CN106447082A - Parking demand pre-estimation method and parking demand pre-estimation device - Google Patents
Parking demand pre-estimation method and parking demand pre-estimation device Download PDFInfo
- Publication number
- CN106447082A CN106447082A CN201610799062.2A CN201610799062A CN106447082A CN 106447082 A CN106447082 A CN 106447082A CN 201610799062 A CN201610799062 A CN 201610799062A CN 106447082 A CN106447082 A CN 106447082A
- Authority
- CN
- China
- Prior art keywords
- vehicle flowrate
- curve
- parking
- cyclical fluctuations
- monitoring point
- 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 invention relates to the electronic communication technology field and particularly relates to a parking demand pre-estimation method. According to the method, fluctuation curves are generated, a dynamic change function of parking demands relative to the vehicle flow data of vehicle flow mounting sites is established according to a time delay coefficient of each vehicle flow mounting site, a comprehensive pre-estimation function is established according to a weight coefficient of each vehicle flow monitoring point and the corresponding dynamic change function to acquire relatively precise pre-estimation parking demands. Quantitative analysis is acquired through establishing relationships between the parking demand fluctuation curve and the vehicle flow fluctuation curve; parking demands are comprehensively acquired through influence weight of multiple vehicle flow monitoring sites on parking demands; more preceise pre-estimation about parking demands is acquired through calculating different time delay effects. The method is advantaged in that a function module framework can be successfully combined through establishing function modules, and a computer program stored in a readable computer storage medium can be utilized for enforcement.
Description
Technical field
The present invention relates to electronic communication technology field, particularly to parking demand predictor method.Parking demand is estimated
Method, can be combined into functional module construction by setting up functional module, by the meter storing in a computer-readable storage medium
Calculation machine program is implementing.
Background technology
With the development of the city, the automobile pollution in city gets more and more, and parking demand also becomes the one of city management
An individual difficult problem.In order to preferably carry out parking management, need the regional to city to carry out parking demand and estimate.At present, in order to
Estimate parking demand, introduce in the industry thermodynamic chart and put forward car demand to analyze, thermodynamic chart can embody the vehicle flowrate inside region, energy
Enough reflect certain parking demand, but, because the influence factor of parking demand is various, vehicle flowrate is with parking demand simultaneously
Linear relationship can not directly be set up, current analysis method but seldom obtains the analytical data quantifying, and is more base
To judge in the subjective feeling to thermodynamic chart.
On the other hand, current analysis mainly one day is a unit of analysis, by thermodynamic chart and conventional thermodynamic chart
Be compared to predict the parking demand on the same day, however, for city management, more in the urgent need to be daytime (i.e.
Vehicle runs more frequently time period) parking demand is made and timely estimates and respond, however, current predictor method is all
Also it is difficult to this point.
Content of the invention
It is an object of the invention to avoiding above-mentioned weak point of the prior art and providing a kind of parking demand side of estimating
Method, timely estimates and responds to make to parking demand.
The purpose of the present invention is achieved through the following technical solutions：
Parking demand predictor method is provided, comprises the steps：
Curve of cyclical fluctuations generation step：Treating to set up at least three vehicle flowrate monitoring points in discreet area, obtain this region
The history vehicle flowrate data of history parking capacity data and each vehicle flowrate monitoring point in each measurement period, generates history parking capacity
The history vehicle flowrate data of the parking capacity curve of cyclical fluctuations between different measurement periods for the data and each vehicle flowrate monitoring point is in difference
The vehicle flowrate curve of cyclical fluctuations between measurement period；
Coefficient determines step：Calculate the flowed fluctuation curve of each vehicle flowrate monitoring point car and the phase of the parking capacity curve of cyclical fluctuations
Like degree and time delay coefficient, determining the weight coefficient of each vehicle flowrate monitoring point, similarity degree is higher for the sequence according to similarity
Then weight is bigger；
Prediction model establishment step：Respectively parking demand is set up relatively according to the time delay coefficient of each vehicle flowrate monitoring point
The dynamic change function of the vehicle flowrate data of this vehicle flowrate monitoring point, then each vehicle flowrate monitoring point comprehensive weight coefficient and its
Corresponding dynamic change function comprehensively estimates function to set up；
Demand estimates step：The corresponding data of each vehicle flowrate monitoring point is substituted into and comprehensively estimates function, thus estimate stopping
Car amount data.
Preferably, described coefficient determines that step includes time delay coefficient and determines step：Obtain the parking capacity curve of cyclical fluctuations each
Peak value and the peak value of the vehicle flowrate curve of cyclical fluctuations, if the peak value of any one curve of cyclical fluctuations and the peak with its immediate curve of cyclical fluctuations
Value difference on a timeline is single deviation, the time shafts of the adjustment parking capacity curve of cyclical fluctuations and/or the vehicle flowrate curve of cyclical fluctuations
Until all single deviations are less than threshold value, and all single deviations and be adjusted to minimum, then according to now time
The adjustment amount of axle is determining time delay coefficient.
