CN107134170A - A kind for the treatment of method and apparatus of parking position information of park - Google Patents
A kind for the treatment of method and apparatus of parking position information of park Download PDFInfo
- Publication number
- CN107134170A CN107134170A CN201710538059.XA CN201710538059A CN107134170A CN 107134170 A CN107134170 A CN 107134170A CN 201710538059 A CN201710538059 A CN 201710538059A CN 107134170 A CN107134170 A CN 107134170A
- Authority
- CN
- China
- Prior art keywords
- time series
- parking stall
- remaining
- parking
- remaining parking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
Abstract
The invention discloses a kind for the treatment of method and apparatus of parking position information of park, including：The remaining parking stall number information of history is obtained from the database for preserving specified parking position information of park；The remaining parking stall array got is handled into time series and to time series, autoregressive moving-average model is built according to the time series after processing；Time variable is inputted to the autoregressive moving-average model built, the remaining parking stall number in parking lot described in the same day predicted and afterwards predetermined number of days.The technical scheme of the embodiment of the present invention can be predicted to the remaining parking stall number in parking lot, facilitated car owner user and stopped according to remaining parking stall number.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind for the treatment of method and apparatus of parking position information of park.
Background technology
With economic fast development and the raising of living standards of the people, increasing people has the ability buying car, vehicle
Increase the nervous problem in the congestion problems that result in city and parking stall, many times car owner is to look for parking stall to worry.
Therefore, it is necessary to propose a kind of technical scheme for handling parking position information of park to meet user's parking need
Ask.
The content of the invention
The invention provides a kind for the treatment of method and apparatus of parking position information of park, the remaining parking stall number in parking lot is entered
Row prediction, facilitates car owner user to stop.
According to an aspect of the invention, there is provided a kind of processing method of parking position information of park, including：
The remaining parking stall number information of history is obtained from the database for preserving specified parking position information of park；
The remaining parking stall array got is handled into time series and to time series, according to the time after processing
Sequence construct autoregressive moving-average model；
Time variable is inputted to the autoregressive moving-average model built, the same day predicted and made a reservation for afterwards
The remaining parking stall number in parking lot described in number of days.
According to a further aspect of the invention there is provided a kind of processing unit of parking position information of park, including：
Information acquisition unit, for obtaining the remaining parking stall number of history from the database for specifying parking position information of park is preserved
Information；
Model construction unit, at by the remaining parking stall array got into time series and to time series
Reason, autoregressive moving-average model is built according to the time series after processing；
Predicting unit, for time variable to be inputted into the autoregressive moving-average model built, that is predicted works as
It and the remaining parking stall number in parking lot described in predetermined number of days afterwards.
The beneficial effects of the invention are as follows：The treating method and apparatus of the parking position information of park of the embodiment of the present invention, is obtained
History residue parking stall number information, builds by the remaining parking stall array got into time series and after handling time series
Autoregressive moving-average model, it is that can be predicted to obtain the surplus of parking lot that time variable then is inputted into autoregressive moving-average model
Remaining parking stall number, so that the remaining parking space information for meeting the user for wanting the Parking obtains demand, improves parking
The service level of field.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the processing method of the parking position information of park of one embodiment of the invention；
Fig. 2 is the flow chart of the autoregressive moving-average model structure of one embodiment of the invention；
Fig. 3 is the block diagram of the processing unit of the parking position information of park of one embodiment of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
Referring to Fig. 1, the processing method of parking position information of park comprises the following steps in one embodiment：
Step S101, obtains the remaining parking stall number information of history from the database for preserving specified parking position information of park；
Step S102, the remaining parking stall array got is handled into time series and to time series, according to place
Time series after reason builds autoregressive moving-average model；
Step S103, by time variable input build the autoregressive moving-average model, the same day predicted with
And the remaining parking stall number in parking lot described in predetermined number of days afterwards.
Understand as shown in Figure 1, the processing method of the parking position information of park of the present embodiment, by obtaining history residue parking
The information of the quantity of position, after handling remaining parking space information builds autoregressive moving-average model, using structure from
Regressive averaging model was to following one day or the remaining parking stall number in the parking lot is predicted within these few days, facilitated parking lot to manage
Reason side grasps remaining parking stall number, has been also convenient for car owner user to before the Parking, has understood how many remaining car gone back in time
Digit, improves satisfaction of the car owner user to parking, also improves the market competitiveness in parking lot.
