CN107292649A - The method and apparatus of traffic forecast Data correction - Google Patents
The method and apparatus of traffic forecast Data correction Download PDFInfo
- Publication number
- CN107292649A CN107292649A CN201610204277.5A CN201610204277A CN107292649A CN 107292649 A CN107292649 A CN 107292649A CN 201610204277 A CN201610204277 A CN 201610204277A CN 107292649 A CN107292649 A CN 107292649A
- Authority
- CN
- China
- Prior art keywords
- moment
- traffic forecast
- forecast data
- business
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Data Mining & Analysis (AREA)
Abstract
The invention discloses a kind of method and apparatus of traffic forecast Data correction.Wherein, this method includes：The first business datum is extracted at the first moment, wherein, the first business datum includes：The business exchange hand produced at the first moment；Judge whether the second moment corresponding second traffic forecast data are more than the first business datum, wherein, the second moment was time point adjacent after the first moment；In the case where judged result is no, the difference of the second traffic forecast data and the first business datum is calculated；Corrected for the second moment to clearing moment corresponding traffic forecast data according to difference.The present invention is solved due to lacking the technology to managing individual correction prediction portfolio in the case of second day actual volume significant changes in the prior art, causes prediction data to be less than actual volume, so that the low technical problem of the precision of prediction brought.
Description
Technical field
The present invention relates to application of electronic technology field, in particular to a kind of method of traffic forecast Data correction and
Device.
Background technology
With growing, the prediction calculating to the following turnover in electric business platform of electric business platform, become current get over
Carry out the technological means of more following turnovers of electric business prediction, and how accurately to estimate the following turnover for obtaining electric business
Become urgent problem to be solved.
In the prior art due to managing individual same day portfolio by factors such as activity, marketing methods and promotion periods
Influence, the operation individual same day portfolio by than the operation individual historical traffic exist is obviously improved.And
Before the same day, business system will be estimated to the portfolio of second day, if but estimating predicting the outcome of obtaining
Less than the same day actual turnover, then illustrate that the estimation results have mistake, precision of prediction is too low.
In the technology for the turnover that individual is managed in existing prediction, Traffic prediction algorithm is added up usually using hour, i.e.
The ratio that accumulative portfolio of each hour accounts for total traffic is obtained according to historical data, then according to the total pre- of same day portfolio
Measured value calculates accumulative Traffic prediction value hourly.
But, predicted according to historical data and manage the individual portfolio (or, turnover) of second day, and the same day per small
When accumulative portfolio, so as to describe the variation tendency for managing individual service amount, this method according to 24 hourage strong points
It is only capable of only just getting preferable effect when portfolio is more steady, once significant changes occur for second day real time traffic
When, the problem of predicted value is inaccurate not only occurs, or even when 24 points of clearing of the same day occur, Traffic prediction total value
The small gross error of actual services amount accumulative before than 24 points.
For above-mentioned due to lacking in the prior art to managing individual in the case of second day actual volume significant changes
The technology of correction prediction portfolio, causes prediction data to be less than actual volume, is asked so that the precision of prediction brought is low
Topic, not yet proposes effective solution at present.
The content of the invention
The embodiments of the invention provide a kind of method and apparatus of traffic forecast Data correction, at least to solve due to existing
Lack the technology to managing individual correction prediction portfolio in the case of second day actual volume significant changes in technology,
Prediction data is caused to be less than actual volume, so that the low technical problem of the precision of prediction brought.
One side according to embodiments of the present invention there is provided a kind of method of traffic forecast Data correction, including：
First moment extracted the first business datum, wherein, the first business datum includes：The business produced at the first moment strikes a bargain
Amount；Judge whether the second moment corresponding second traffic forecast data are more than the first business datum, wherein, the second moment
For time point adjacent after the first moment；In judged result in the case of no, calculate the second traffic forecast data with
The difference of first business datum；Corrected for the second moment to clearing moment corresponding traffic forecast data according to difference.
Another aspect according to embodiments of the present invention, additionally provides a kind of device of traffic forecast Data correction, including：
Extraction module, for extracting the first business datum at the first moment, wherein, the first business datum includes：At first
Carve the business exchange hand produced；Judge module, for judging whether the second moment corresponding second traffic forecast data are big
In the first business datum, wherein, the second moment was time point adjacent after the first moment；Computing module, for
In the case that judged result is no, the difference of the second traffic forecast data and the first business datum is calculated；Correction module,
For correcting for the second moment to clearing moment corresponding traffic forecast data according to difference.
In embodiments of the present invention, by extracting the first business datum at the first moment, wherein, the first business data packet
Include：The business exchange hand produced at the first moment；Judge whether the second moment corresponding second traffic forecast data are more than
First business datum, wherein, the second moment was time point adjacent after the first moment；The feelings for being no in judged result
Under condition, the difference of the second traffic forecast data and the first business datum is calculated；Corrected for the second moment to clearing according to difference
Moment corresponding traffic forecast data, having reached can be timely when actual volume changes within second day to managing individual
The purpose of correction, it is achieved thereby that technique effect of the lifting to Traffic prediction precision, and then solve due to existing skill
Lack the technology to managing individual correction prediction portfolio in the case of second day actual volume significant changes in art,
Prediction data is caused to be less than actual volume, so that the low technical problem of the precision of prediction brought.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In accompanying drawing
In：
Fig. 1 is a kind of hardware configuration frame of the terminal of the method for traffic forecast Data correction of the embodiment of the present invention
Figure；
Fig. 2 is the flow chart of the method for according to embodiments of the present invention one traffic forecast Data correction；
Fig. 3 a are a kind of schematic flow sheets of the method for according to embodiments of the present invention one traffic forecast Data correction；
Fig. 3 b are the schematic flow sheets of the method for according to embodiments of the present invention one another traffic forecast Data correction；
Fig. 4 be a kind of according to embodiments of the present invention one traffic forecast Data correction method in business datum and business it is pre-
Survey the curve synoptic diagram of data；
Fig. 5 is the structural representation of the device of according to embodiments of the present invention two traffic forecast Data correction；
Fig. 6 is a kind of structural representation of the device of according to embodiments of the present invention two traffic forecast Data correction；
Fig. 7 is the structural representation of the device of according to embodiments of the present invention two another traffic forecast Data correction；
Fig. 8 is the structural representation of the device of according to embodiments of the present invention two another traffic forecast Data correction；
Fig. 9 is the structural representation of the device of according to embodiments of the present invention two another traffic forecast Data correction.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment
The only embodiment of a present invention part, rather than whole embodiments.Based on the embodiment in the present invention, ability
The every other embodiment that domain those of ordinary skill is obtained under the premise of creative work is not made, should all belong to
The scope of protection of the invention.