Preferably, described dynamic change function is fT(i)=K (iT-t), wherein t is time delay coefficient, and K is constant.
Preferably, described vehicle flowrate monitoring point is based on radio frequency vehicle electron identifying.
Preferably, described curve of cyclical fluctuations generation step also includes data and filters step：Fluctuation by the parking capacity curve of cyclical fluctuations
The section that rate is less than fluctuation threshold filters.
For parking demand predictor method, functional module construction can be combined into by setting up functional module, by being stored in
Computer program in computer-readable recording medium is implementing.
Beneficial effects of the present invention：The parking demand predictor method that the present invention provides has following characteristics, first although stopping
Linear relationship cannot directly be set up between demand and vehicle flowrate, but inventor finds that both fluctuations have dependency,
Therefore, the analysis of quantization can be obtained by setting up the contact of both curves of cyclical fluctuations；Secondly, need it was recognized by the inventor that stopping
Seeking Truth is affected by many factors, and single vehicle flowrate is the parking demand being difficult to reflect a region, but, different factor
Parking demand finally all can embody in the vehicle flowrate of diverse location, therefore the present invention passes through to arrange multiple vehicle flowrates prison
Measuring point, by drawing parking demand to the weighing factor of parking demand Lai comprehensive to multiple vehicle flowrate monitoring points；Again, the present invention
It is also recognized that in delay effect between vehicle flowrate and parking demand, and the delay effect of different vehicle flowrate monitoring points is different
, therefore by calculating to different delay effects, you can more accurately estimate parking demand.
Specific embodiment
The invention will be further described with the following Examples.
The parking demand predictor method that the present invention provides, according to the fluctuation dependency between parking demand and vehicle flowrate, right
Multiple vehicle flowrate monitoring points comprehensively to draw parking demand to the weighing factor of parking demand, then by different time delay effects
Should be calculated, you can more accurately estimate parking demand.
First, treating to set up at least three vehicle flowrate monitoring points based on radio frequency vehicle electron identifying in discreet area, obtain
Take the history vehicle flowrate data of history parking capacity data and each vehicle flowrate monitoring point in each measurement period in this region, generate
The parking capacity curve of cyclical fluctuations between different measurement periods for the history parking capacity data and the history vehicle flowrate of each vehicle flowrate monitoring point
Data vehicle flowrate curve of cyclical fluctuations between different measurement periods.The data that at least three vehicle flowrate monitoring points obtain can fully be reacted
The practical situation of vehicle flowrate, the section that the stability bandwidth of the parking capacity curve of cyclical fluctuations is less than fluctuation threshold filters, and can be had more
Universality feature and the representational curve of cyclical fluctuations.By setting up the contact of the vehicle flowrate curve of cyclical fluctuations and the parking capacity curve of cyclical fluctuations
Obtain the analysis quantifying.
Then, calculate the flowed fluctuation curve of each vehicle flowrate monitoring point car and the similarity of the parking capacity curve of cyclical fluctuations and prolong
When coefficient, determining the weight coefficient of each vehicle flowrate monitoring point, the more high then weight of similarity degree is more for the sequence according to similarity
Greatly.Then the flowed fluctuation curve of car and the Changing Pattern of the parking capacity curve of cyclical fluctuations are closer to rule of can more accurately being fluctuated
Rule.Obtain each peak value of the parking capacity curve of cyclical fluctuations and the peak value of the vehicle flowrate curve of cyclical fluctuations, if the peak of any one curve of cyclical fluctuations
Value and be single deviation with the peak value of its immediate curve of cyclical fluctuations difference on a timeline, adjusts the parking capacity curve of cyclical fluctuations
And/or the time shafts of the vehicle flowrate curve of cyclical fluctuations until all single deviations be less than threshold value, and all single deviations and quilt
Adjust to minimum, then the adjustment amount according to now time shafts is determining time delay coefficient.By carrying out to different delay effects
Calculate, you can more accurately estimate parking demand.
Respectively parking demand is set up relative to this vehicle flowrate monitoring point according to the time delay coefficient of each vehicle flowrate monitoring point
The dynamic change function f of vehicle flowrate dataT(i)=K (iT-t), wherein t is time delay coefficient, and K is constant, then each wagon flow comprehensive
The weight coefficient of amount monitoring point and its corresponding dynamic change function comprehensively estimate function to set up.Finally each vehicle flowrate is supervised
The corresponding data of measuring point substitutes into comprehensively estimates function, thus estimating parking capacity data.