In one embodiment, the parking position information of park processing of the present embodiment is i.e. pre- according to the remaining parking stall number of parking lot history
The remaining parking stall number in the following several days parking lots is surveyed, is realized based on autoregressive moving-average model.Autoregressive moving-average model,
Also known as arma modeling (Auto-Regressive Moving Average Mode), the one kind belonged in time series analysis.
Referring to Fig. 2, building the specific steps of autoregressive moving-average model includes：Flow starts, and first carries out step S201,
Step S201, obtains historical data；
Here historical data refers to the remaining parking stall number of the history in parking lot, for example, the A parking lots of Zhongguancun Area are in mistake
Go the remaining parking stall number of each minute within N days.
Here N can be equal to 60, i.e. the remaining parking stall number of each minute in past 60 days be obtained, then by each point
The remaining parking stall number of clock is expressed as time series.
Here parking stall number that remaining parking stall number refers to the free time, not parking cars.
By obtaining the historical data (equivalent to sample) of 60 days, predicated error is reduced, accuracy is improved.
It should be noted that carried out by taking the remaining parking stall number of each minute in past 60 days as an example in the present embodiment
Schematically illustrate, in other embodiments of the invention, the historical data not limited to this of acquisition can for example obtain over 30 days
It is interior, remaining parking stall number per half an hour etc..
Step S202, judges whether steady；It is then to perform step S204, otherwise performs step S203；
Time series is steadily the premise of modeling, is also the primary step of prediction to the judgement that time series carries out stationarity
Suddenly.In general, so-called stationary time series refers to wide stationary processes.Each variable in stationary sequence occasion, time series
Some features such as average it is identical, when estimating these features, the observation of each variable can be regarded as same variable not
Handled with observation, add sample size, improve estimated accuracy.
There are several determination methods：The first is datagram Direct Test method.The image of time series is drawn, when each sample
The fluctuation above and below certain level line and rise, decline or during cyclical trend without obvious, then it is assumed that time series is stable.The
Two kinds are auto-correlation, deviation―related function method of inspection.The auto-correlation function and partial autocorrelation function of one zero-mean stationary sequence will
It is truncation, otherwise it is hangover.Therefore, if a sequence zero averaging later auto-correlation function or partial autocorrelation letter
Number neither truncation, and do not trail, it is non-stable for can be concluded that the sequence.The third is characteristic root test method.First it is fitted sequence
Adaptive model, the characteristic root for the characteristic equation being made up of the parameter of adaptive model is then sought, if all characteristic roots are all met
Stationarity condition, then it is believed that the sequence is stable, otherwise the sequence is non-stable.
To time series carry out stationarity judgement after, if current time series is jiggly, need into
Row calm disposing.Calculus of differences processing is carried out to time series in the present embodiment.
Step S203, calculus of differences；
Calculus of differences has the ability of information extraction, and the sequence of non-stationary finally can all show that it is put down by calculus of differences
Steady sequence.The specific calculating process of calculus of differences may refer to explanation of the prior art when building arma modeling, here not
Repeat.
Step S204, white noise verification；By then performing end flow；Not by then performing step S205；
After by step S203, stable time series, i.e. difference sequence can be obtained.
The foundation of arma modeling is a process adapted to repeatedly, by assuming that examining to detect mould after model is obtained
The conspicuousness of type.The significance test of model is that the analysis based on residual sequence is obtained, if residual sequence is white noise,
Such model is exactly valid model, otherwise residual sequence is not white noise, illustrates that such model is effective not enough, generally needs
Other models of reselection are wanted to be fitted again.
In the present embodiment, information useful in time series is illustrated if the inspection that time series have passed through white noise
Finished through being extracted, remaining is random perturbation, it is impossible to predicts and uses.Difference sequence (that is, have passed through after calculus of differences
Time series) if having passed through white noise verification, modeling can just terminate, because no information can continue to extract.
For white noise verification, by assuming that examining to complete, such as in the present embodiment：Assume initially that the aobvious of specification test
Work level is p=0.05.Carry out finding that its statistic is 190 after significantly examining, search level of signifiance table and find its corresponding p value
Far smaller than 0.01, because p value (being less than 0.01) is inconsistent with null hypothesis (p=0.05), then releases model and have rejected it is assumed that institute
Using it is assumed that difference sequence is nonwhite noise.
