CN107832866A - A kind of method for predicting and device, storage medium, terminal - Google Patents
A kind of method for predicting and device, storage medium, terminal Download PDFInfo
- Publication number
- CN107832866A CN107832866A CN201710881422.8A CN201710881422A CN107832866A CN 107832866 A CN107832866 A CN 107832866A CN 201710881422 A CN201710881422 A CN 201710881422A CN 107832866 A CN107832866 A CN 107832866A
- Authority
- CN
- China
- Prior art keywords
- predeterminable area
- flow rate
- real
- characteristic parameter
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000008859 change Effects 0.000 claims description 59
- 230000004907 flux Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 9
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of method for predicting and device, storage medium, terminal, methods described include:Obtain the real-time traffic data in predeterminable area;Type based on the real-time traffic data and changes in flow rate of the predeterminable area determines predictor formula in history;According to predeterminable area described in the predictor formula and real-time traffic data prediction in the flow of following special time period.Can be according to the flow for precisely predicting predeterminable area in following random time section by scheme provided by the invention, also, corresponding to the different types of real-time traffic data of access, can flexibly obtain different types of volume forecasting result.
Description
Technical field
The present invention relates to big data application field, more particularly to a kind of method for predicting and device, storage medium, end
End.
Background technology
Flux prediction model is more and more applied to daily life.For example, in the scene of smart city, can
With the prediction by the inlet flow rate to specific region, prediction of wagon flow flow to specific region etc., with information and communication
Technological means is made rational planning for the running of city items function, and then creates more good days for the people in city, promotes city
Harmony, Sustainable Growth.
But existing volume forecasting scheme generally existing precision of prediction it is low, can not be flexible with the prediction logic of standardization
Suitable for different types of volume forecasting demand.
The content of the invention
Present invention solves the technical problem that it is how a kind of flux prediction model is provided, so as to improve the same of precision of prediction
When, corresponding to different data types, the property of can adapt to obtains different types of volume forecasting result.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of method for predicting, including:Obtain predeterminable area
Interior real-time traffic data;The changes in flow rate of type based on the real-time traffic data and the in history predeterminable area is true
Determine predictor formula;According to predeterminable area described in the predictor formula and real-time traffic data prediction in the stream of following special time period
Amount.
Optionally, the real-time traffic data obtained in predeterminable area include:Divided on default longitude and latitude flowmeter,
To obtain at least one predeterminable area, the difference between the flux density of each predeterminable area is not more than predetermined threshold value;For each
Individual predeterminable area, the real-time traffic data of the predeterminable area are obtained based on the default longitude and latitude flowmeter.
Optionally, the type based on the real-time traffic data and the in history changes in flow rate of the predeterminable area
Determine that predictor formula includes:Based on the changes in flow rate of the predeterminable area and its neighboring area in history, at least one spy is predicted
Levy predicted flow rate change of the parameter in following special time period;Changes in flow rate based on the predeterminable area in history determines every
The weight of one characteristic parameter;The preset formula is determined based on each characteristic parameter and its weight, wherein, the preset formula is
Linear formula.
Optionally, the predicted flow rate change of the characteristic parameter is influenceed by least one reference factor, and described at least one
Individual reference factor determines according to the type of the real-time traffic data.
Optionally, the reference factor includes following one or more:Weather conditions, festivals or holidays factor and traffic congestion because
Element.
Optionally, the predicted flow rate change of the characteristic parameter comprises at least:Predicted flow rate inside the predeterminable area
Change;The borderline predicted flow rate change of predeterminable area.
Optionally, when the predicted flow rate of the characteristic parameter becomes the predicted flow rate change turned to inside predeterminable area, institute
State based on the changes in flow rate of the predeterminable area and its neighboring area in history, predict at least one characteristic parameter following specific
Predicted flow rate change in period includes:Data on flows training based on the predeterminable area in history obtains time series mould
Type, the time series models are used for the changes in flow rate trend for describing the predeterminable area;Flow based on the predeterminable area
Predicted flow rate change of the trend inside the predeterminable area in following special time period.
Optionally, when the predicted flow rate change of the characteristic parameter, which turns to the borderline predicted flow rate of predeterminable area, to be changed,
It is described based on the changes in flow rate of the predeterminable area and its neighboring area in history, predict at least one characteristic parameter following special
The predicted flow rate in section of fixing time change includes:Based on the data on flows of the predeterminable area and its neighboring area in history, really
The borderline flow for being positioned at the predeterminable area enters the probability of the predeterminable area.
Optionally, the data on flows is vector data.
Optionally, the probability is determined based on pre-programmed curve, and the pre-programmed curve is determined based on day type.
Optionally, the day type is selected from:Working day, weekend and festivals or holidays.
Optionally, the changes in flow rate based on the predeterminable area in history determines the weight bag of each characteristic parameter
Include:The preset formula is tested by multivariate logistic regression algorithm, it is described described default in history to determine to best suit
The benchmark preset formula of the changes in flow rate in region;Weight based on each characteristic parameter in the benchmark preset formula determines each spy
Levy the weight of parameter.
Optionally, the type of the real-time traffic data is selected from:The information point data of mobile device;The monitoring number of vehicle
According to.
The embodiment of the present invention also provides a kind of volume forecasting device, including:Acquisition module, for obtaining in predeterminable area
Real-time traffic data;Determining module, for the type based on the real-time traffic data and in history predeterminable area
Changes in flow rate determines predictor formula;Prediction module, for being preset according to the predictor formula and real-time traffic data prediction
Flow of the region in following special time period.
Optionally, the acquisition module includes:Submodule is divided, for being divided on default longitude and latitude flowmeter, to obtain
At least one predeterminable area, the difference between the flux density of each predeterminable area are not more than predetermined threshold value;Acquisition submodule is right
In each predeterminable area, the real-time traffic data based on the default longitude and latitude flowmeter acquisition predeterminable area.
Optionally, the determining module includes:Submodule is predicted, for based on the predeterminable area and its periphery in history
The changes in flow rate in region, predict predicted flow rate change of at least one characteristic parameter in following special time period;First determines
Submodule, the weight of each characteristic parameter is determined for the changes in flow rate based on the predeterminable area in history;Second determines son
Module, for determining the preset formula based on each characteristic parameter and its weight, wherein, the preset formula is linear public
Formula.
Optionally, the predicted flow rate change of the characteristic parameter is influenceed by least one reference factor, and described at least one
Individual reference factor determines according to the type of the real-time traffic data.
Optionally, the reference factor includes following one or more:Weather conditions, festivals or holidays factor and traffic congestion because
Element.
Optionally, the predicted flow rate change of the characteristic parameter comprises at least:Predicted flow rate inside the predeterminable area
Change;The borderline predicted flow rate change of predeterminable area.