For parking demand predictor method, functional module construction can be combined into by setting up functional module, by being stored in
Computer program in computer-readable recording medium is implementing.
Finally it should be noted that above example is only in order to illustrating technical scheme, rather than the present invention is protected
The restriction of shield scope, although having made to explain to the present invention with reference to preferred embodiment, those of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent, without deviating from the reality of technical solution of the present invention
Matter and scope.
Claims (10)
1. parking demand predictor method is it is characterised in that comprise the steps：
Curve of cyclical fluctuations generation step：Treating to set up at least three vehicle flowrate monitoring points in discreet area, obtain this region each
The history vehicle flowrate data of history parking capacity data and each vehicle flowrate monitoring point in measurement period, generates history parking capacity data
The history vehicle flowrate data of the parking capacity curve of cyclical fluctuations between different measurement periods and each vehicle flowrate monitoring point is in different statistics
The vehicle flowrate curve of cyclical fluctuations during week；
Coefficient determines step：Calculate the flowed fluctuation curve of each vehicle flowrate monitoring point car and the similarity of the parking capacity curve of cyclical fluctuations
With time delay coefficient, determining the weight coefficient of each vehicle flowrate monitoring point, similarity degree gets over Gao Zequan to the sequence according to similarity
Again bigger；
Prediction model establishment step：Respectively parking demand is set up relative to this car according to the time delay coefficient of each vehicle flowrate monitoring point
The dynamic change function of the vehicle flowrate data of flow monitoring point, the more comprehensively weight coefficient of each vehicle flowrate monitoring point and its correspondence
Dynamic change function comprehensive estimate function to set up；
Demand estimates step：The corresponding data of each vehicle flowrate monitoring point is substituted into and comprehensively estimates function, thus estimating parking capacity
Data.
2. parking demand predictor method as claimed in claim 1 is it is characterised in that described coefficient determines that step includes time delay system
Number determines step：Obtain each peak value of the parking capacity curve of cyclical fluctuations and the peak value of the vehicle flowrate curve of cyclical fluctuations, if any one fluctuation
The peak value of curve and be single deviation with the peak value of its immediate curve of cyclical fluctuations difference on a timeline, adjusts parking capacity
The time shafts of the curve of cyclical fluctuations and/or the vehicle flowrate curve of cyclical fluctuations are until all single deviations are less than threshold value, and all single deviations
Value and be adjusted to minimum, then the adjustment amount according to now time shafts is determining time delay coefficient.
3. parking demand predictor method as claimed in claim 1 it is characterised in that：Described dynamic change function is fT(i)=K
(iT-t), wherein t is time delay coefficient, and K is constant.
4. parking demand predictor method as claimed in claim 1 it is characterised in that：Described vehicle flowrate monitoring point is based on radio frequency vapour
Car electronic mark.
5. parking demand predictor method as claimed in claim 1 it is characterised in that：Described curve of cyclical fluctuations generation step also includes
Data filters step：The section that the stability bandwidth of the parking capacity curve of cyclical fluctuations is less than fluctuation threshold filters.
6. parking demand estimating device is it is characterised in that include：
Curve of cyclical fluctuations generation module：It obtains each of this region treating to set up at least three vehicle flowrate monitoring points in discreet area
The history vehicle flowrate data of history parking capacity data and each vehicle flowrate monitoring point in individual measurement period, generates history parking capacity number
History vehicle flowrate data according to the parking capacity curve of cyclical fluctuations between different measurement periods and each vehicle flowrate monitoring point is united different
The vehicle flowrate curve of cyclical fluctuations during meter week；
Coefficient determination module：It is similar to the parking capacity curve of cyclical fluctuations that it calculates the flowed fluctuation curve of each vehicle flowrate monitoring point car
Degree and time delay coefficient, determining the weight coefficient of each vehicle flowrate monitoring point, similarity degree gets over Gao Ze to the sequence according to similarity
Weight is bigger；
Prediction model sets up module：It is set up according to the time delay coefficient of each vehicle flowrate monitoring point respectively, and parking demand is relative to be somebody's turn to do
The dynamic change function of the vehicle flowrate data of vehicle flowrate monitoring point, then the weight coefficient of each vehicle flowrate monitoring point comprehensive and its right
The dynamic change function answered comprehensively estimates function to set up；
Demand estimates module：The corresponding data of each vehicle flowrate monitoring point is substituted into and comprehensively estimates function by it, thus estimating parking
Amount data.