Step S205, is fitted arma modeling.
In this step, it is determined that difference sequence white noise verification not by when, the coefficient of its partial autocorrelation will be investigated
Property, by corresponding computer software (as SAS/ETS softwares), calculates its corresponding arma modeling, relevant to build ARMA
The more details of model may refer to explanation of the prior art, be not repeated herein.
After arma modeling is obtained, according to this arma modeling, you can remaining parking space number evidence is predicted and estimated.
For example, after arma modeling is constructed according to step shown in Fig. 2, the step-length that arma modeling is predicted is 3 days, i.e. prediction is not
The tendency come in 3 days, so as to predict the remaining parking stall in the parking lot.
In one embodiment, in order to meet the same day of prediction in the information acquisition request of car owner user, the present embodiment
And the remaining parking stall number in predetermined number of days parking lot is sent to the intelligent movable of each parking user in parking lot by network afterwards
In terminal (such as smart mobile phone).So, user can understand that desired stopped in time by the smart mobile phone of oneself and stop
The remaining parking stall number in parking lot, facilitates user's parking, improves the service level in parking lot.
Fig. 3 is the block diagram of the processing unit of the parking position information of park of one embodiment of the invention, referring to Fig. 3, the parking
The processing unit 300 of field parking space information includes：
Information acquisition unit 301, for obtaining the remaining car of history from the database for specifying parking position information of park is preserved
Digit information；
Model construction unit 302, for by the remaining parking stall array got into time series and to time series carry out
Processing, autoregressive moving-average model is built according to the time series after processing；
Predicting unit 303, for time variable to be inputted into the autoregressive moving-average model built, is predicted
The remaining parking stall number in parking lot described in the same day and afterwards predetermined number of days.
In one embodiment, information acquisition unit 301, specifically for each minute is corresponding in N days before obtaining the same day
Remaining parking stall number, the N is the positive integer more than zero, and such as N is equal to 60.
In one embodiment, model construction unit 302, specifically for judging whether the time series meets stationarity bar
Part, otherwise, carries out calculus of differences；Be then, to the time series carry out white noise verification, the test fails then according to it is described when
Between sequence construct autoregressive moving-average model, upcheck, terminate.
In one embodiment, in addition to：Release unit, for being stopped by the same day of prediction and afterwards described in predetermined number of days
The remaining parking stall number of field is sent on the mobile intelligent terminal of each parking user in the parking lot by network.
It should be noted that for device embodiment, because it corresponds essentially to embodiment of the method, so correlation
Place illustrates referring to the part of embodiment of the method, will not be repeated here.
In summary, the treating method and apparatus of the parking position information of park of the embodiment of the present invention, based on the remaining car of history
Digit, builds autoregressive moving-average model, then predicts the remaining parking stall number in parking lot, meets and want to the parking lot to stop
The remaining parking space information of the user of car obtains demand, improves the service level in parking lot.
The foregoing is only a specific embodiment of the invention, under the above-mentioned teaching of the present invention, those skilled in the art
Other improvement or deformation can be carried out on the basis of above-described embodiment.It will be understood by those skilled in the art that above-mentioned tool
The purpose of the present invention is simply preferably explained in body description, and protection scope of the present invention is defined by scope of the claims.
Claims (10)
1. a kind of processing method of parking position information of park, it is characterised in that including：
The remaining parking stall number information of history is obtained from the database for preserving specified parking position information of park；
The remaining parking stall array got is handled into time series and to time series, according to the time series after processing
Build autoregressive moving-average model；
Time variable is inputted to the autoregressive moving-average model built, the afterwards same day predicted and predetermined number of days
The remaining parking stall number in the parking lot.
2. according to the method described in claim 1, it is characterised in that obtaining the remaining parking stall data of history includes：
Each minute corresponding remaining parking stall number in N days before obtaining the same day, the N is the positive integer more than zero.
3. method according to claim 2, it is characterised in that the remaining parking stall array got is gone forward side by side into time series
Row data processing includes：
Judge whether the time series meets stationarity condition, otherwise, carry out calculus of differences；
It is then, white noise verification to be carried out to the time series, the test fails then builds autoregression according to the time series
Moving average model, upchecks, and terminates.