Optionally, when the predicted flow rate of the characteristic parameter becomes the predicted flow rate change turned to inside predeterminable area, institute
Stating prediction submodule includes:Training unit, time sequence is obtained for the data on flows training based on the predeterminable area in history
Row model, the time series models are used for the changes in flow rate trend for describing the predeterminable area;Predicting unit, for based on institute
Predicted flow rate of the changes in flow rate trend prediction of predeterminable area inside the predeterminable area in following special time period is stated to become
Change.
Optionally, when the predicted flow rate change of the characteristic parameter, which turns to the borderline predicted flow rate of predeterminable area, to be changed,
The prediction submodule includes:First determining unit, for based on the predeterminable area in history and its flow of neighboring area
Data, it is determined that the borderline flow positioned at the predeterminable area enters the probability of the predeterminable area.
Optionally, the data on flows is vector data.
Optionally, the probability is determined based on pre-programmed curve, and the pre-programmed curve is determined based on day type.
Optionally, the day type is selected from:Working day, weekend and festivals or holidays.
Optionally, first determination sub-module includes:Test cell, for by multivariate logistic regression algorithm to described
Preset formula is tested, to determine to best suit the benchmark preset formula of the changes in flow rate of the predeterminable area described in history;
Second determining unit, the power of each characteristic parameter is determined for the weight based on each characteristic parameter in the benchmark preset formula
Weight.
Optionally, the type of the real-time traffic data is selected from:The information point data of mobile device;The monitoring number of vehicle
According to.
The embodiment of the present invention also provides a kind of storage medium, is stored thereon with computer instruction, the computer instruction fortune
The step of above method is performed during row.
The embodiment of the present invention also provides a kind of terminal, including memory and processor, and being stored with the memory can
The computer instruction run on the processor, the processor perform the step of the above method when running the computer instruction
Suddenly.
Compared with prior art, the technical scheme of the embodiment of the present invention has the advantages that:
Obtain the real-time traffic data in predeterminable area;Type based on the real-time traffic data and described in history
The changes in flow rate of predeterminable area determines predictor formula;According to predeterminable area described in the predictor formula and real-time traffic data prediction
In the flow of following special time period.Needed than existing for the special flux prediction model of different types of design data
Scheme, the technical scheme of the embodiment of the present invention can make the type of the real-time traffic data of access it is determined that during predictor formula
For one of measurement factor, to determine more suitably predictor formula according to the type of the real-time traffic data so that it is determined that it is pre-
The type characteristic of real-time traffic data of access can preferably be met by surveying formula, and then obtains more accurately flow on this basis
Measure prediction result.It will be appreciated by those skilled in the art that can be following any according to accurate prediction by the scheme of the embodiment of the present invention
The flow of predeterminable area in period, also, corresponding to the different types of real-time traffic data of access, can be according to the reality
When data on flows type characteristic targetedly determine predictor formula, and then obtain different types of volume forecasting result.
Further, the real-time traffic data obtained in predeterminable area can include:On default longitude and latitude flowmeter
Division, to obtain at least one predeterminable area, the difference between the flux density of each predeterminable area is not more than predetermined threshold value;For
Each predeterminable area, the real-time traffic data of the predeterminable area are obtained based on the default longitude and latitude flowmeter.Than existing
There is the scheme that volume forecasting is carried out in units of a single point, can be reasonable according to flux density using the scheme of the embodiment of the present invention
Predeterminable area is divided, so as to effectively avoid producing sparse matrix, provides more preferable data basis for follow-up volume forecasting, greatly
Improve the precision of follow-up volume forecasting.
Brief description of the drawings
Fig. 1 is a kind of flow chart of method for predicting of the first embodiment of the present invention;
Fig. 2 is inlet flow rate's versus time curve in history in first embodiment of the invention;
Fig. 3 is a kind of structural representation of volume forecasting device of the second embodiment of the present invention.
Embodiment
It will be appreciated by those skilled in the art that as background technology is sayed, existing flux prediction model is mostly for certain kinds
The design data of type.In actual applications, for different types of access data, user needs to train different models to come pair
Different types of access data carry out volume forecasting, cause to train cost increase, influence the application of flux prediction model.
Further, generally also there is the problem of precision of prediction is low in existing flux prediction model, cause to accessing data
Prediction result it is inaccurate, influence the use feeling of user.
In order to solve this technical problem, the technical scheme of the embodiment of the present invention obtains the real-time traffic number in predeterminable area
According to;Type based on the real-time traffic data and changes in flow rate of the predeterminable area determines predictor formula in history;Root
According to predeterminable area described in the predictor formula and real-time traffic data prediction in the flow of following special time period.
It will be appreciated by those skilled in the art that the technical scheme of the embodiment of the present invention will can access it is determined that during predictor formula
Real-time traffic data type as one of measurement factor, to be determined more suitably according to the type of the real-time traffic data
Predictor formula so that it is determined that predictor formula can preferably meet access real-time traffic data type characteristic, Jin Er
More accurately volume forecasting result is obtained on the basis of this.
Further, can be according to precisely predicting preset areas in following random time section by the scheme of the embodiment of the present invention
The flow in domain, also, corresponding to the different types of real-time traffic data of access, can be according to the class of the real-time traffic data
Type feature targetedly determines predictor formula, and then obtains different types of volume forecasting result.
It is understandable to enable above-mentioned purpose, feature and the beneficial effect of the present invention to become apparent, below in conjunction with the accompanying drawings to this
The specific embodiment of invention is described in detail.
Fig. 1 is a kind of flow chart of method for predicting of the first embodiment of the present invention.Wherein, the flow can be
Pass through the physical quantities of predeterminable area in preset time;The object can include vehicle, pedestrian etc..
Specifically, the present embodiment can be according to the different types of data on flows (can be referred to as data) of access, in advance
Survey predicted flow rate of the type in following special time period on predeterminable area.For example, when the stream of input (alternatively referred to as accessing)
Data are measured when be population data on flows, can be using described in the present embodiment in program prediction future special time period on predeterminable area
Inlet flow rate;In another example when the data on flows of input is flow motor (can be referred to as wagon flow), this implementation can be used
Wagon flow in the example program prediction future special time period on predeterminable area.
Next the idiographic flow of the present embodiment is specifically described using forecasted population flow as example.It is pointed out that institute
The inlet flow rate and flow motor can be not limited only to by stating the type of data on flows.In actual applications, people in the art
Member can input other kinds of data on flows as needed, and the flow that corresponding types are obtained with the scheme based on the present embodiment is pre-
Result is surveyed, will not be described here.
More specifically, in the present embodiment, the method for predicting may include steps of:
Step S101, obtain the real-time traffic data in predeterminable area.
Step S102, the changes in flow rate of type based on the real-time traffic data and the in history predeterminable area are true
Determine predictor formula.
Step S103, according to predeterminable area described in the predictor formula and real-time traffic data prediction in following special time
The flow of section (alternatively referred to as preset time period).
Further, the real-time traffic data can be mobile information point (Point of Interest, abbreviation
POI, alternatively referred to as point of interest) data, it is described default by being determined with the information exchange of object to be predicted in the predeterminable area
The real-time traffic data of the object to be predicted in region.Preferably, the information point data of the movement can be set including user
Standby interaction data;The monitoring data of vehicle can also be included.
For example, it is necessary to obtain described default when it is desirable that predicting predeterminable area in the inlet flow rate of following special time period
The current real-time inlet flow rate in region, accordingly, the object to be predicted can be the people by the predeterminable area, then can be with
Data interaction of the communication apparatus (such as mobile phone, IPAD) between communication base station based on the people in the predeterminable area, obtain
The location information of the communication apparatus, so as to position communication apparatus quantity and the position in the predeterminable area, and then really
Real-time inlet flow rate in the fixed predeterminable area.Further, the real-time traffic data can also be vector data, that is, wrap
Moving direction containing the real-time traffic data.
In another example, it is necessary to obtain described default when it is desirable that predicting wagon flow of the predeterminable area in following special time period
The current real-time traffic flow data in region, accordingly, the object to be predicted can be (also may be used by the vehicle of the predeterminable area
Referred to as automobile), then the vehicle number that the predeterminable area can be passed through based on camera (such as monitoring camera) collection on road surface
According to, and then determine the real-time traffic flow in the predeterminable area.Wherein, the vehicle data can include, and the automobile of certain car plate exists
Time point A is by the camera on the B of section.
Further, the predeterminable area can be dynamically determined according to flux density, to avoid producing coefficient matrix, it is ensured that
Performing when the present embodiment is predicted can have enough basic datas (to be able to ensure that the real-time traffic data all the time
Data volume is sufficiently large).
As a non-limiting example, the step S101 can include:Divided on default longitude and latitude flowmeter,
To obtain at least one predeterminable area, the difference between the flux density of each predeterminable area is not more than predetermined threshold value;For each
Individual predeterminable area, the real-time traffic data of the predeterminable area are obtained based on the default longitude and latitude flowmeter.
Preferably, the default longitude and latitude flowmeter can include the real time position and mobile message for being identified with population
Map.Wherein, the map can be global map, or map of China, can also be the map of some specific region.
Preferably, the real time position of the population on the map can be based on latitude and longitude information acquisition.It is for example, described
Latitude and longitude information can (can such as be based on sending out to the user equipment by what the user device associations such as the mobile phone of user obtained
The broadcast message sent determines).For example, can be according to positional information (such as longitude and latitude identified in the default longitude and latitude flowmeter
Information) determine the inlet flow rate of predeterminable area described in current time.
Preferably, on the default longitude and latitude flowmeter, the area of population more intensive (i.e. the density of inlet flow rate is bigger)
Domain, the predeterminable area length of division are shorter (that is, the predeterminable area marked off is smaller);Population is more sparse, the predeterminable area of division
It is bigger, to ensure the density of the inlet flow rate in each predeterminable area marked off (density of population can be referred to as) basic phase
Together, so as to effectively avoid producing coefficient matrix.
Preferably, the predetermined threshold value can predefine, and in actual applications, user can also be to the predetermined threshold value
It is adjusted.
In another example user can initially provide the candidate's predeterminable area for wishing to predict, then scheme described in the present embodiment can be with
The geographic range for providing covering is more than the map for the scope that candidate's predeterminable area covers, to perform the step S101
When, the actual coverage of candidate's predeterminable area can be finely tuned according to the real-time inlet flow rate on the map with final true
The fixed predeterminable area, because the real-time inlet flow rate of the predeterminable area after adjustment is enough, it can be ensured that subsequent prediction
Precision.
As a non-limiting example, performing the step S101 to obtain the real-time traffic of the predeterminable area
After data, before performing the step S102, it can also include:Examine the real-time traffic data of the predeterminable area obtained
Whether Gaussian Profile, and the real-time traffic data fit Gaussian Profile of the predeterminable area in the detection determination acquisition are met
When, just perform the step S102;Otherwise, i.e., when testing result shows the real-time traffic data of the predeterminable area of acquisition not
When meeting the Gaussian Profile, the step S101 can be re-executed, to adjust the length of the predeterminable area, until obtaining
The predeterminable area real-time traffic data fit described in Gaussian Profile.
Preferably, can be based on the predeterminable area that K-S (Kolmogorov-Smirnov) test and judge obtains
Whether real-time traffic data meet Gaussian Profile.Those skilled in the art can also use other inspection parties according to being actually needed
Whether the real-time traffic data on the predeterminable area that method judges to obtain meet Gaussian Profile.
For example, the real-time traffic data on the predeterminable area that can first assume to obtain meet Gaussian Profile, so
Verify whether the real-time traffic data on the predeterminable area of acquisition actually meet Gaussian Profile using K-S hypothesis afterwards.
Specifically, if the real-time traffic data on the predeterminable area obtained examine the assumed value (p- calculated through K-S
Value) it is more than default tolerance, real-time traffic data fit Gaussian Profile on the predeterminable area that obtains can be received
It is assumed that the present embodiment can continue executing with the step S102 and step S103;Otherwise, the step S101 is re-executed, can
In a manner of the body of a map or chart covered by adjusting the predeterminable area, the real-time streams on the predeterminable area of acquisition are adjusted
Data are measured, until the real-time traffic data fit Gaussian Profile position on the predeterminable area obtained.Or re-executing
During the step S101, the predeterminable area temporarily can not also be adjusted, but is waited for a period of time, described when acquisition is preset
When real-time traffic data on region change, examine whether the real-time traffic data on the predeterminable area after change accord with
Close Gaussian Profile.
Wherein, the default tolerance can be used for the shortage of data for accommodating certain rank, so as to when the institute of the acquisition
The real-time traffic data on predeterminable area are stated when meeting Gaussian Profile in general trend, it is possible to continue subsequently to calculate.
Preferably, the default tolerance can be 0.05.
Preferably, all data that can include to the real-time traffic data on the predeterminable area of acquisition carry out K-S
Examine, to judge whether the real-time traffic data on the predeterminable area obtained meet Gaussian Profile;Or can also be from obtaining
A certain amount of data are randomly selected as sample data in the real-time traffic data on the predeterminable area taken, by detecting
State whether sample data meets Gaussian Profile to judge whether the real-time traffic data on the predeterminable area obtained meet height
This distribution.
Further, in the present embodiment, the type of the real-time traffic data can be population;Accordingly, it is described to go through
The changes in flow rate of the predeterminable area can include inlet flow rate's change of the predeterminable area in history in history.