7. parking demand estimating device as claimed in claim 6 is it is characterised in that described coefficient determination module includes time delay system
Number determining module：It obtains each peak value of the parking capacity curve of cyclical fluctuations and the peak value of the vehicle flowrate curve of cyclical fluctuations, if any one ripple
The peak value of moving curve and be single deviation with the peak value of its immediate curve of cyclical fluctuations difference on a timeline, adjustment is stopped
The time shafts of the amount curve of cyclical fluctuations and/or the vehicle flowrate curve of cyclical fluctuations are until all single deviations are less than threshold value and all single inclined
Difference and be adjusted to minimum, then the adjustment amount according to now time shafts is determining time delay coefficient.
8. parking demand estimating device as claimed in claim 6 is it is characterised in that described dynamic change function is fT(i)=K
(iT-t), wherein t is time delay coefficient, and K is constant.
9. parking demand estimating device as claimed in claim 6 is it is characterised in that described vehicle flowrate monitoring point is based on radio frequency vapour
Car electronic mark.
10. parking demand estimating device as claimed in claim 6 is it is characterised in that described curve of cyclical fluctuations generation module includes
Data filters module：The section that the stability bandwidth of the parking capacity curve of cyclical fluctuations is less than fluctuation threshold is filtered by it.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610799062.2A CN106447082A (en) | 2016-08-31 | 2016-08-31 | Parking demand pre-estimation method and parking demand pre-estimation device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610799062.2A CN106447082A (en) | 2016-08-31 | 2016-08-31 | Parking demand pre-estimation method and parking demand pre-estimation device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447082A true CN106447082A (en) | 2017-02-22 |
Family
ID=58165168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610799062.2A Pending CN106447082A (en) | 2016-08-31 | 2016-08-31 | Parking demand pre-estimation method and parking demand pre-estimation device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447082A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229739A (en) * | 2017-12-29 | 2018-06-29 | 深圳春沐源控股有限公司 | Crop yield prediction method, terminal and computer readable storage medium |
| WO2019241974A1 (en) * | 2018-06-21 | 2019-12-26 | 深圳先进技术研究院 | Parking lot data repair method and apparatus, device and storage medium |
-
2016
- 2016-08-31 CN CN201610799062.2A patent/CN106447082A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229739A (en) * | 2017-12-29 | 2018-06-29 | 深圳春沐源控股有限公司 | Crop yield prediction method, terminal and computer readable storage medium |
| WO2019241974A1 (en) * | 2018-06-21 | 2019-12-26 | 深圳先进技术研究院 | Parking lot data repair method and apparatus, device and storage medium |
| US11295619B2 (en) | 2018-06-21 | 2022-04-05 | Shenzhen Institutes Of Advanced Technology | Parking lot data repair method and apparatus, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107933317B (en) | Method, device and equipment for estimating remaining driving range and pure electric vehicle | |
| CN108819722A (en) | A kind of electric car course continuation mileage predictor method | |
| CN107458259A (en) | A kind of New-energy electric vehicle remaining mileage evaluation method | |
| DE112016006295T5 (en) | CLOUD-BASED DYNAMIC SYSTEM AND METHOD FOR VEHICLE SHARING | |
| CN109291826B (en) | Method and device for automatically searching charging equipment according to characteristics of electric vehicle | |
| US11858377B2 (en) | Information provision service system for electric vehicle using vehicle sensors | |
| CN102622880A (en) | Traffic information data recovery method and device | |
| CN103280110B (en) | The Forecasting Methodology and device of expressway travel time | |
| CA3015320C (en) | Road monitoring method and system | |
| US20220035778A1 (en) | Methods and systems for fixed interpolation error data simplification processes for telematics | |
| US20200320874A1 (en) | System to optimize scats adaptive signal system using trajectory data | |
| CN111301172B (en) | Estimation method, device, equipment and storage medium of driving range | |
| CN106447082A (en) | Parking demand pre-estimation method and parking demand pre-estimation device | |
| WO2022156583A1 (en) | Method and apparatus for predicting average energy consumption of an electric vehicle | |
| CN108831181A (en) | A kind of method for establishing model and system for Forecasting of Travel Time for Public Transport Vehicles | |
| CN104751650A (en) | Method and equipment for controlling road traffic signals | |
| CN103530190B (en) | A kind of load predicting method and device | |
| CN112257936B (en) | Recommendation method and device for order receiving area, electronic equipment and storage medium | |
| CN104050349B (en) | External air temperature measuring apparatus and method | |
| CN106528553A (en) | A running signal processing method and device | |
| CN113361810A (en) | Passenger flow volume prediction method, device, equipment and storage medium | |
| US20080015924A1 (en) | Tire market forecasting method | |
| Klunder et al. | The effect of inaccurate traffic data for ramp metering: Comparing loop detectors and cameras using information utility | |
| CN114741806A (en) | Suspension optimization method, system, device, equipment and medium | |
| CN115685932A (en) | Logistics information intelligent management system and method based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |