electric automobile charging pile cluster management system communication mode integrated evaluating method | |
| CN106295875A (en) | A kind of open service district addressing location mode | |
| CN107284452A (en) | Merge the following operating mode forecasting system of hybrid vehicle of intelligent communication information | |
| CN103955868A (en) | Demand response effect evaluation method based on fuzzy comprehensive analysis | |
| CN110807651A (en) | Intercity railway passenger ticket time-sharing pricing method based on generalized cost function | |
| Cai et al. | Mechanics of spatial growth | |
| CN106682765A (en) | Charging station optimization layout method and apparatus thereof | |
| CN110598971B (en) | Responsive bus service planning method based on ant colony algorithm | |
| CN108322915A (en) | The information processing method and device of base station planning | |
| CN113420967B (en) | Urban water supply pipe network operation evaluation method based on prediction | |
| Zhou et al. | Exploring the impact of energy factor prices and environmental regulation on China’s green innovation efficiency | |
| Li et al. | Prediction of electric vehicle ownership based on Gompertz model | |
| CN111260161A (en) | Method and device for issuing crowdsourcing tasks | |
| CN106022496A (en) | Raw material sintering burdening optimization method and system | |
| CN116307647A (en) | Electric vehicle charging station site selection and volume determination optimization method and device and storage medium | |
| Peng et al. | An Estimation Model of Traffic Carbon Emission Based on Traffic Planning Index and STIRPAT in Counties | |
| Zan | Modeling of the impact of regional transportation on social and economic development. | |
| CN116739322B (en) | Taxi supply and demand assessment method, equipment and medium based on service acquisition index | |
| Tan et al. | Pricing of Responsive Feeder Transit Considering Competitive Relationships with Bike Sharing |
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: 20170531 |
|
| RJ01 | Rejection of invention patent application after publication |