4. according to the method described in claim 1, it is characterised in that this method also includes：By same day of prediction and pre- afterwards
The intelligent movable for each parking user that the remaining parking stall number for determining parking lot described in number of days is sent to the parking lot by network is whole
On end.
5. method according to claim 2, it is characterised in that the N is equal to 60.
6. a kind of processing unit of parking position information of park, it is characterised in that including：
Information acquisition unit, for obtaining the remaining parking stall number letter of history from the database for specifying parking position information of park is preserved
Breath；
Model construction unit, for by the remaining parking stall array got is into time series and handles time series, root
Autoregressive moving-average model is built according to the time series after processing；
Predicting unit, for by time variable input build the autoregressive moving-average model, the same day predicted with
And the remaining parking stall number in parking lot described in predetermined number of days afterwards.
7. device according to claim 6, it is characterised in that described information acquiring unit, specifically for obtaining the same day
Each minute corresponding remaining parking stall number in first N days, the N is the positive integer more than zero.
8. device according to claim 7, it is characterised in that the model construction unit, during specifically for judging described
Between sequence whether meet stationarity condition, otherwise, carry out calculus of differences；It is then, white noise verification to be carried out to the time series,
The test fails then builds autoregressive moving-average model according to the time series, upchecks, terminates.
9. device according to claim 6, it is characterised in that also include：Release unit, for by the same day of prediction and
The remaining parking stall number in parking lot described in predetermined number of days is sent to the movement of each parking user in the parking lot by network afterwards
On intelligent terminal.
10. device according to claim 7, it is characterised in that the N is equal to 60.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710538059.XA CN107134170A (en) | 2017-07-04 | 2017-07-04 | A kind for the treatment of method and apparatus of parking position information of park |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710538059.XA CN107134170A (en) | 2017-07-04 | 2017-07-04 | A kind for the treatment of method and apparatus of parking position information of park |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107134170A true CN107134170A (en) | 2017-09-05 |
Family
ID=59736687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710538059.XA Pending CN107134170A (en) | 2017-07-04 | 2017-07-04 | A kind for the treatment of method and apparatus of parking position information of park |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107134170A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108091166A (en) * | 2017-12-25 | 2018-05-29 | 中国科学院深圳先进技术研究院 | Forecasting Methodology, device, equipment and the storage medium of available parking places number of variations |
| CN110164171A (en) * | 2019-04-18 | 2019-08-23 | 孙进 | A kind of parking stall distribution method, parking stall distribution system and storage medium |
| CN111079962A (en) * | 2019-12-02 | 2020-04-28 | 北京停简单信息技术有限公司 | Parking reservation method and device |
| CN112613802A (en) * | 2021-01-08 | 2021-04-06 | 王刚 | Parking space layout information generation method and three-dimensional parking system |
| CN113223291A (en) * | 2021-03-19 | 2021-08-06 | 青岛亿联信息科技股份有限公司 | System and method for predicting number of free parking spaces in parking lot |
| CN113838303A (en) * | 2021-09-26 | 2021-12-24 | 千方捷通科技股份有限公司 | Parking lot recommendation method and device, electronic equipment and storage medium |
| CN115050210A (en) * | 2022-06-07 | 2022-09-13 | 杭州市城市大脑停车系统运营股份有限公司 | Parking lot intelligent induction method, system and device based on time sequence prediction |
| CN117649781A (en) * | 2024-01-30 | 2024-03-05 | 泰安市东信智联信息科技有限公司 | Intelligent parking monitoring data intelligent processing method based on data fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295888A (en) * | 2016-08-12 | 2017-01-04 | 东南大学 | A kind of public building based on measured data is joined and is built parking position and share time window and determine method |
| CN106503840A (en) * | 2016-10-17 | 2017-03-15 | 中国科学院深圳先进技术研究院 | Parking stall Forecasting Methodology and system can be used in parking lot |
-
2017
- 2017-07-04 CN CN201710538059.XA patent/CN107134170A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295888A (en) * | 2016-08-12 | 2017-01-04 | 东南大学 | A kind of public building based on measured data is joined and is built parking position and share time window and determine method |
| CN106503840A (en) * | 2016-10-17 | 2017-03-15 | 中国科学院深圳先进技术研究院 | Parking stall Forecasting Methodology and system can be used in parking lot |
Non-Patent Citations (1)
| Title |
|---|
| 张雷: "基于时间序列模型的停车场泊位特性预测研究", 《南京师大学报(自然科学版)》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108091166A (en) * | 2017-12-25 | 2018-05-29 | 中国科学院深圳先进技术研究院 | Forecasting Methodology, device, equipment and the storage medium of available parking places number of variations |
| CN110164171A (en) * | 2019-04-18 | 2019-08-23 | 孙进 | A kind of parking stall distribution method, parking stall distribution system and storage medium |
| CN111079962A (en) * | 2019-12-02 | 2020-04-28 | 北京停简单信息技术有限公司 | Parking reservation method and device |
| CN112613802A (en) * | 2021-01-08 | 2021-04-06 | 王刚 | Parking space layout information generation method and three-dimensional parking system |
| CN113223291A (en) * | 2021-03-19 | 2021-08-06 | 青岛亿联信息科技股份有限公司 | System and method for predicting number of free parking spaces in parking lot |
| CN113223291B (en) * | 2021-03-19 | 2023-10-20 | 青岛亿联信息科技股份有限公司 | System and method for predicting number of idle parking spaces in parking lot |
| CN113838303A (en) * | 2021-09-26 | 2021-12-24 | 千方捷通科技股份有限公司 | Parking lot recommendation method and device, electronic equipment and storage medium |
| CN113838303B (en) * | 2021-09-26 | 2023-04-28 | 千方捷通科技股份有限公司 | Parking lot recommendation method and device, electronic equipment and storage medium |
| CN115050210A (en) * | 2022-06-07 | 2022-09-13 | 杭州市城市大脑停车系统运营股份有限公司 | Parking lot intelligent induction method, system and device based on time sequence prediction |
| CN115050210B (en) * | 2022-06-07 | 2023-10-20 | 杭州市城市大脑停车系统运营股份有限公司 | Parking lot intelligent induction method, system and device based on time sequence prediction |
| CN117649781A (en) * | 2024-01-30 | 2024-03-05 | 泰安市东信智联信息科技有限公司 | Intelligent parking monitoring data intelligent processing method based on data fusion |
| CN117649781B (en) * | 2024-01-30 | 2024-04-16 | 泰安市东信智联信息科技有限公司 | Intelligent parking monitoring data intelligent processing method based on data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107134170A (en) | A kind for the treatment of method and apparatus of parking position information of park | |
| CN106503840B (en) | Available parking space prediction method and system for parking lot | |
| CN110894038B (en) | Method and device for predicting running state of elevator door system | |
| DE102017223856A1 (en) | Dialogue system, vehicle with this and dialogue processing method | |
| CN110147367B (en) | Temperature missing data filling method and system and electronic equipment | |
| CN109933852B (en) | Method and device for predicting vehicle size deviation, storage medium and electronic equipment | |
| CN108829778A (en) | Charging pile intelligent recommendation methods, devices and systems | |
| CN104599002B (en) | Method and equipment for predicting order value | |
| CN105144174A (en) | Bioage prediction apparatus and method | |
| WO2021179818A1 (en) | Travel state recognition method and apparatus, and terminal and storage medium | |
| CN103678869A (en) | Prediction and estimation method of flight parameter missing data | |
| CN110852476A (en) | Passenger flow prediction method and device, computer equipment and storage medium | |
| CN107025576A (en) | The push control method of carwash information on services, apparatus and system | |
| CN111985452B (en) | Automatic generation method and system for personnel movement track and foot drop point | |
| CN109308343A (en) | A kind of Forecasting of Travel Time and degree of reiability method based on Stochastic Volatility Model | |
| CN113988441A (en) | Power wireless network link quality prediction and model training method and device | |
| CN104618949A (en) | Complaint predicting method and device based on ARMA model | |
| CN115050210A (en) | Parking lot intelligent induction method, system and device based on time sequence prediction | |
| CN114330120A (en) | 24-hour PM prediction based on deep neural network2.5Method of concentration | |
| CN109995549B (en) | Method and device for evaluating flow value | |
| CN112785044B (en) | Real-time full-load rate prediction method, device, equipment and medium for public transport means | |
| CN113779391A (en) | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium | |
| CN114154622A (en) | Algorithm model for traffic operation system flow data acquisition missing completion | |
| CN114239952A (en) | Method, device, equipment and medium for detecting abnormity of key performance index | |
| CN113986700A (en) | Data acquisition frequency optimization method, system, device and storage medium |
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: 20170905 |