It should be noted that term " first ", " second " in description and claims of this specification and above-mentioned accompanying drawing
Etc. being for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so making
Data can be exchanged in the appropriate case, so that embodiments of the invention described herein can be with except herein
Order beyond those of diagram or description is implemented.In addition, term " comprising " and " having " and their any deformation,
Be intended to that covering is non-exclusive to be included, for example, contain the process of series of steps or unit, method, system,
Product or equipment are not necessarily limited to those steps clearly listed or unit, but may include not list clearly or
For the intrinsic other steps of these processes, method, product or equipment or unit.
Embodiment 1
According to embodiments of the present invention, additionally provide a kind of embodiment of the method for the method of traffic forecast Data correction, it is necessary to
Illustrate, the step of the flow of accompanying drawing is illustrated can such as one group computer executable instructions department of computer science
Performed in system, and, although logical order is shown in flow charts, but in some cases, can be with difference
Shown or described step is performed in order herein.
The embodiment of the method that the embodiment of the present application one is provided can be in mobile terminal, terminal or similar fortune
Calculate in device and perform.Exemplified by running on computer terminals, Fig. 1 is a kind of traffic forecast number of the embodiment of the present invention
According to the hardware block diagram of the terminal of the method for correction.As shown in figure 1, terminal 10 can include one
(processor 102 can include but is not limited to Micro-processor MCV to individual or multiple (one is only shown in figure) processor 102
Or PLD FPGA etc. processing unit), the memory 104 for data storage and for communicating
The transport module 106 of function.It will appreciated by the skilled person that the structure shown in Fig. 1 is only signal, its
The structure to above-mentioned electronic installation does not cause to limit.For example, terminal 10 may also include than shown in Fig. 1 more
Many either less components or with the configuration different from shown in Fig. 1.
The business that memory 104 can be used in the software program and module of storage application software, such as embodiment of the present invention
Corresponding programmed instruction/the module of method of prediction data correction, processor 102 is stored in memory 104 by operation
Software program and module, so as to perform various function application and data processing, that is, realize above-mentioned application program
Leak detection method.Memory 104 may include high speed random access memory, may also include nonvolatile memory, such as
One or more magnetic storage device, flash memory or other non-volatile solid state memories.In some instances,
Memory 104 can further comprise the memory remotely located relative to processor 102, and these remote memories can be with
Pass through network connection to terminal 10.The example of above-mentioned network include but is not limited to internet, intranet,
LAN, mobile radio communication and combinations thereof.
Transmitting device 106 is used to data are received or sent via a network.Above-mentioned network instantiation may include
The wireless network that the communication providerses of terminal 10 are provided.In an example, transmitting device 106 includes one
Network adapter (Network Interface Controller, NIC), it can be connected by base station with other network equipments
So as to be communicated with internet.In an example, transmitting device 106 can for radio frequency (Radio Frequency,
RF) module, it is used to wirelessly be communicated with internet.
Under above-mentioned running environment, this application provides the method for traffic forecast Data correction as shown in Figure 2.Fig. 2
It is the flow chart of the method for according to embodiments of the present invention one traffic forecast Data correction.
Step S202, the first business datum is extracted at the first moment, wherein, the first business datum includes：At first
Carve the business exchange hand produced；
In the application above-mentioned steps S202, the method for the traffic forecast Data correction that the embodiment of the present application is provided can be applicable
The prediction data for managing individual same day portfolio is corrected in electric business platform, it is to avoid manage individual same day portfolio always pre-
Survey data and be less than moment on same day business datum actual value, the traffic forecast Data correction provided in the embodiment of the present application
In method, to judge whether the total prediction data for managing individual is less than actual business exchange hand, then need to exist first
First moment extracted the first business datum, and first business datum can be 0 point of business exchange hand to the first moment
Aggregate-value.
Wherein, the second can be accurate at the first moment in the embodiment of the present application, i.e. when extracting the first business datum, should
The structure at the first moment can be expressed as：Year-month-day hour：Minute：Second (yyyy-mm-dd hh:mm:Ss) when
Punctum.In the embodiment of the present application because the first moment can be as accurate as the second, and by the first industry of first moment extraction
Business data are by be accurate to the business exchange hand of second, to sum up according to being accurate to the business exchange hand of second to subsequent prediction number
According to timing, the correction accuracy of predicted value will be improved, wherein, trimming process is shown in step S204 to S208.
Step S204, judges whether the second moment corresponding second traffic forecast data are more than the first business datum, wherein,
Second moment was time point adjacent after the first moment；
Based on the first business datum extracted in step S202, in the application above-mentioned steps S204, by the second moment pair
The the second traffic forecast data answered are compared with first business datum, judge whether the second traffic forecast data are big
In the first business datum, wherein, the second moment was time point adjacent after the first moment.
Specifically, assuming that the first moment the first business datum of extraction is：09:15:20 business datum Date1, second
Moment, corresponding second traffic forecast data can be：10:00 corresponding traffic forecast data Date2, is obtaining Date1
Date2 is judged with Date1 afterwards, judges whether the Date2 is more than Date1.
Step S206, in the case where judged result is no, calculates the second traffic forecast data and the first business datum
Difference；
In the application above-mentioned steps S206, in the case where judged result is less than the first business datum for the second prediction data,
The difference of the second traffic forecast data and the first business datum can be obtained calculating.
Specifically, still by taking the example in step S204 as an example, when Date1 is more than Date2, calculating Date2 and Date1
Between difference, i.e. difference D=Date1-Date2.
Step S208, corrected for the second moment to clearing moment corresponding traffic forecast data according to difference.
In the difference obtained based on step S206, the application above-mentioned steps S208, according to the difference, to the second moment
It is corrected to clearing moment corresponding traffic forecast data, by the business datum and business of one day in the embodiment of the present application
Prediction data is divided into 24 stages according to daily 24 hours, i.e. 0 point to 24 points, totally 24 periods,
When obtaining the difference, the second moment to 24 points of corresponding traffic forecast data will be corrected.
Specifically, still by taking the example in step S204 as an example, when the difference for obtaining Date1 and Date2 is D,
If the second moment was, the traffic forecast number at 10 points to 24 points this 15 time points is corrected according to difference D at 10 points
According to.