Further, the predictor formula can be used for the inlet flow rate's changing rule for describing the predeterminable area.For example,
The predictor formula can be that inlet flow rate's change fitting of the predeterminable area in history according to obtains.
As a non-limiting example, the step S102 can include:Based on the predeterminable area in history and
The changes in flow rate of its neighboring area, predict predicted flow rate change of at least one characteristic parameter in following special time period;Base
The weight of each characteristic parameter is determined in the changes in flow rate of the predeterminable area in history;Based on each characteristic parameter and its weight
The preset formula is determined, wherein, the preset formula is linear formula.
Represented for example, the preset formula can be based on equation below:
Predicted flow rate change=∑ (characteristic parameter i predicted flow rate change × weight i) of predeterminable area;
Wherein, the characteristic parameter i is ith feature parameter;The weight i is weight corresponding to ith feature parameter.
Preferably, the characteristic parameter can include the inlet flow rate in the predeterminable area, can also include described pre-
If the inlet flow rate on zone boundary.Accordingly, predicted flow rate change of the characteristic parameter in following special time period can
With including:Predicted flow rate inside the predeterminable area in following special time period changes;Not on the predeterminable area border
Carry out the predicted flow rate change of special time period.
For example, above-mentioned predictor formula can be refined as equation below:
Forecasted population changes in flow rate × first weight+preset areas in predicted flow rate change=predeterminable area of predeterminable area
The weight of the borderline forecasted population changes in flow rate in domain × second;
Wherein, first weight is corresponding with the forecasted population changes in flow rate in the predeterminable area;Second power
Weight is corresponding with the borderline forecasted population changes in flow rate of the predeterminable area × second weight.
Further, the predicted flow rate change of the characteristic parameter can be influenceed by least one reference factor, described
At least one reference factor determines according to the type of the real-time traffic data.Preferably, the reference factor can include with
The next item down is multinomial:Weather conditions, festivals or holidays factor and traffic congestion factor.
For example, the predictor formula after above-mentioned refinement can be further refined as equation below:
The predicted flow rate change of predeterminable area=by the forecasted population changes in flow rate in the predeterminable area of inside even from weather
Forecasted population changes in flow rate × four weights+predeterminable area in the predeterminable area for × the three weight+influenceed by festivals or holidays factor
The weight of borderline forecasted population changes in flow rate × second;
Wherein, the 3rd weight and the forecasted population changes in flow rate phase in the predeterminable area by inside even from weather
It is corresponding;4th weight is corresponding with the forecasted population changes in flow rate in the predeterminable area influenceed by festivals or holidays factor.
It is similar, the borderline forecasted population changes in flow rate of predeterminable area can also be further refined as by weather because
The borderline forecasted population changes in flow rate of predeterminable area that element influences, and on the predeterminable area border influenceed by festivals or holidays factor
Forecasted population changes in flow rate.
Further, when prediction is wagon flow of the predeterminable area in following special time period, the reference factor may be used also
With including traffic congestion factor, traffic accident factor etc..
As a non-limiting example, when the predicted flow rate of the characteristic parameter become turn to it is pre- inside predeterminable area
When measurement of discharge changes, data on flows training that can be based on the predeterminable area in history obtains time series models, when described
Between series model can be used for the changes in flow rate trend that describes the predeterminable area;The flow for being then based on the predeterminable area becomes
Change predicted flow rate change of the trend prediction inside the predeterminable area in following special time period, with based on the time sequence
Row model, the changes in flow rate rule with reference to described in historical data analysis in predeterminable area, and then predict the predeterminable area not
Carry out the flow of special time period.
It will be appreciated by those skilled in the art that the time series models can be used for counting in predeterminable area one section in history
Data on flows in time.Specifically, can when observing the position data of inlet flow rate on the basis of the predeterminable area
The data more than comparison are collected into, by taking a long cycle (such as one month) as an example, can be shown in the form of statistical chart described pre-
If the situation of change of inlet flow rate's data in region, also, this change is usually regular.So it can use
Difference integrates rolling average autoregression (Autoregressive Integrated Moving Average Model, abbreviation
ARIMA) model, the predicted flow rate changing rule inside the predeterminable area is fitted based on historical data, it is described pre- so as to predict
If region is in the inlet flow rate of following special time period.
Further, the inlet flow rate in the predeterminable area be it is regular can be target-seeking, can typically pass through scatter diagram, song
The modes such as line chart describe inlet flow rate's variation tendency of the predeterminable area.
For example, with reference to figure 2, the change of the inlet flow rate over time is regular (for example, it may be shown in Fig. 2
Alternating changing rule).More specifically, when the predeterminable area is industrial park, on Monday to Friday (i.e. working day)
The preset areas during the inlet flow rate of predeterminable area described in period can be more than Saturday and Sunday (i.e. two-day weekend) on the whole
The inlet flow rate in domain;And when being observed in units of day, inlet flow rate inside predeterminable area change can be again with
Time adds up and is on the whole reduction trend, but the particular moment (such as noon, evening peak) in one day, the preset areas
Inlet flow rate inside domain has a small amount of rise again.
Further, on this basis, the ARIMA models can be used, by history several cycles shown in Fig. 2
The inlet flow rate's data inside the predeterminable area obtained, simulation, predict the predeterminable area in following special time period
Inlet flow rate's variation tendency.For example, when the following special time period for needing to predict is working day, can be according to Fig. 2
Date in history between inlet flow rate's trend described in following special time period inlet flow rate.
As a non-limiting example, when the predicted flow rate of the characteristic parameter becomes, to turn to predeterminable area borderline
, can be based on the data on flows of the predeterminable area and its neighboring area in history, it is determined that positioned at described when predicted flow rate changes
The borderline flow of predeterminable area enters the probability of the predeterminable area.
It will be appreciated by those skilled in the art that when performing scheme described in the present embodiment, except needing to predict the predeterminable area
Outside internal inlet flow rate's variation tendency, it is also necessary to the borderline inlet flow rate's variation tendency of the predeterminable area is predicted, with
More accurately predict inlet flow rate of the predeterminable area in following special time period.
Preferably, the border of the predeterminable area can include the part that the predeterminable area is bordered on its neighboring area.
Preferably, the probability can be based on pre-programmed curve determination, and the pre-programmed curve can be based on day type and determine.Its
In, the day type can be selected from:Working day, weekend and festivals or holidays.
Preset for example, the borderline population entrance for being located at the specific trellis can be calculated according to Bayes or leave this
The probability of grid, and then determine the borderline forecasted population changes in flow rate of predeterminable area.
Specifically, for positioned at the borderline people of the predeterminable area, it can be observed on the predeterminable area border
On moving direction, still try to exit from institute being attempt to the predeterminable area as described in positioned at the borderline people of predeterminable area
State predeterminable area.
Based on above-mentioned thought, the borderline inlet flow rate of the predeterminable area can be become and be divided into two kinds of vector datas:P
(in) and P (out), wherein, P (in) can enter the predeterminable area positioned at the borderline inlet flow rate of the predeterminable area
Probability;P (out) can be the probability that the predeterminable area is left positioned at the borderline inlet flow rate of the predeterminable area.
More specifically, the pre-programmed curve can be based on and weigh the P (in) and P (out), and with described in above-mentioned determination
The changing rule of inlet flow rate is similar in predeterminable area, the pre-programmed curve can also because the day type it is different without
Together.
Further, for different day types, on the predeterminable area border, the movement probability of the inlet flow rate
May be different, that is, inlet flow rate variation tendency of the borderline inlet flow rate of the predeterminable area in not type on the same day may
It is different.
Accordingly, the P (in) can be refined as P_ (u, t, dt) (in), for describing under time t, day type dt,
The borderline inlet flow rate of predeterminable area enters predeterminable area u probability.Similar, the P (out) can be refined as P_
(u, t, dt) (out), it is described to prefetch described in borderline inlet flow rate leaves for describing under time t, day type dt
Predeterminable area u probability.
Further, R_ (u, t, dt) (in) can also be defined to describe in following special time period t from the preset areas
On the u borders of domain enter the predeterminable area u inlet flow rate, wherein it is possible to obtain formula R_ (u, t, dt) (in)=(time t,
Under its type dt, positioned at the borderline forecasted population flows of predeterminable area u) × P_ (u, t, dt) (in).
Accordingly, R_ (u, t, dt) (out) can also be defined to describe in following special time period t from the predeterminable area
The inlet flow rate of the predeterminable area u is left on u borders, wherein it is possible to obtain formula R_ (u, t, dt) (out)=(time t,
Under its type dt, positioned at the borderline forecasted population flows of predeterminable area u) × P_ (u, t, dt) (out).
Further, it is determined that after the characteristic parameter that predictor formula needs include, it is also necessary to determine each feature ginseng
Several weight, more accurately to predict flow of the predeterminable area in following special time period.
As a non-limiting example, to the weight, constant current journey can include really:Pass through multivariate logistic regression
Algorithm is tested the preset formula, to determine to best suit the benchmark of the changes in flow rate of the predeterminable area described in history
Preset formula;Weight based on each characteristic parameter in the benchmark preset formula determines the weight of each characteristic parameter.
For example, it is determined that after the characteristic parameter that predictor formula needs include, the multivariate logistic regression can be based on
Algorithm, the predictor formula is detected and trained with reference to historical data, by assuming that the side of the weight of each characteristic parameter
Formula, simulate the benchmark preset formula for best suiting the changes in flow rate of the predeterminable area in history.When the benchmark preset formula
After it is determined that, the weight of parameters in the benchmark preset formula both can be as the weight of the predictor formula.
Further, in actual applications, with the increase of historical data, the weight of parameters feature can also be real-time
Adjustment, to keep even improving prediction precision.
Preferably, the changes in flow rate of each characteristic parameter and the predeterminable area in history can be calculated based on scatter diagram
As a result relation, because the result of picture is substantial linear, it may be determined that the inlet flow rate of the predeterminable area and each spy
Sign parameter has linear relationship, therefore, it is possible to determine the weight of each characteristic parameter using linear regression algorithm.
Further, when performing the step S103, the prediction result at different time interval can be illustrated in map
Superposition displaying is done on (such as the default longitude and latitude flowmeter).Curve that can also be in different colors represents the predeterminable area
Real time section inlet flow rate and early stage to the difference of the forecasted population flow of the period so that the flow finally obtained
Bandwagon effect is more convenient for understanding, analyzed.
,, can be by the real-time traffic data of access it is determined that during predictor formula using scheme described in the present embodiment by upper
Type is as one of measurement factor, to determine more suitably predictor formula according to the type of the real-time traffic data so that really
Fixed predictor formula can preferably meet the type characteristic of the real-time traffic data of access, and then obtain on this basis more smart
Accurate volume forecasting result.It will be appreciated by those skilled in the art that can be according to accurate prediction not by the scheme of the embodiment of the present invention
Carry out the flow of predeterminable area in random time section, also, corresponding to the different types of real-time traffic data of access, being capable of basis
The type characteristic of the real-time traffic data targetedly determines predictor formula, and then obtains different types of volume forecasting knot
Fruit.
Fig. 3 is a kind of structural representation of volume forecasting device of the second embodiment of the present invention.Those skilled in the art
Understand, volume forecasting device 3 described in the present embodiment can be used for implementing the method described in above-mentioned Fig. 1 and embodiment illustrated in fig. 2
Technical scheme.
Specifically, in the present embodiment, the volume forecasting device 3 can include acquisition module 31, default for obtaining
Real-time traffic data in region;Determining module 32, for the type based on the real-time traffic data and described in history
The changes in flow rate of predeterminable area determines predictor formula;Prediction module 33, for according to the predictor formula and real-time traffic data
Predict flow of the predeterminable area in following special time period.
Further, the acquisition module 31 can include division submodule 311, in default longitude and latitude flowmeter
Division, to obtain at least one predeterminable area, the difference between the flux density of each predeterminable area is not more than predetermined threshold value;Obtain
Submodule 312, for each predeterminable area, the real-time streams based on the default longitude and latitude flowmeter acquisition predeterminable area
Measure data.
Further, the determining module 32 can include prediction submodule 321, for based on the preset areas in history
Domain and its changes in flow rate of neighboring area, predict that predicted flow rate of at least one characteristic parameter in following special time period becomes
Change;First determination sub-module 322, the power of each characteristic parameter is determined for the changes in flow rate based on the predeterminable area in history
Weight;Second determination sub-module 323, for determining the preset formula based on each characteristic parameter and its weight, wherein, it is described pre-
If formula is linear formula.
Preferably, the characteristic parameter predicted flow rate change can be influenceed by least one reference factor, it is described extremely
A few reference factor can determine according to the type of the real-time traffic data.Wherein, the reference factor can include with
The next item down is multinomial:Weather conditions, festivals or holidays factor and traffic congestion factor.
Preferably, the predicted flow rate change of the characteristic parameter can at least include:Prediction inside the predeterminable area
Changes in flow rate;The borderline predicted flow rate change of predeterminable area.
As a non-limiting example, when the predicted flow rate of the characteristic parameter become turn to it is pre- inside predeterminable area
When measurement of discharge changes, the prediction submodule 321 can include training unit 3211, for based on the predeterminable area in history
Data on flows training obtain time series models, the time series models are used to describe the changes in flow rate of the predeterminable area
Trend;Predicting unit 3212, for based on the changes in flow rate trend prediction of the predeterminable area in following special time period
Predicted flow rate change inside the predeterminable area.
As another non-limiting example, turned to when the predicted flow rate of the characteristic parameter becomes on predeterminable area border
Predicted flow rate change when, it is described prediction submodule 321 can include the first determining unit 3213, for based on described in history
Predeterminable area and its data on flows of neighboring area, it is determined that the borderline flow positioned at the predeterminable area enters described preset
The probability in region.
Further, the data on flows can be vector data.
Further, the probability can be based on pre-programmed curve determination, and the pre-programmed curve can be based on day type and determine.
Wherein, the day type can be selected from:Working day, weekend and festivals or holidays.
Further, first determination sub-module 322 can include test cell 3221, for being returned by more metalogic
Reduction method is tested the preset formula, to determine to best suit the base of the changes in flow rate of the predeterminable area described in history
Quasi- preset formula;Second determining unit 3222, determined for the weight based on each characteristic parameter in the benchmark preset formula every
The weight of one characteristic parameter.
Further, the type of the real-time traffic data can be selected from:The information point data of mobile device;The prison of vehicle
Control data.
More contents of operation principle, working method on the volume forecasting device 3, are referred in Fig. 1 and Fig. 2
Associated description, repeat no more here.
Further, a kind of storage medium is also disclosed in the embodiment of the present invention, is stored thereon with computer instruction, the calculating
The method and technology scheme described in above-mentioned Fig. 1 and embodiment illustrated in fig. 2 is performed during machine instruction operation.Preferably, the storage is situated between
Matter can include computer-readable recording medium.The storage medium can include ROM, RAM, disk or CD etc..
Further, a kind of terminal, including memory and processor is also disclosed in the embodiment of the present invention, is deposited on the memory
The computer instruction that can be run on the processor is contained, the processor performs above-mentioned when running the computer instruction
Method and technology scheme described in Fig. 1 and embodiment illustrated in fig. 2.
Although present disclosure is as above, the present invention is not limited to this.Any those skilled in the art, this is not being departed from
In the spirit and scope of invention, it can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
The scope of restriction is defined.
Claims (28)
- A kind of 1. method for predicting, it is characterised in that including:Obtain the real-time traffic data in predeterminable area;Type based on the real-time traffic data and changes in flow rate of the predeterminable area determines predictor formula in history;According to predeterminable area described in the predictor formula and real-time traffic data prediction in the flow of following special time period.
- 2. method for predicting according to claim 1, it is characterised in that the real-time traffic obtained in predeterminable area Data include:Divided on default longitude and latitude flowmeter, to obtain at least one predeterminable area, between the flux density of each predeterminable area Difference be not more than predetermined threshold value;For each predeterminable area, the real-time traffic number based on the default longitude and latitude flowmeter acquisition predeterminable area According to.
- 3. method for predicting according to claim 1, it is characterised in that the class based on the real-time traffic data The type and changes in flow rate of the predeterminable area determines that predictor formula includes in history:Based on the changes in flow rate of the predeterminable area and its neighboring area in history, predict at least one characteristic parameter following special The predicted flow rate change fixed time in section;Changes in flow rate based on the predeterminable area in history determines the weight of each characteristic parameter;The preset formula is determined based on each characteristic parameter and its weight, wherein, the preset formula is linear formula.
- 4. method for predicting according to claim 3, it is characterised in that the characteristic parameter predicted flow rate change by The influence of at least one reference factor, at least one reference factor determine according to the type of the real-time traffic data.
- 5. method for predicting according to claim 4, it is characterised in that the reference factor is included with the next item down or more :Weather conditions, festivals or holidays factor and traffic congestion factor.
- 6. method for predicting according to claim 3, it is characterised in that the predicted flow rate of the characteristic parameter is changed to Include less:Predicted flow rate change inside the predeterminable area;The borderline predicted flow rate change of predeterminable area.
- 7. method for predicting according to claim 6, it is characterised in that when the predicted flow rate of the characteristic parameter changes It is described to be become based on the predeterminable area in history and its flow of neighboring area when changing for the predicted flow rate inside predeterminable area Change, predict that predicted flow rate change of at least one characteristic parameter in following special time period includes:Data on flows training based on the predeterminable area in history obtains time series models, and the time series models are used for The changes in flow rate trend of the predeterminable area is described;Inside the predeterminable area based on the changes in flow rate trend prediction of the predeterminable area in following special time period Predicted flow rate changes.
- 8. method for predicting according to claim 6, it is characterised in that when the predicted flow rate of the characteristic parameter changes It is described based on the predeterminable area in history and its flow of neighboring area during predicted flow rate change borderline for predeterminable area Change, predict that predicted flow rate change of at least one characteristic parameter in following special time period includes:Based on the data on flows of the predeterminable area and its neighboring area in history, it is determined that on the border of the predeterminable area Flow enter the predeterminable area probability.
- 9. method for predicting according to claim 8, it is characterised in that the data on flows is vector data.
- 10. method for predicting according to claim 8, it is characterised in that the probability is based on pre-programmed curve determination, institute Pre-programmed curve is stated to determine based on day type.
- 11. method for predicting according to claim 10, it is characterised in that the day type is selected from:Working day, weekend And festivals or holidays.
- 12. method for predicting according to claim 3, it is characterised in that described based on the predeterminable area in history Changes in flow rate determine that the weight of each characteristic parameter includes:The preset formula is tested by multivariate logistic regression algorithm, it is described described default in history to determine to best suit The benchmark preset formula of the changes in flow rate in region;Weight based on each characteristic parameter in the benchmark preset formula determines the weight of each characteristic parameter.
- 13. the method for predicting according to any one of claim 1 to 12, it is characterised in that the real-time traffic number According to type be selected from:The information point data of mobile device;The monitoring data of vehicle.
- A kind of 14. volume forecasting device, it is characterised in that including:Acquisition module, for obtaining the real-time traffic data in predeterminable area;Determining module, the changes in flow rate of the predeterminable area is true for the type based on the real-time traffic data and in history Determine predictor formula;Prediction module, for according to the predictor formula and real-time traffic data prediction predeterminable area in following special time The flow of section.
- 15. volume forecasting device according to claim 14, it is characterised in that the acquisition module includes:Submodule is divided, for being divided on default longitude and latitude flowmeter, to obtain at least one predeterminable area, each preset areas Difference between the flux density in domain is not more than predetermined threshold value;Acquisition submodule, for each predeterminable area, the predeterminable area is obtained based on the default longitude and latitude flowmeter Real-time traffic data.
- 16. volume forecasting device according to claim 14, it is characterised in that the determining module includes:Submodule is predicted, at least one based on the changes in flow rate of the predeterminable area and its neighboring area in history, prediction Predicted flow rate change of the characteristic parameter in following special time period;First determination sub-module, the power of each characteristic parameter is determined for the changes in flow rate based on the predeterminable area in history Weight;Second determination sub-module, for determining the preset formula based on each characteristic parameter and its weight, wherein, it is described default Formula is linear formula.
- 17. volume forecasting device according to claim 16, it is characterised in that the predicted flow rate change of the characteristic parameter Influenceed by least one reference factor, at least one reference factor determines according to the type of the real-time traffic data.
- 18. volume forecasting device according to claim 17, it is characterised in that the reference factor include with the next item down or It is multinomial:Weather conditions, festivals or holidays factor and traffic congestion factor.
- 19. volume forecasting device according to claim 16, it is characterised in that the predicted flow rate change of the characteristic parameter Comprise at least:Predicted flow rate change inside the predeterminable area;The borderline predicted flow rate change of predeterminable area.
- 20. volume forecasting device according to claim 19, it is characterised in that when the predicted flow rate of the characteristic parameter becomes When turning to the predicted flow rate change inside predeterminable area, the prediction submodule includes:Training unit, time series models are obtained for the data on flows training based on the predeterminable area in history, when described Between series model be used to describe the changes in flow rate trend of the predeterminable area;Predicting unit, for described pre- in following special time period based on the changes in flow rate trend prediction of the predeterminable area If the predicted flow rate change inside region.
- 21. volume forecasting device according to claim 19, it is characterised in that when the predicted flow rate of the characteristic parameter becomes When turning to the change of predeterminable area borderline predicted flow rate, the prediction submodule includes:First determining unit, for based on the data on flows of the predeterminable area and its neighboring area in history,It is determined that the borderline flow positioned at the predeterminable area enters the probability of the predeterminable area.
- 22. volume forecasting device according to claim 21, it is characterised in that the data on flows is vector data.
- 23. volume forecasting device according to claim 21, it is characterised in that the probability based on pre-programmed curve determine, The pre-programmed curve is determined based on day type.
- 24. volume forecasting device according to claim 23, it is characterised in that the day type is selected from:Working day, weekend And festivals or holidays.
- 25. volume forecasting device according to claim 16, it is characterised in that first determination sub-module includes:Test cell, it is described to determine to best suit for being tested by multivariate logistic regression algorithm the preset formula The benchmark preset formula of the changes in flow rate of the predeterminable area in history;Second determining unit, each characteristic parameter is determined for the weight based on each characteristic parameter in the benchmark preset formula Weight.
- 26. the volume forecasting device according to any one of claim 14 to 25, it is characterised in that the real-time traffic number According to type be selected from:The information point data of mobile device;The monitoring data of vehicle.
- 27. a kind of storage medium, is stored thereon with computer instruction, it is characterised in that is performed during the computer instruction operation The step of any one of claim 1 to 13 methods described.
- 28. a kind of terminal, including memory and processor, it is stored with what can be run on the processor on the memory Computer instruction, it is characterised in that any one of perform claim requirement 1 to 13 institute when the processor runs the computer instruction The step of stating method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710881422.8A CN107832866A (en) | 2017-09-26 | 2017-09-26 | A kind of method for predicting and device, storage medium, terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710881422.8A CN107832866A (en) | 2017-09-26 | 2017-09-26 | A kind of method for predicting and device, storage medium, terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107832866A true CN107832866A (en) | 2018-03-23 |
Family
ID=61643378
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710881422.8A Pending CN107832866A (en) | 2017-09-26 | 2017-09-26 | A kind of method for predicting and device, storage medium, terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107832866A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108765010A (en) * | 2018-05-29 | 2018-11-06 | 腾讯科技(深圳)有限公司 | User retains probability forecasting method, device, predictive server and storage medium |
CN108961762A (en) * | 2018-08-24 | 2018-12-07 | 东北林业大学 | A kind of urban road traffic flow amount prediction technique based on multifactor fusion |
CN109039691A (en) * | 2018-06-01 | 2018-12-18 | 平安科技(深圳)有限公司 | The method and storage medium of server, forecasting system calling amount |
CN109413071A (en) * | 2018-10-31 | 2019-03-01 | 新华三信息安全技术有限公司 | A kind of anomalous traffic detection method and device |
CN109615852A (en) * | 2018-11-20 | 2019-04-12 | 上海海事大学 | A kind of method of road traffic delay distribution quick predict under burst accident |
CN110400024A (en) * | 2019-07-31 | 2019-11-01 | 京东城市(北京)数字科技有限公司 | Method, apparatus, equipment and the computer readable storage medium of order forecasting |
CN110535784A (en) * | 2018-05-23 | 2019-12-03 | 北京三快在线科技有限公司 | Flow managing method and device and calculating equipment based on confidence interval |
CN110555537A (en) * | 2018-05-30 | 2019-12-10 | 微软技术许可有限责任公司 | Multi-factor multi-time point correlated prediction |
CN110838018A (en) * | 2018-08-16 | 2020-02-25 | 中国移动通信集团浙江有限公司 | Method and device for predicting maximum number of users in cell during holidays |
CN111147899A (en) * | 2019-12-16 | 2020-05-12 | 南京亚信智网科技有限公司 | Fault early warning method and device |
CN111343006A (en) * | 2020-02-12 | 2020-06-26 | 咪咕文化科技有限公司 | CDN peak flow prediction method, device and storage medium |
CN111461384A (en) * | 2019-12-10 | 2020-07-28 | 阿里巴巴集团控股有限公司 | Object flow prediction method, device and equipment |
CN113642807A (en) * | 2021-09-01 | 2021-11-12 | 智慧足迹数据科技有限公司 | Population mobility prediction method and related device |
CN114282732A (en) * | 2021-12-29 | 2022-04-05 | 重庆紫光华山智安科技有限公司 | Regional pedestrian flow prediction method and device |
CN114333324A (en) * | 2022-01-06 | 2022-04-12 | 厦门市美亚柏科信息股份有限公司 | Real-time traffic state acquisition method and terminal |
CN117332239A (en) * | 2023-11-27 | 2024-01-02 | 深圳润世华软件和信息技术服务有限公司 | Method, device, equipment and storage medium for calculating generated energy |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5168136A (en) * | 1991-10-15 | 1992-12-01 | Otis Elevator Company | Learning methodology for improving traffic prediction accuracy of elevator systems using "artificial intelligence" |
CN105404850A (en) * | 2015-10-21 | 2016-03-16 | 中南大学 | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method |
CN105512447A (en) * | 2014-09-26 | 2016-04-20 | 山西云智慧科技股份有限公司 | Bus passenger volume prediction method based on Holt-Winters model |
CN106355879A (en) * | 2016-09-30 | 2017-01-25 | 西安翔迅科技有限责任公司 | Time-space correlation-based urban traffic flow prediction method |
-
2017
- 2017-09-26 CN CN201710881422.8A patent/CN107832866A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5168136A (en) * | 1991-10-15 | 1992-12-01 | Otis Elevator Company | Learning methodology for improving traffic prediction accuracy of elevator systems using "artificial intelligence" |
CN105512447A (en) * | 2014-09-26 | 2016-04-20 | 山西云智慧科技股份有限公司 | Bus passenger volume prediction method based on Holt-Winters model |
CN105404850A (en) * | 2015-10-21 | 2016-03-16 | 中南大学 | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method |
CN106355879A (en) * | 2016-09-30 | 2017-01-25 | 西安翔迅科技有限责任公司 | Time-space correlation-based urban traffic flow prediction method |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110535784A (en) * | 2018-05-23 | 2019-12-03 | 北京三快在线科技有限公司 | Flow managing method and device and calculating equipment based on confidence interval |
CN110535784B (en) * | 2018-05-23 | 2021-01-15 | 北京三快在线科技有限公司 | Traffic management method and device based on confidence interval and computing equipment |
CN108765010A (en) * | 2018-05-29 | 2018-11-06 | 腾讯科技(深圳)有限公司 | User retains probability forecasting method, device, predictive server and storage medium |
CN110555537A (en) * | 2018-05-30 | 2019-12-10 | 微软技术许可有限责任公司 | Multi-factor multi-time point correlated prediction |
CN109039691A (en) * | 2018-06-01 | 2018-12-18 | 平安科技(深圳)有限公司 | The method and storage medium of server, forecasting system calling amount |
CN110838018A (en) * | 2018-08-16 | 2020-02-25 | 中国移动通信集团浙江有限公司 | Method and device for predicting maximum number of users in cell during holidays |
CN108961762A (en) * | 2018-08-24 | 2018-12-07 | 东北林业大学 | A kind of urban road traffic flow amount prediction technique based on multifactor fusion |
CN109413071A (en) * | 2018-10-31 | 2019-03-01 | 新华三信息安全技术有限公司 | A kind of anomalous traffic detection method and device |
CN109413071B (en) * | 2018-10-31 | 2021-08-06 | 新华三信息安全技术有限公司 | Abnormal flow detection method and device |
CN109615852A (en) * | 2018-11-20 | 2019-04-12 | 上海海事大学 | A kind of method of road traffic delay distribution quick predict under burst accident |
CN109615852B (en) * | 2018-11-20 | 2021-03-30 | 上海海事大学 | Method for rapidly predicting road traffic flow distribution under sudden accident |
CN110400024A (en) * | 2019-07-31 | 2019-11-01 | 京东城市(北京)数字科技有限公司 | Method, apparatus, equipment and the computer readable storage medium of order forecasting |
CN111461384A (en) * | 2019-12-10 | 2020-07-28 | 阿里巴巴集团控股有限公司 | Object flow prediction method, device and equipment |
CN111461384B (en) * | 2019-12-10 | 2024-04-05 | 阿里巴巴集团控股有限公司 | Object flow prediction method, device and equipment |
CN111147899B (en) * | 2019-12-16 | 2023-05-23 | 南京亚信智网科技有限公司 | Fault early warning method and device |
CN111147899A (en) * | 2019-12-16 | 2020-05-12 | 南京亚信智网科技有限公司 | Fault early warning method and device |
CN111343006A (en) * | 2020-02-12 | 2020-06-26 | 咪咕文化科技有限公司 | CDN peak flow prediction method, device and storage medium |
CN113642807B (en) * | 2021-09-01 | 2022-04-12 | 智慧足迹数据科技有限公司 | Population mobility prediction method and related device |
CN113642807A (en) * | 2021-09-01 | 2021-11-12 | 智慧足迹数据科技有限公司 | Population mobility prediction method and related device |
CN114282732A (en) * | 2021-12-29 | 2022-04-05 | 重庆紫光华山智安科技有限公司 | Regional pedestrian flow prediction method and device |
CN114333324A (en) * | 2022-01-06 | 2022-04-12 | 厦门市美亚柏科信息股份有限公司 | Real-time traffic state acquisition method and terminal |
CN117332239A (en) * | 2023-11-27 | 2024-01-02 | 深圳润世华软件和信息技术服务有限公司 | Method, device, equipment and storage medium for calculating generated energy |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107832866A (en) | A kind of method for predicting and device, storage medium, terminal | |
Selby et al. | Spatial prediction of traffic levels in unmeasured locations: applications of universal kriging and geographically weighted regression | |
CN107111794B (en) | Predicting and exploiting variability of travel time in a mapping service | |
Lin et al. | A review of travel-time prediction in transport and logistics | |
US9349150B2 (en) | System and method for multi-task learning for prediction of demand on a system | |
Kurzhanskiy et al. | Active traffic management on road networks: a macroscopic approach | |
Van Lint | Reliable travel time prediction for freeways | |
Hans et al. | Real-time bus route state forecasting using particle filter and mesoscopic modeling | |
Nagle et al. | Accuracy of networkwide traffic states estimated from mobile probe data | |
US20140222321A1 (en) | Traffic state estimation with integration of traffic, weather, incident, pavement condition, and roadway operations data | |
US7363144B2 (en) | Method and apparatus for predicting future travel times over a transportation network | |
US20060178811A1 (en) | Method and apparatus for end-to-end travel time estimation using dynamic traffic data | |
CN110517492A (en) | Based on the traffic route recommended method of parallel integrated study, system, device | |
CN110956807B (en) | Highway flow prediction method based on combination of multi-source data and sliding window | |
Polson et al. | Bayesian analysis of traffic flow on interstate I-55: The LWR model | |
Chu et al. | Real-time traffic prediction and probing strategy for Lagrangian traffic data | |
Celikoglu | Reconstructing freeway travel times with a simplified network flow model alternating the adopted fundamental diagram | |
Chen et al. | A multiscale-grid-based stacked bidirectional GRU neural network model for predicting traffic speeds of urban expressways | |
Wismans et al. | Real time traffic models, decision support for traffic management | |
Gómez et al. | Evaluation of trade-offs between two data sources for the accurate estimation of origin–destination matrices | |
Pirc et al. | Highway travel time estimation using multiple data sources | |
Moghaddam et al. | Evaluating the performance of algorithms for the detection of travel time outliers | |
Baclet et al. | Near-real-time dynamic noise mapping and exposure assessment using calibrated microscopic traffic simulations | |
Goodall et al. | Microscopic estimation of freeway vehicle positions using mobile sensors | |
Tettamanti et al. | Road traffic measurement and related data fusion methodology for traffic estimation |
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: 20180323 |
|
RJ01 | Rejection of invention patent application after publication |