With reference to step S202 to step S208, in the embodiment of the present application, predicted value (that is, the application of portfolio
The second traffic forecast data that embodiment is provided) it is the industry on the day of being obtained before predicting the business date by prediction algorithm
Business data are estimated, and real time traffic data is that (that is, the embodiment of the present application is carried for the practical business value that obtained in real time on the same day
The first business datum supplied).Smoothly made up the difference to realize, first obtaining accumulative portfolio of each hour according to historical data accounts for industry
The ratio for total amount of being engaged in, is then multiplied by same day Traffic prediction value, obtains the predicted value of 25 small time points of the same day, according to
This draws one using hour as transverse axis, and portfolio is the prediction curve of the longitudinal axis.When real time data is bigger than next hour data
When (that is, the first business datum be more than the second traffic forecast data in the case of), calculate the difference and (calculate the first business
The difference of data and the second traffic forecast data), and the predicted value of each small time point behind current time is all added into the difference
Complete to make up the difference.Fig. 3 a are that the flow of the method for according to embodiments of the present invention one another traffic forecast Data correction is shown
Be intended to, as shown in Figure 3 a, the embodiment of the present application provide traffic forecast Data correction method in, by according to from
Line predicts the accounting of total traffic and offline prediction hour sales volume, obtains off-line data (that is, in the embodiment of the present application
Traffic forecast data), by updating obtained actual traffic data at the first moment, if the business datum is more than and first
Moment adjacent the second moment corresponding traffic forecast data, then by comparing business datum and the traffic forecast data,
Corrected value (that is, the difference in the embodiment of the present application) is generated, and then the second moment was corrected to settling accounts the moment by corrected value
Corresponding traffic forecast data.
From the foregoing, it will be observed that the scheme that the above embodiments of the present application one are provided, by extracting the first business number at the first moment
According to, wherein, the first business datum includes：The business exchange hand produced at the first moment；Judge that the second moment is corresponding
Whether the second traffic forecast data are more than the first business datum；In the case where judged result is no, the second business is calculated
The difference of prediction data and the first business datum；Corrected for the second moment to clearing moment corresponding traffic forecast according to difference
Data, have reached to managing the purpose that individual can be corrected in time when actual volume changed in second day, so that real
Technique effect of the lifting to Traffic prediction precision is showed, and then has solved due to lacking in the prior art to managing individual
The technology of correction prediction portfolio, causes prediction data less than real in the case of second day actual volume significant changes
Border portfolio, so that the low technical problem of the precision of prediction brought.
Specifically, the flow that Fig. 3 b are the methods of according to embodiments of the present invention one another traffic forecast Data correction is shown
It is intended to, as shown in Figure 3 b, the method for the traffic forecast Data correction that the embodiment of the present application is provided is specific as follows：
Optionally, extracting the first business datum at the first moment in step S202 includes：
Step1, judges whether the first moment was more than the clearing moment；
In Step1 in the application above-mentioned steps S202, it is necessary to judge current before the first business datum is extracted
Whether extraction time is the clearing moment, i.e. if the first moment was the clearing moment, shows that the same day is over, has not had
It is necessary to be compared current time corresponding business datum and traffic forecast data, checking procedure terminates, so
Extract before the first business datum, whether need to be to judge at the clearing moment to extracting at the time of the first business datum.
Step2, in the case where judged result is no, extracts the first business datum.
It is to be less than clearing at first moment in judged result in judgement based on Step1, the application above-mentioned steps Step2
In the case of moment, the first business datum is extracted.
Specifically, the method with reference to Step1 and Step2, the embodiment of the present application the traffic forecast Data correction provided is being carried
Take specific as follows during the first business datum：Judge whether current first moment is more than the clearing moment, judging knot
Fruit is in the case of being, the first business datum is extracted flow and terminated；In the case where judged result is no, first is extracted
Moment corresponding first business datum, wherein, the first business datum can be in the case where the first moment was accurate to the second,
The business exchange hand of extraction, the business exchange hand can be 0 point of accumulation exchange hand to the first moment.
Optionally, in step S202 the first moment extract the first business datum before, the embodiment of the present application provide
The method of traffic forecast Data correction also include：
The accumulation portfolio of step S200, acquisition traffic forecast data and preset time accounts for the proportion of total business volume；
In the application above-mentioned steps S200, the traffic forecast data in the embodiment of the present application can be with day traffic forecast data
Exemplified by, the accumulation portfolio of preset time can be illustrated by taking accumulation portfolio per hour as an example, wherein, the application
The traffic forecast data that will be previously obtained one day this day each hour for one day in embodiment before practical business conclusion of the business,
Wherein, during the traffic forecast data of each hour are obtained, firstly, it is necessary to obtain a day traffic forecast data,
The history service data of at least 7 days and the ratio for accounting for same day total business data per hour；Secondly, according at least 7 days
History service data and the ratios of same day total business data is accounted for per hour be worth to accumulation portfolio per hour and account for total business volume
Proportion, wherein, what the ratio in the embodiment of the present application was refetched is the average value of nearest 7 days proportion.That is, first calculate each small
When account for the ratio of same day total business data, then take being averaged for nearest 7 days ratio per hour.Thus be avoided that certain Tiantu it is high or
Prominent low exception.
Specifically, the day traffic forecast data in the embodiment of the present application can be calculated by being sampled in a time interval
Obtained average daily business datum, i.e. by gathering the daily business fetched data of one week (7 days), pass through summation
Mode obtains the business conclusion of the business total data of one week, so according to the business conclusion of the business total data by divided by 7 transaction dates obtain
Day traffic forecast data are used as to average daily business datum, and using the average daily business datum.
Assuming that, it is necessary to obtain the day traffic forecast data of Day1 (1 day 2 months), then needing to obtain 1 before Day1
The fetched data in month 7 days 26 to January 31 day, operation individual January 26 to January 31 daily business into
Intersection number is according to that can be Date1, Date2, Date3, Date4, Date5, Date6 and Date7, by daily to 7 days
The summation of business fetched data, can obtain the business conclusion of the business total data of one week, and the business conclusion of the business total data of one week is represented
It is as follows：
DateZ1~7=Date1+Date2+Date3+Date4+Date5+Date6+Date7；
And then for obtain predict Day1 day traffic forecast data, then the business conclusion of the business total data of one week by divided by 7
Individual transaction date, obtains average daily business datum, i.e. DateDay1=DateZ1~7/ 7, can be by after average daily business datum is obtained
The DateDay1It is used as Day1 day traffic forecast data；Or, Day1 day industry is obtained by prediction algorithm model
Business prediction data.
If obtaining accumulation portfolio per hour accounts for the proportion of total business volume, needing first to calculate each hour accounts for same day total business
The ratio of data, then take being averaged for nearest 7 days ratio per hour, finally obtaining accumulation portfolio per hour, to account for business total
The proportion of amount, for example, first calculating the ratio for accounting for same day total business data in 7 days per hour, can be obtained：
Day1:P10~P124；
Day2:P20~P224；
……
Day7:P70~P724；Wherein, Day1 to the Day7 ratio for accounting for same day total business data per hour is per small
When accumulation portfolio account for the same day total business data accounting.
And then, then being averaged for nearest 7 days ratio per hour is taken, it can obtain：
P0'=(P10+P20+……+P70)/7；
P1'=(P11+P21+……+P71)/7；
……
P23'=(P124+P224+……+P724)/7。
From the foregoing, it will be observed that obtaining the proportion P that accumulation portfolio per hour accounts for total business volume0', P1' ... ..., P24’。
Need exist for explanation is acquisition day traffic forecast data that the embodiment of the present application is provided and accumulation portfolio per hour
The method of proportion of total business volume is accounted for only exemplified by above-mentioned, to realize the traffic forecast data school of the embodiment of the present application offer
Positive method is defined, and does not limit specifically.
Step S201, the proportion that the accumulation portfolio of traffic forecast data and preset time is accounted for into total business volume is calculated,
Obtain the traffic forecast data of correspondence Each point in time.
The day traffic forecast data and accumulation portfolio accounts for the proportion of total business volume per hour obtained based on step S200,
Apply in above-mentioned steps S201, by the day traffic forecast data and accumulation portfolio accounts for total business volume per hour got
Proportion is calculated, and will obtain traffic forecast data per hour.It is specific as follows：
Step1, calculates day traffic forecast data and the product of proportion, product is defined as into traffic forecast data per hour.
, can be by by calculating the product of day traffic forecast data and proportion from above-mentioned steps S200 and S201
Obtain product and be defined as traffic forecast data per hour.It is specific as follows,
Still by taking the example in step S200 as an example, it is assumed that day traffic forecast data be DateDay1, accumulation industry per hour
The proportion that business amount accounts for total business volume is P0', P1' ... ..., P24’：By DateDay1Respectively with P0', P1' ... ...,
P24' product is carried out, the Day1 data D ' of traffic forecast per hour 0~D ' 24 can be obtained.
In addition, the proportion that the accumulation portfolio of preset time accounts for total business volume can also be each hour in seconds
The accumulation industry for the preset time that the portfolio of accumulation per hour of middle second level is accounted in the proportion of total business volume, the embodiment of the present application
Business amount is by taking accumulation portfolio hourly as an example, and the accumulation portfolio of preset time accounts for the proportion of total business volume with per hour
Accumulation portfolio account for the proportion of total business volume exemplified by illustrate, with realize the embodiment of the present application provide traffic forecast
The method of Data correction is defined, and does not limit specifically.
To sum up, with reference to the method that traffic forecast data per hour are calculated in step S200 and step S201, the application is real
Apply example offer traffic forecast Data correction method in except in step S200 and step S201 by averaging
To traffic forecast data per hour, the rate of people logging in shop, the adding rate of shopping cart, the collection rate of commodity can also be passed through
And transaction data generates traffic forecast data computation model as training characteristics, and then traffic forecast data are obtained, this
The method for the traffic forecast data that application embodiment is provided is illustrated by taking average algorithm as an example, to realize that the application is real
The method for applying the traffic forecast data of example offer is defined, and does not limit specifically.
Optionally, correcting the second moment to clearing moment corresponding traffic forecast data according to difference in step S208 includes：
Step1, corrected value is generated according to difference；
In Step1 in the application above-mentioned steps S208, the second traffic forecast data are less than first in step S206
In the case of business datum, the difference generation corrected value according to the first business datum and the second traffic forecast data.
Step2, is adjusted to moment corresponding traffic forecast data are settled accounts to the second moment according to corrected value, obtains school
Traffic forecast data after just.
In the corrected value generated based on step Step1, the above-mentioned Step2 of the application, according to corrected value to the second moment to knot
Calculate moment corresponding traffic forecast data to be adjusted, the traffic forecast data after being corrected.
Specifically, according to corrected value to the second moment to clearing moment corresponding traffic forecast data in the embodiment of the present application
Two ways can be included by being adjusted, wherein, mode one for difference is defined as into corrected value, and difference is added to
Second moment extremely settled accounts moment corresponding traffic forecast data, the traffic forecast data after being corrected；Mode two, according to
The second moment was entered to moment corresponding traffic forecast data are settled accounts according to difference generation correction proportion, and according to correction proportion
Row adjustment, the traffic forecast data after being corrected.Here mode one perform step A, mode two perform step B and
Step C.
Further, optionally, according to corrected value is extremely settled accounts to the second moment the moment pair in the Step2 in step S208
The traffic forecast data answered are adjusted, and the traffic forecast data after being corrected include：
In the embodiment of the present application, the second moment was adjusted to moment corresponding traffic forecast data are settled accounts according to corrected value
Whole, the traffic forecast data after being corrected include following two modes：
Mode one, corrected value is the situation of difference；
Step A, in the case where difference is defined as into corrected value, added to for the second moment corresponding to the moment is settled accounts by difference
Traffic forecast data, the traffic forecast data after being corrected；
In the application above-mentioned steps A, the first business datum and the second traffic forecast data are sought into the difference that difference is obtained and the
Two moment summed to the moment corresponding data of traffic forecast per hour are settled accounts, the traffic forecast number per hour after being corrected
According to.
Specifically, assuming that the difference that the first business datum asks difference to obtain with the second traffic forecast data is △ d, the second moment
The data of traffic forecast per hour to the clearing moment can be D ' i~D ' 24, and D ' i~D ' 24 is summed with △ d respectively, obtained
Data D ' the i+ △ of traffic forecast per hour d~D ' 24+ △ d after to correction.
Or,
Mode two, corrected value is the situation of the correction proportion generated according to difference；
Step B, according to difference generation correction proportion, and the positive proportion of high-ranking officers is defined as corrected value；
In the application above-mentioned steps B, it is assumed that the difference is △ d, according to △ d generation correction proportions Bi.
Step C, is adjusted according to correction proportion to moment corresponding traffic forecast data are settled accounts to the second moment, obtains
Traffic forecast data after to correction.
Based on the correction proportion obtained in step B, in the application above-mentioned steps C, after correction proportion Bi is obtained,
The second moment was adjusted to moment corresponding traffic forecast data are settled accounts according to the correction proportion Bi, obtained after correction
Traffic forecast data.
Specifically, assuming correction proportion Bi, the data of traffic forecast per hour at the second moment to clearing moment can be
D ' i~D ' 24, by D ' i~D ' 24 respectively with Bi products, the data D ' of the traffic forecast per hour i*Bi after being corrected
~D ' 24*Bi.
With reference to above-mentioned steps S202 to step S208, as shown in Figure 3 b, it is assumed that offline prediction same day total traffic is X
(that is, the day traffic forecast data in the embodiment of the present application), predicting that portfolio accounts for total traffic accounting per hour offline is
pn, n=0,1,2 ..., 23 (that is, the portfolio of accumulation per hour in the embodiment of the present application accounts for the proportion of total business volume), then
24 hour Traffic prediction values are X*pn(n=0,1,2 ..., 23) (that is, business per hour in the embodiment of the present application
Prediction data).Real time data be on the day of portfolio real-time tracing to reality produced portfolio, be designated as Ti(i.e.,
The first business datum in the embodiment of the present application), i is accurate to the second, that is, represents yyyy-mm-dd hh:mm:At the time of ss
Point.The technology of making up the difference refers to, the real time data T that current time i (hour is h) is obtainediWith (h+1) hour predicted value (
Two moment corresponding second traffic forecast data) contrast, i.e. Δ t=Ti-X*Ph+1(that is, in the embodiment of the present application
The second traffic forecast data and the first business datum difference), as Δ t>By (h+1) hour to 23 points when 0
Per hour predicted value plus Δ t (that is, in the embodiment of the present application difference is added to the second moment to settle accounts the moment it is corresponding
Traffic forecast data, the traffic forecast data per hour after being corrected per hour).Explanation is needed exist for, is such as schemed
Shown in 3b, when implement data than it is small when predicted value it is small when (that is, the first business datum is less than the second traffic forecast data
In the case of), then the actual business datum produced is extracted again, i.e. after the first moment, before the clearing moment, extract
Business datum, until the adjacent position moment after the business datum the extracted extraction moment corresponding more than the business datum
Traffic forecast data；As shown in Figure 3 b, after a correcting process terminates, second-order correction will be entered and prepare flow,
That is, in the case of the traffic forecast data that the T2 moment is more than in the business datum that there is the T1 moment, correction stream will be performed
Journey.
Fig. 4 be a kind of according to embodiments of the present invention one traffic forecast Data correction method in business datum and business it is pre-
Survey the curve synoptic diagram of data；The ratio that accumulative portfolio of each hour accounts for total business volume is first obtained according to historical data, so
Same day Traffic prediction value is multiplied by afterwards, the predicted value of 24 small time points of the same day is obtained, and one is drawn accordingly with hour
For transverse axis, portfolio is the prediction curve of the longitudinal axis.When real time data is bigger than next hour data, the difference is calculated,
And be that completion is made up the difference all plus the difference by the predicted value of each small time point behind current time.As shown in figure 4,10 points it
Dotted portion afterwards is all predicted value, and 23 points of value is the total predicted value X of portfolio, 09:15:20 numbers obtained in real time
According to for T9, T9 is compared with the prediction data of 10 points of the integral point of its latter hour.Upper figure T9 values are not more pre- than 10 points
Measured value is very much not corrected, if but 09:15:The 20 picturesque thick lines of the data taken in real time, hence it is evident that find that its value compares 10
The predicted value of point is big, and curve now occurs in that bucket peak.This prediction is full of prunes, because curve performance is
Value after the cumulative data of hour, T10 is certainly bigger than T9, at least maintains an equal level, band can be reached by the technology of making up the difference
All predicted values put below are done a smooth lifting by the effect of pecked line, timely and effective to solve because the same day manages individual
The forecasting inaccuracy that effect is mutated and caused really even predicts the problem that goes against accepted conventions.
Method based on above-mentioned steps S202 to step S208, the embodiment of the present application the traffic forecast Data correction provided
" double 11 " or " this kind of single day promotion situation in double 12 ", can be applicable to the activity time except going for
The advertising campaign of two days is continued above, for example, the poly- activity to one's profit of continuous three days, golden week；Or a hour
Or the advertising campaign in preset time, based on above-mentioned environment, the method for traffic forecast Data correction in the embodiment of the present application
To the correction principle of business datum, i.e. no matter any advertising campaign, the activity start the previous day or previous time
The traffic forecast data in the advertising campaign period can be all generated in section, when being carried out in advertising campaign, if actual industry
Data of being engaged in are more than the corresponding traffic forecast data of moment adjacent time point, then by comparing the traffic forecast data and being somebody's turn to do
The business datum at moment, generates corrected value, and correct the moment adjacent time point to the clearing moment according to the corrected value
Traffic forecast data.
For example, by taking the promotion period of 3 days as an example, before 3 days promotion periods, by the promotion period activity in 3 days
Business datum is predicted, and then obtains the traffic forecast data of 3 days, i.e. Dday1、Dday2And Dday3
When in the activity in promotion in 3 days, it is assumed that the 11 of first day Day1:35:The business number of the actual generation of 30 seconds
It is more than the traffic forecast data Date2 of 12 points to 1 point 1 hours section according to Date1 ', then according to current industry
Business data Date1 ' and traffic forecast data Date2 generates the difference that corrected value J1, J1 can be Date1 ' and Date2
Value, when clearing time corresponding traffic forecast data Date2~Date12 is corrected on the day of to 12 points to Day1,
Can be by the way that J1 be added separately into the traffic forecast data, i.e. obtain Date2+J1~Date12+J1；When this
After correction terminates, 11 on the day of Day1:35:Also there is actual business datum after 30 (second levels) and be more than adjacent time
The corresponding traffic forecast data of point, then continue executing with and be compared business datum and traffic forecast data, and by than
The relatively corrected value of generation, corrects the adjacent time point to clearing moment on the same day corresponding traffic forecast data；Similarly, 3
The correction of the Day2 and Day3 of its promotion traffic forecast data is identical with the method in Day1, will not be repeated here.
Promotion period identical with 3 days was, in the advertising campaign of golden week, to the method for traffic forecast Data correction and 3 days
Promotion period it is identical.
If the promotion period of one hour, likewise, the previous day initiated in the advertising campaign in one hour, it will to hair
The business datum for playing one hour same day of promotion does a prediction, if on the day of advertising campaign, actual generation in this hour
Business datum is more than the corresponding traffic forecast data of this hour adjacent time point, then with above-mentioned traffic forecast Data correction
Method is identical, and corrected value is generated by the comparison of business datum and traffic forecast data, and then according to corrected value correction
Adjacent time point settled accounts the traffic forecast data at moment to the same day.
Here the method for the traffic forecast Data correction that the embodiment of the present application is provided goes for the one of Alibaba Co
Plant and calculate clothes using the big data of SQL (Structures Query Language, abbreviation SQL) deployment
Business (Open Data Processing Service, abbreviation ODPS) platform.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as to one it is
The combination of actions of row, but those skilled in the art should know, the present invention is not limited by described sequence of movement
System, because according to the present invention, some steps can be carried out sequentially or simultaneously using other.Secondly, art technology
Personnel should also know that embodiment described in this description belongs to preferred embodiment, involved action and module
Not necessarily necessary to the present invention.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of the traffic forecast Data correction of example can add the mode of required general hardware platform to realize by software, certainly
Can also the former be more preferably embodiment by hardware, but in many cases.Understood based on such, it is of the invention
The part that technical scheme substantially contributes to prior art in other words can be embodied in the form of software product,
The computer software product is stored in a storage medium (such as ROM/RAM, magnetic disc, CD), including some
Instruction is to cause a station terminal equipment (can be mobile phone, computer, server, or network equipment etc.) to perform
Method described in each embodiment of the invention.
Embodiment 2
According to embodiments of the present invention, a kind of device embodiment for being used to implement above method embodiment, this Shen are additionally provided
Please the device that is provided of above-described embodiment can run on computer terminals.
Fig. 5 is the structural representation of the device of according to embodiments of the present invention two traffic forecast Data correction.
As shown in figure 5, the device of the traffic forecast Data correction can include：Extraction module 52, judge module 54,
Computing module 56 and correction module 58.
Wherein, extraction module 52, for extracting the first business datum at the first moment, wherein, the first business data packet
Include：The business exchange hand produced at the first moment；Judge module 54, for judging the second moment corresponding second business
Whether prediction data is more than the first business datum, wherein, the second moment was time point adjacent after the first moment；Meter
Module 56 is calculated, in the case of being no in judged result, the second traffic forecast data and the first business datum are calculated
Difference；Correction module 58, for correcting for the second moment to clearing moment corresponding traffic forecast data according to difference.
From the foregoing, it will be observed that the scheme that the above embodiments of the present application two are provided, by extracting the first business number at the first moment
According to, wherein, the first business datum includes：The business exchange hand produced at the first moment；Judge that the second moment is corresponding
Whether the second traffic forecast data are more than the first business datum；In the case where judged result is no, the second business is calculated
The difference of prediction data and the first business datum；Corrected for the second moment to clearing moment corresponding traffic forecast according to difference
Data, have reached to managing the purpose that individual can be corrected in time when actual volume changed in second day, so that real
Technique effect of the lifting to Traffic prediction precision is showed, and then has solved due to lacking in the prior art to managing individual
The technology of correction prediction portfolio, causes prediction data less than real in the case of second day actual volume significant changes
Border portfolio, so that the low technical problem of the precision of prediction brought.
Herein it should be noted that said extracted module 52, judge module 54, computing module 56 and correction module 58
Corresponding to the step S202 in embodiment one to step S208, example that four modules are realized with corresponding step and
Application scenarios are identical, but are not limited to the disclosure of that of above-described embodiment one.It should be noted that above-mentioned module conduct
A part for device may operate in the terminal 10 of the offer of embodiment one, can be realized, also may be used by software
To be realized by hardware.
Optionally, Fig. 6 is a kind of structural representation of the device of according to embodiments of the present invention two traffic forecast Data correction
Figure.As shown in fig. 6, extraction module 52 includes：Judging unit 521 and extraction unit 522.
Wherein, judging unit 521, for judging whether the first moment was more than the clearing moment；Extraction unit 522, is used for
In the case where judged result is no, the first business datum is extracted.
Herein it should be noted that the step that above-mentioned judging unit 521 and extraction unit 522 correspond in embodiment one
Step1 and Step2 in S202, two modules are identical with example and application scenarios that the step of correspondence is realized, but
It is not limited to the disclosure of that of above-described embodiment one.It should be noted that above-mentioned module can be with as a part for device
In the terminal 10 that the offer of embodiment one is provided, it can be realized, can also be realized by hardware by software.
Optionally, Fig. 7 is that the structure of the device of according to embodiments of the present invention two another traffic forecast Data correction is shown
It is intended to.As shown in fig. 7, the device for the traffic forecast Data correction that the embodiment of the present application is provided also includes：Acquisition module
50 and data computation module 51.
Wherein, acquisition module 50, for before the first moment extracted the first business datum, obtaining traffic forecast data
The proportion of total business volume is accounted for the accumulation portfolio of preset time；Data computation module 51, for by traffic forecast data
The proportion for accounting for total business volume with the accumulation portfolio of preset time is calculated, and the business for obtaining correspondence Each point in time is pre-
Survey data.
Herein it should be noted that the step that above-mentioned acquisition module 50 and data computation module 51 correspond in embodiment one
Rapid S200 and step S201, two modules are identical with example and application scenarios that the step of correspondence is realized, but do not limit
In the disclosure of that of above-described embodiment one.It should be noted that above-mentioned module can be run as a part of of device
In the terminal 10 that embodiment one is provided, it can be realized, can also be realized by hardware by software.
Optionally, Fig. 8 is that the structure of the device of according to embodiments of the present invention two another traffic forecast Data correction is shown
It is intended to.As shown in figure 8, correction module 58 includes：Numerical generation unit 581 and correction unit 582.
Wherein, numerical generation unit 581, for generating corrected value according to difference；Unit 582 is corrected, for according to school
It is adjusted on the occasion of to the second moment to clearing moment corresponding traffic forecast data, the traffic forecast number after being corrected
According to.
Herein it should be noted that above-mentioned numerical generation unit 581 and correction unit 582 correspond in embodiment one
Step1 and Step2 in step S208, two modules are identical with example and application scenarios that the step of correspondence is realized,
But it is not limited to the disclosure of that of above-described embodiment one.It should be noted that above-mentioned module can as a part for device
To operate in the terminal 10 of the offer of embodiment one, it can be realized, can also be realized by hardware by software.
Further, optionally, Fig. 9 is the dress of according to embodiments of the present invention two another traffic forecast Data correction
The structural representation put.As shown in figure 9, correction unit 582 includes：First correction subelement 5821, numerical generation
Subelement 5822 and second corrects subelement 5823.
Wherein, the first correction subelement 5821, in the case where difference is defined as into corrected value, difference to be added to
Second moment extremely settled accounts moment corresponding traffic forecast data, the traffic forecast data after being corrected；Or, numerical value
Subelement 5822 is generated, for correcting proportion according to difference generation, and the positive proportion of high-ranking officers is defined as corrected value；Second school
Syndromes unit 5823, for being adjusted to the second moment to moment corresponding traffic forecast data are settled accounts according to correction proportion
It is whole, the traffic forecast data after being corrected.
Herein it should be noted that above-mentioned first correction subelement 5821, the school of numerical generation subelement 5822 and second
Syndromes unit 5823 corresponds to the step A to step C in Step2, three moulds in the step S208 in embodiment one
Block is identical with example and application scenarios that the step of correspondence is realized, but is not limited to the disclosure of that of above-described embodiment one.
It should be noted that above-mentioned module may operate in the terminal 10 of the offer of embodiment one as a part for device
In, it can be realized, can also be realized by hardware by software.
From the foregoing, it will be observed that the device for the traffic forecast Data correction that the embodiment of the present application is provided, by being extracted at the first moment
First business datum, and first business datum and the second traffic forecast data at the second moment are compared,
In the case that two traffic forecast data are less than the first business datum, the first business datum and the second traffic forecast data are calculated
Between difference, and according to the difference correct the second moment to settle accounts the moment traffic forecast data, pass through the technology of making up the difference
It can reach that all predicted values put below are done a smooth lifting by the effect with pecked line, it is timely and effective to solve because working as
Its forecasting inaccuracy managed individual effect mutation and caused really even predicts the problem that goes against accepted conventions.
Embodiment 3
Embodiments of the invention additionally provide a kind of storage medium.Alternatively, in the present embodiment, above-mentioned storage medium
It can be used for preserving the program code performed by the method for the traffic forecast Data correction that above-described embodiment one is provided.
Alternatively, in the present embodiment, above-mentioned storage medium can be located in computer network Computer terminal group
In any one terminal, or in any one mobile terminal in mobile terminal group.
Alternatively, in the present embodiment, storage medium is arranged to the program code that storage is used to perform following steps：
The first business datum is extracted at the first moment, wherein, the first business datum includes：The first moment produce business into
Friendship amount；Judge whether the second moment corresponding second traffic forecast data are more than the first business datum, wherein, when second
Carve as time point adjacent after the first moment；In the case where judged result is no, the second traffic forecast data are calculated
With the difference of the first business datum；Corrected for the second moment to clearing moment corresponding traffic forecast data according to difference.
Alternatively, in the present embodiment, storage medium is arranged to the program code that storage is used to perform following steps：
Judge whether the first moment was more than the clearing moment；In the case where judged result is no, the first business datum is extracted.
Alternatively, in the present embodiment, storage medium is arranged to the program code that storage is used to perform following steps：
Obtain day traffic forecast data and accumulation portfolio accounts for the proportion of total business volume per hour；By day traffic forecast data and often
The proportion that hour accumulation portfolio accounts for total business volume is calculated, and obtains traffic forecast data per hour.
Alternatively, in the present embodiment, storage medium is arranged to the program code that storage is used to perform following steps：
Day traffic forecast data and the product of proportion are calculated, product is defined as traffic forecast data per hour.
Alternatively, in the present embodiment, storage medium is arranged to the program code that storage is used to perform following steps：
Difference was added into for the second moment to daily settlement moment corresponding traffic forecast data per hour are worked as, it is every small after being corrected
When traffic forecast data.
The embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in some embodiment
The part of detailed description, may refer to the associated description of other embodiment.
, can be by other in several embodiments provided herein, it should be understood that disclosed technology contents
Mode realize.Wherein, device embodiment described above is only schematical, such as division of described unit,
It is only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component
Another system can be combined or be desirably integrated into, or some features can be ignored, or do not perform.It is another, institute
Display or the coupling each other discussed or direct-coupling or communication connection can be by some interfaces, unit or mould
The INDIRECT COUPLING of block or communication connection, can be electrical or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to
On multiple NEs.Some or all of unit therein can be selected to realize the present embodiment according to the actual needs
The purpose of scheme.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit realized using in the form of SFU software functional unit and as independent production marketing or in use,
It can be stored in a computer read/write memory medium.Understood based on such, technical scheme essence
On all or part of the part that is contributed in other words to prior art or the technical scheme can be with software product
Form is embodied, and the computer software product is stored in a storage medium, including some instructions are to cause one
Platform computer equipment (can be personal computer, server or network equipment etc.) performs each embodiment institute of the invention
State all or part of step of method.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disc or
CD etc. is various can be with the medium of store program codes.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improve and moistened
Decorations also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of method of traffic forecast Data correction, it is characterised in that including：
The first business datum is extracted at the first moment, wherein, first business datum includes：Described first
The business exchange hand that moment produces；
Judge whether the second moment corresponding second traffic forecast data are more than first business datum, wherein,
Second moment is time point adjacent after first moment；
In the case where judged result is no, the second traffic forecast data and first business datum are calculated
Difference；
Second moment is corrected to clearing moment corresponding traffic forecast data according to the difference.
2. according to the method described in claim 1, it is characterised in that described to extract the first business data packet at the first moment
Include：
Judge whether first moment is more than the clearing moment；
In the case where judged result is no, first business datum is extracted.
3. according to the method described in claim 1, it is characterised in that it is described extracted at the first moment the first business datum it
Before, methods described also includes：
The accumulation portfolio of acquisition traffic forecast data and preset time accounts for the proportion of total business volume；
The proportion that the accumulation portfolio of the traffic forecast data and the preset time is accounted for into total business volume is counted
Calculate, obtain the traffic forecast data of correspondence Each point in time.
4. according to the method described in claim 1, it is characterised in that described to correct second moment according to the difference
Include to clearing moment corresponding traffic forecast data：
Corrected value is generated according to the difference；
Second moment to the clearing moment corresponding traffic forecast data are adjusted according to the corrected value
It is whole, the traffic forecast data after being corrected.
5. method according to claim 4, it is characterised in that it is described according to the corrected value to second moment
It is adjusted to the clearing moment corresponding traffic forecast data, the traffic forecast data after being corrected
Including：
In the case where the difference is defined as into the corrected value, the difference is added into second moment extremely
It is described to settle accounts moment corresponding traffic forecast data, the traffic forecast data after being corrected；Or,
It is defined as the corrected value according to difference generation correction proportion, and by the correction proportion；
Second moment to the clearing moment corresponding traffic forecast data are carried out according to the correction proportion
Adjustment, the traffic forecast data after being corrected.
6. a kind of device of traffic forecast Data correction, it is characterised in that including：
Extraction module, for extracting the first business datum at the first moment, wherein, first business data packet
Include：The business exchange hand produced at first moment；
Judge module, for judging whether the second moment corresponding second traffic forecast data are more than first industry
Business data, wherein, second moment is time point adjacent after first moment；
Computing module, in the case of being no in judged result, calculates the second traffic forecast data and institute
State the difference of the first business datum；
Correction module, for correcting second moment to clearing moment corresponding traffic forecast according to the difference
Data.
7. device according to claim 6, it is characterised in that the extraction module includes：
Judging unit, for judging whether first moment is more than the clearing moment；
Extraction unit, in the case of being no in judged result, extracts first business datum.
8. device according to claim 6, it is characterised in that described device also includes：
Acquisition module, for before the first business datum of the first moment extraction, obtaining traffic forecast data and pre-
If the accumulation portfolio of time accounts for the proportion of total business volume；
Data computation module, for the accumulation portfolio of the traffic forecast data and the preset time to be accounted for into industry
The proportion of business total amount is calculated, and obtains the traffic forecast data of correspondence Each point in time.
9. device according to claim 6, it is characterised in that the correction module includes：
Numerical generation unit, for generating corrected value according to the difference；
Unit is corrected, for settling accounts moment corresponding business to described to second moment according to the corrected value
Prediction data is adjusted, the traffic forecast data after being corrected.
10. device according to claim 9, it is characterised in that the correction unit includes：
First correction subelement, in the case where the difference is defined as into the corrected value, by the difference
Value adds to second moment to the clearing moment corresponding traffic forecast data, the industry after being corrected
Business prediction data；Or,
Numerical generation subelement, for being determined according to difference generation correction proportion, and by the correction proportion
For the corrected value；
Second correction subelement, for second moment to the clearing moment corresponding traffic forecast data
It is adjusted according to the correction proportion, the traffic forecast data after being corrected.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610204277.5A CN107292649A (en) | 2016-04-01 | 2016-04-01 | The method and apparatus of traffic forecast Data correction |
| TW106107621A TW201737164A (en) | 2016-04-01 | 2017-03-08 | Method and apparatus for correcting service data prediction |
| PCT/CN2017/077243 WO2017167041A1 (en) | 2016-04-01 | 2017-03-20 | Method and apparatus for correcting service data prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610204277.5A CN107292649A (en) | 2016-04-01 | 2016-04-01 | The method and apparatus of traffic forecast Data correction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107292649A true CN107292649A (en) | 2017-10-24 |
Family
ID=59963443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610204277.5A Pending CN107292649A (en) | 2016-04-01 | 2016-04-01 | The method and apparatus of traffic forecast Data correction |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN107292649A (en) |
| TW (1) | TW201737164A (en) |
| WO (1) | WO2017167041A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019192262A1 (en) * | 2018-04-02 | 2019-10-10 | 阿里巴巴集团控股有限公司 | Method, apparatus and device for evaluating operation conditions of merchant |
| CN111311014A (en) * | 2020-02-27 | 2020-06-19 | 广州酷旅旅行社有限公司 | Service data processing method and device, computer equipment and storage medium |
| CN112488377A (en) * | 2020-11-25 | 2021-03-12 | 上海中通吉网络技术有限公司 | Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101729690A (en) * | 2008-10-20 | 2010-06-09 | 中兴通讯股份有限公司 | System and method for scheduling shifts |
| CN103678514A (en) * | 2013-11-26 | 2014-03-26 | 安徽科大讯飞信息科技股份有限公司 | Business trend prediction method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102711177A (en) * | 2012-04-26 | 2012-10-03 | 北京邮电大学 | Service prediction based load balancing method |
| CN103490956A (en) * | 2013-09-22 | 2014-01-01 | 杭州华为数字技术有限公司 | Self-adaptive energy-saving control method, device and system based on traffic predication |
| CN105205297B (en) * | 2014-06-12 | 2020-04-03 | 腾讯科技（深圳）有限公司 | Service prediction method and system based on time sequence |
-
2016
- 2016-04-01 CN CN201610204277.5A patent/CN107292649A/en active Pending
-
2017
- 2017-03-08 TW TW106107621A patent/TW201737164A/en unknown
- 2017-03-20 WO PCT/CN2017/077243 patent/WO2017167041A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101729690A (en) * | 2008-10-20 | 2010-06-09 | 中兴通讯股份有限公司 | System and method for scheduling shifts |
| CN103678514A (en) * | 2013-11-26 | 2014-03-26 | 安徽科大讯飞信息科技股份有限公司 | Business trend prediction method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019192262A1 (en) * | 2018-04-02 | 2019-10-10 | 阿里巴巴集团控股有限公司 | Method, apparatus and device for evaluating operation conditions of merchant |
| CN111311014A (en) * | 2020-02-27 | 2020-06-19 | 广州酷旅旅行社有限公司 | Service data processing method and device, computer equipment and storage medium |
| CN111311014B (en) * | 2020-02-27 | 2024-04-12 | 广州酷旅旅行社有限公司 | Service data processing method, device, computer equipment and storage medium |
| CN112488377A (en) * | 2020-11-25 | 2021-03-12 | 上海中通吉网络技术有限公司 | Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017167041A1 (en) | 2017-10-05 |
| TW201737164A (en) | 2017-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Van Ryzin et al. | Computing virtual nesting controls for network revenue management under customer choice behavior | |
| CN108345958A (en) | A kind of order goes out to eat time prediction model construction, prediction technique, model and device | |
| CN104252680B (en) | Keyword automatic pricing method and search engine marketing system | |
| CN107292649A (en) | The method and apparatus of traffic forecast Data correction | |
| CN109544233A (en) | A kind of fashion product needing forecasting method towards electric business business | |
| CN112734392B (en) | BIM engineering project cost rapid calculation system and method | |
| CN104268715A (en) | Performance appraisal system and method | |
| CN108038740A (en) | The crowdsourcing platform task price and distribution method of time-sensitive | |
| CN109829758A (en) | Sales Volume of Commodity prediction technique and system towards more duration of insurances | |
| US8412559B2 (en) | Systems and methods for improved calculation of coefficient for price sensitivity | |
| Karlsson | Feedback control in programmatic advertising: The frontier of optimization in real-time bidding | |
| CN112700200B (en) | Method, device and medium for delivering express terminal | |
| CN101197010A (en) | Working flow distribution system and method | |
| CN113344467A (en) | Method and device for predicting capital of electric power engineering | |
| JPH05314094A (en) | Sales prediction supporting device | |
| CN107025575A (en) | Brand client KPI predictor methods in sequencing advertisement putting | |
| Lian et al. | Rolling‐horizon replenishment: Policies and performance analysis | |
| Li | Design and analysis of robust kanban system in an uncertain environment | |
| Banks et al. | Discrete-event system simulationfourth edition | |
| Miao et al. | Agile forecasting of dynamic logistics demand | |
| US20030204468A1 (en) | Stock planning method | |
| CN102855584A (en) | Commodity price predicting method based on linear interpolation and self-adaptive sliding window | |
| CN113554204A (en) | Method, device, storage medium and electronic equipment for determining event probability | |
| CN110533485A (en) | A kind of method, apparatus of object select, storage medium and electronic equipment | |
| CN106803198A (en) | Control method of bidding, device and terminal for party in request's platform |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1245969 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |