CN107038492A - Daily Order volume Forecasting Methodology and device based on Arma models - Google Patents
Daily Order volume Forecasting Methodology and device based on Arma models Download PDFInfo
- Publication number
- CN107038492A CN107038492A CN201610079381.6A CN201610079381A CN107038492A CN 107038492 A CN107038492 A CN 107038492A CN 201610079381 A CN201610079381 A CN 201610079381A CN 107038492 A CN107038492 A CN 107038492A
- Authority
- CN
- China
- Prior art keywords
- historical data
- arma
- order
- daily
- preset time
- 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"
Abstract
Present disclose provides a kind of daily Order volume Forecasting Methodology based on Arma models and device.The Forecasting Methodology includes：Obtain the historical data of the successful order in the first preset time period；The Arma models selected are fitted using the historical data to reconcile the multiple parameters of the Arma models；Using reconciling the daily success quantity on order of the following preset number of days of the Arma model predictions after parameter.The prediction meanss that the disclosure is provided are used to realize above-mentioned Forecasting Methodology.The disclosure can accurately predict the daily success quantity on order of following preset number of days, so as to provide reference to formulate effective marketing strategy.
Description
Technical field
This disclosure relates to computer processing technology field, more particularly to a kind of daily Order volume based on Arma models
Forecasting Methodology and device.
Background technology
Daily order numbers are the important service indexs of sales department.To formulate rational marketing strategy, it is necessary to following index
Make effective prediction, gain supplies to realize the good development of business.However, many factors either objectively or subjectively can be to daily
Conclusion of the business order numbers produce influence.Objective aspects, such as weather, weekend, the Spring Festival；Subjective aspect, such as subsidy amount, incentive measure
Deng all can influence index to a certain extent.
Aspect is being predicted to index, Normal practice is the correlation between each factor of the daily Order volume of analyzing influence
Property, provide daily Order volume Forecasting Methodology from influence factor angle.There is following drawback in above-mentioned Normal practice：
First, it is no matter subjective or objective, weather conditions, subsidy factor, working day factor, Spring Festival Marketing Factors factor data
The not congruent reason in storehouse does not have available explicit or historical data, thus, the historical datas of these elements in lane database not
It can be corresponded to well.
Secondly, if setting up model based on influence factor, need prediction target indicator before pre-estimate these influence because
The future value of element, then daily order fixture number purpose prediction is done in the prediction based on these influence factors again.Thus, it is such pre-
Survey can be related to two step errors：Factor predicated error and target prediction error, thus, the confidence level of target indicator prediction can be reduced.
Disclosure
For the defect of prior art, the disclosure provides a kind of daily Order volume Forecasting Methodology based on Arma models
And device, during for solving not corresponded to historical data preferably by subjective factor in the prior art and set up model prediction data
The technical problem for the two step errors brought.
In a first aspect, present disclose provides a kind of daily Order volume Forecasting Methodology based on Arma models, it is described pre-
Survey method includes：
Obtain the historical data of the successful order in the first preset time period；
The Arma models selected are fitted using the historical data to reconcile the multiple parameters of the Arma models；
Using reconciling the daily success quantity on order of the following preset number of days of the Arma model predictions after parameter.
Preferably, the Arma models selected are obtained using following steps：
Obtain the historical data in the second preset time period；
The Arma is set up by curve matching and method for parameter estimation using the historical data in second preset time period
Model.
Preferably, first preset time period is identical with the second preset time segment length；
Or,
First preset time period is second preset time period and the following preset number of days sum.
Preferably, it is characterised in that the Arma models selected are represented using below equation：
In formula, XtRepresent the conclusion of the business quantity on order of t；C is constant term；εtRepresent the average value of daily quantity on order；
Represent the weight of conclusion of the business quantity on order not in the same time；θjRepresent the weight of daily quantity on order；P represents to include p in the model
Individual autoregression；Q is represented in the model comprising q rolling average.
Second aspect, it is described pre- present disclose provides a kind of daily Order volume prediction meanss based on Arma models
Surveying device includes：
Historical data acquiring unit, the historical data for obtaining the successful order in the first preset time period；
Arma model parameters reconcile unit, for being fitted the Arma models selected using the historical data to reconcile this
The multiple parameters of Arma models；
Success order forecasting unit, for using reconcile the following preset number of days of Arma model predictions after parameter it is daily into
Work(quantity on order.
Preferably, the prediction meanss also set up unit including Arma models, and the Arma models, which set up unit, to be included：
Historical data acquisition module, for obtaining the historical data in the second preset time period；
Arma model building modules, for passing through curve matching and ginseng using the historical data in second preset time period
Number estimation method sets up the Arma models.
Preferably, in the historical data acquiring unit the in the first preset time period and the historical data acquisition module
The length of two preset time periods is identical；
Or,
The first preset time period is preset in the historical data acquisition module second in the historical data acquiring unit
Period and following preset number of days sum.
Preferably, the Arma model parameters mediation unit represents selected Arma models using below equation：
From such scheme, the disclosure is by directly joining the historical data in first time period to Arma models
Number reconciles, using reconciling daily success quantity on order of the Arma models after parameter to following preset number of days.Due to historical data
It is authentic and valid, and sets up in model process and will not be influenceed by subjective factor and objective factor, can avoids occurring
The problem of setting up the two step error brought during model prediction data in the prior art, thus the daily success order of disclosure prediction
Quantity is more accurate, so as to provide parameter to formulate effective marketing strategy.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of the embodiment of the present disclosure or technical scheme of the prior art
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some disclosed embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these figures.
Fig. 1 is that the flow for the daily Order volume Forecasting Methodology based on Arma models that the embodiment of the disclosure one is provided is shown
It is intended to；
Fig. 2 is the specific schematic diagram that predicts the outcome of Forecasting Methodology shown in Fig. 1；
Fig. 3 is the daily Order volume prediction meanss block diagram based on Arma models that another embodiment of the disclosure is provided；
Fig. 4 is the daily Order volume prediction meanss block diagram based on Arma models that the another embodiment of the disclosure is provided.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present disclosure, the technical scheme in the embodiment of the present disclosure is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the disclosure, rather than whole embodiments.It is based on
Embodiment in the disclosure, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of disclosure protection.
As shown in figure 1, the daily Order volume Forecasting Methodology based on Arma models that the embodiment of the disclosure one is provided, institute
Stating Forecasting Methodology includes：
S11, the successful order obtained in the first preset time period historical data.
To avoid the influence that the selection due to subjective factor or objective factor is brought to predicting the outcome, the disclosure one is implemented
The historical data of successful order in the first preset time period is directly used in example as foundation.Due to first preset time period
Interior successful quantity on order be it is random and effective, using the historical data can than it is more objective reflection driver's competition for orders or
The rule of passenger's chauffeur, therefore the confidence level of subsequent prediction process can be improved.
It should be noted that the first preset time period comprising a number of natural number of days or calculating cycle constitute when
Between fragment.Natural number of days terminates since daily 0 point to 24 points, and calculating cycle then can be identical with natural number of days,
Can be using 12 hours as calculating cycle.For convenience of explanation, nature number of days is used uniformly in the disclosure to illustrate.This area skill
Art personnel should be understood that first preset time period can include many days, how all or many month, can be according to specifically using field
Scape selects suitable calculating cycle, and the disclosure is not construed as limiting.
S12, using the historical data it is fitted the Arma models selected to reconcile the multiple parameters of the Arma models.
Also needed in the disclosure selected autoregressive moving average (Auto-Regressive and Moving Average,
Arma) model.It should be noted that the disclosure, which selectes Arma models, can use Arma models of the prior art, so
It is fitted to obtain being adapted to the Arma models of the disclosure using the historical data in step S11 afterwards.
Arma models newly are set up to improve in the confidence level of prediction process, the disclosure, are comprised the following steps：
S121, the historical data obtained in the second preset time period；
S122, set up using the historical data in second preset time period by curve matching and method for parameter estimation should
Arma models.
It should be noted that the second preset time period includes identical time slice with the first preset time period, both adopt
With same calculating cycle, the description to the first preset time period is specifically referred to, be will not be repeated here.
It should also be noted that, step S122 is using curve-fitting method of the prior art and ginseng in the embodiment of the present disclosure
Number estimation method sets up above-mentioned Arma models.Those skilled in the art, which can also select, to be had and curve-fitting method or parameter
The other method that method of estimation has same effect realizes that the disclosure is not construed as limiting.
Preferably, the Arma models set up in the embodiment of the present disclosure are indicated using below equation：
In formula (1), in formula, XtRepresent the conclusion of the business quantity on order of t；C is constant term；εtRepresent daily quantity on order
Average value；Represent the weight of conclusion of the business quantity on order not in the same time；θjRepresent the weight of daily quantity on order；P represents this
P autoregression is included in model；Q is represented in the model comprising q rolling average.
Above-mentioned Arma models substantially at any time passage formed by a random sequence.I.e. according to historical data with when
Between changing rule obtain prediction data, the prediction data is the continuity of historical data in time.The Arma models are not only examined
Influence of the various factors to predicting the outcome is considered, has allowed also for the Self-variation rule of historical data, improved prediction
The confidence level of data.
S13, using reconciling the daily success quantity on order of the following preset number of days of the Arma model predictions after parameter.
The daily success quantity on order of following preset number of days is predicted in the embodiment of the present disclosure using formula (1).
Arma models in the embodiment of the present disclosure after acquired mediation parameter are eventually restrained, and predicted time is got over
Long, data fluctuations will be less and less, thus the prediction degree of reliability will be lower.Therefore, only predicting following default day in the disclosure
Several daily success quantity on orders.The following preset number of days can be several days, several all or some months.During the following preset number of days
Between more short then acquired daily success quantity on order it is more accurate, therefore those skilled in the art can according to above-mentioned principle and
Specifically used occasion reasonable disposition parameter.
In practical application, the Arma models that the disclosure is provided can only adjust primary parameter, i.e., only using once above-mentioned pre-
Survey method obtains daily successful quantity on order.The now length phase of the first preset time period and the second preset time period
Together.Sometimes need more accurate daily successful quantity on order, can now adjust second time period length (by this second
The length adjustment of period is to including more historical datas), every time using history during this Forecasting Methodology using these last few days
The make compromises parameter of Arma models of data obtains daily successful quantity on order.Now the first preset time period is second default
Period and the following preset number of days sum.Certainly, the second preset time period is alternatively regular length, per subharmonic parameter
When, several days historical datas of foremost are deleted, the historical data of the successful order of nearest identical number of days included required
Among historical data, the confidence level of pre- quantitation can also be so improved.Those skilled in the art can be according to specifically used field
Conjunction is selected, and the disclosure is not construed as limiting.
For embody that the disclosure provides it is a kind of based on daily Order volume Forecasting Methodology validity, the reality of the disclosure one
Apply in example, adopt the following default 90 days daily success quantity on order of historical data prediction of 220 days.As shown in Fig. 2 horizontal in Fig. 2
Coordinate is historical data before the 220th day, is prediction data after the 220th day, and ordinate is daily success quantity on order.Can be with
Find out, the daily Order volume Forecasting Methodology based on Arma models that the disclosure is provided can accurately predict following daily success
The quantity of order.
As shown in figure 3, another embodiment of the disclosure provides a kind of daily Order volume prediction based on Arma models
Device, realizes, the test device includes based on Forecasting Methodology described above：
Historical data acquiring unit 11, the historical data for obtaining the successful order in the first preset time period；
Arma model parameters reconcile unit 12, for being fitted the Arma models selected using the historical data to reconcile this
The multiple parameters of Arma models；
Success order forecasting unit 13, for using reconciling the daily of the following preset number of days of Arma model predictions after parameter
Success quantity on order.
As shown in figure 4, the another embodiment of the disclosure provides a kind of daily Order volume prediction based on Arma models
Device；Unit 21,22,23 is identical with the unit 11,12,13 in Fig. 3 in Fig. 4, will not be repeated here.Fig. 4 also includes：
Arma models set up unit 24, and the Arma models, which set up unit 24, to be included：
Historical data acquisition module 241, for obtaining the historical data in the second preset time period；
Arma model building modules 242, for passing through curve matching using the historical data in second preset time period
The Arma models are set up with method for parameter estimation.
Preferably, the first preset time period and the historical data acquisition module in the historical data acquiring unit 21
The length of second preset time period is identical in 241；
Or,
First preset time period is second in the historical data acquisition module 241 in the historical data acquiring unit 21
Preset time period and following preset number of days sum.
Preferably, the Arma model parameters mediation unit 22 represents selected Arma models using below equation：
It should be noted that the prediction meanss shown in Fig. 3 and Fig. 4 are in addition to Arma models set up unit 24, other parts
It is all identical.To simplify the length of the disclosure, it will be obvious to one with ordinary skill in the art that preferred scheme below is all to above-mentioned two
The restriction explanation of prediction meanss.
For device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, it is related
Part illustrates referring to the part of embodiment of the method.
It should be noted that disclosed in the present embodiment in all parts of device, it is right according to the function that it to be realized
Part therein has carried out logical partitioning, still, and the present disclosure is not limited thereto, and all parts can be carried out again as needed
Divide or combine, for example, can be single part by some component combinations, or some parts can be further broken into
More subassemblies.
The all parts embodiment of the disclosure can realize with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize some or all portions in the system according to the embodiment of the present disclosure
The some or all functions of part.The disclosure is also implemented as the part or complete for performing method as described herein
The equipment or program of device (for example, computer program and computer program product) in portion.Such program for realizing the disclosure
It can store on a computer-readable medium, or can have the form of one or more signal.Such signal can be with
Download and obtain from internet website, either provide or provided in any other form on carrier signal.
As shown from the above technical solution, the prediction of the daily Order volume based on Arma models that the embodiment of the present disclosure is provided
Method and device, by the way that the historical data in first time period directly is carried out into parameter mediation to Arma models, is joined using reconciling
The daily success quantity on order of Arma models after number to following preset number of days.Because historical data is authentic and valid, and build
It will not be influenceed during formwork erection type by subjective factor and objective factor, can avoid occurring to set up model in the prior art
The problem of two step error brought during prediction data, thus the daily success quantity on order of disclosure prediction is more accurate, so as to
To provide parameter to formulate effective marketing strategy.
The disclosure is limited it should be noted that above-described embodiment is illustrated rather than to the disclosure, and this
Art personnel can design alternative embodiment without departing from the scope of the appended claims.In claim
In, any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" is not excluded for depositing
In element or step not listed in the claims.Word "a" or "an" before element do not exclude the presence of it is multiple this
The element of sample.The disclosure can be by means of including the hardware of some different elements and being come by means of properly programmed computer
Realize.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware
Embody.The use of word first, second, and third does not indicate that any order.These words can be construed to
Title.
Embodiment of above is only suitable to the explanation disclosure, and limitation not of this disclosure, about the common of technical field
Technical staff, in the case where not departing from spirit and scope of the present disclosure, can also make a variety of changes and modification, therefore all
Equivalent technical scheme falls within the category of the disclosure, and the scope of patent protection of the disclosure should be defined by the claims.
Claims (8)
1. a kind of daily Order volume Forecasting Methodology based on Arma models, it is characterised in that the Forecasting Methodology includes：
Obtain the historical data of the successful order in the first preset time period；
The Arma models selected are fitted using the historical data to reconcile the multiple parameters of the Arma models；
Using reconciling the daily success quantity on order of the following preset number of days of the Arma model predictions after parameter.
2. daily Order volume Forecasting Methodology according to claim 1, it is characterised in that the Arma models selected are adopted
Obtained with following steps：
Obtain the historical data in the second preset time period；
The Arma models are set up by curve matching and method for parameter estimation using the historical data in second preset time period.
3. daily Order volume Forecasting Methodology according to claim 2, it is characterised in that first preset time period
It is identical with the second preset time segment length；
Or,
First preset time period is second preset time period and the following preset number of days sum.
4. the daily Order volume Forecasting Methodology according to claims 1 to 3 any one, it is characterised in that select
Arma models represented using below equation：
In formula, XtRepresent the conclusion of the business quantity on order of t；C is constant term；εtRepresent the average value of daily quantity on order；Represent
The not weight of conclusion of the business quantity on order in the same time；θjRepresent the weight of daily quantity on order；P represents individual certainly comprising p in the model
Return item；Q is represented in the model comprising q rolling average.
Wherein X_t is the conclusion of the business quantity on order of t；C is constant term, the average value of the daily quantity on order of acute pyogenic infection of finger tip；When ε _ t is t
The error term at quarter；φ _ i, θ _ j are corresponding parameter item.
5. a kind of daily Order volume prediction meanss based on Arma models, it is characterised in that the prediction meanss include：
Historical data acquiring unit, the historical data for obtaining the successful order in the first preset time period；
Arma model parameters reconcile unit, for being fitted the Arma models selected using the historical data to reconcile the Arma moulds
The multiple parameters of type；
Success order forecasting unit, for using reconciling daily successfully the ordering of the following preset number of days of Arma model predictions after parameter
Odd number amount.
6. daily Order volume prediction meanss according to claim 5, it is characterised in that the prediction meanss also include
Arma models set up unit, and the Arma models, which set up unit, to be included：
Historical data acquisition module, for obtaining the historical data in the second preset time period；
Arma model building modules, for being estimated using the historical data in second preset time period by curve matching with parameter
Meter method sets up the Arma models.
7. daily Order volume prediction meanss according to claim 6, it is characterised in that the historical data acquiring unit
In the first preset time period it is identical with the length of the second preset time period in the historical data acquisition module；
Or,
The first preset time period is the second preset time in the historical data acquisition module in the historical data acquiring unit
Section and following preset number of days sum.
8. the daily Order volume prediction meanss according to claim 5~7 any one, it is characterised in that described
Arma model parameters mediation unit represents selected Arma models using below equation：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610079381.6A CN107038492A (en) | 2016-02-04 | 2016-02-04 | Daily Order volume Forecasting Methodology and device based on Arma models |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610079381.6A CN107038492A (en) | 2016-02-04 | 2016-02-04 | Daily Order volume Forecasting Methodology and device based on Arma models |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107038492A true CN107038492A (en) | 2017-08-11 |
Family
ID=59532061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610079381.6A Pending CN107038492A (en) | 2016-02-04 | 2016-02-04 | Daily Order volume Forecasting Methodology and device based on Arma models |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107038492A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426885A (en) * | 2017-08-28 | 2019-03-05 | 北京小度信息科技有限公司 | Order allocation method and device |
| CN109886489A (en) * | 2019-02-21 | 2019-06-14 | 上海德启信息科技有限公司 | Configuration system and method applied to transfer resource |
| CN110826949A (en) * | 2018-08-08 | 2020-02-21 | 北京京东振世信息技术有限公司 | Capacity control implementation method and device |
| CN111292106A (en) * | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining business demand influence factors |
| CN111768031A (en) * | 2020-06-24 | 2020-10-13 | 中电科华云信息技术有限公司 | Method for predicting crowd gathering tendency based on ARMA algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257133A1 (en) * | 2005-05-09 | 2010-10-07 | Crowe Keith E | Computer-Implemented System And Method For Storing Data Analysis Models |
| CN102252709A (en) * | 2011-04-22 | 2011-11-23 | 上海海洋大学 | Method for diagnosing faults of non-electricity measurement system |
-
2016
- 2016-02-04 CN CN201610079381.6A patent/CN107038492A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257133A1 (en) * | 2005-05-09 | 2010-10-07 | Crowe Keith E | Computer-Implemented System And Method For Storing Data Analysis Models |
| CN102252709A (en) * | 2011-04-22 | 2011-11-23 | 上海海洋大学 | Method for diagnosing faults of non-electricity measurement system |
Non-Patent Citations (2)
| Title |
|---|
| SUMMERSHENGG: "《ARMA模型的概念和构造》", 23 November 2010, HTTPS://WENKU.BAIDU.COM/VIEW/7A51AF0102020740BE1E9B71.HTML?SXTS=1594614894208 * |
| 李根 等: "《基于ARMA模型的世界集装箱船手持订单量预测研究》", 《科技管理研究》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426885A (en) * | 2017-08-28 | 2019-03-05 | 北京小度信息科技有限公司 | Order allocation method and device |
| CN110826949A (en) * | 2018-08-08 | 2020-02-21 | 北京京东振世信息技术有限公司 | Capacity control implementation method and device |
| CN111292106A (en) * | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining business demand influence factors |
| CN109886489A (en) * | 2019-02-21 | 2019-06-14 | 上海德启信息科技有限公司 | Configuration system and method applied to transfer resource |
| CN111768031A (en) * | 2020-06-24 | 2020-10-13 | 中电科华云信息技术有限公司 | Method for predicting crowd gathering tendency based on ARMA algorithm |
| CN111768031B (en) * | 2020-06-24 | 2023-09-19 | 中电科华云信息技术有限公司 | Method for predicting crowd gathering trend based on ARMA algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107038492A (en) | Daily Order volume Forecasting Methodology and device based on Arma models | |
| CN106549772B (en) | Resource prediction method, system and capacity management device | |
| CN104899663B (en) | A kind of data predication method and device | |
| CN104185840B (en) | It is used for being prioritized the mthods, systems and devices of multiple tests in lasting deployment streamline | |
| CN108491951A (en) | A kind of prediction technique, device and electronic equipment for taking out distribution time | |
| CN109409136A (en) | Block chain deposits the verification method, device and calculating equipment of card content | |
| CN106600344A (en) | Method and apparatus for obtaining active user data of target product | |
| CN108345958A (en) | A kind of order goes out to eat time prediction model construction, prediction technique, model and device | |
| CN106327324B (en) | A kind of quick calculation method and system of network behavior feature | |
| CN104025048B (en) | Method and system for estimating installation time of software product in operating environment | |
| CN109711720B (en) | Data quality evaluation method applied to crowd sensing | |
| CN109583946A (en) | A kind of forecasting system and method for active users | |
| US20190171990A1 (en) | Using historical plant-available water metrics to forecast crop yield | |
| CN106803799A (en) | A kind of performance test methods and device | |
| CN113268641B (en) | User data processing method based on big data and big data server | |
| CN103530390B (en) | The method and apparatus of webpage capture | |
| CN109635208A (en) | User, which visits, infers method for establishing model, device and storage medium | |
| CN110769034B (en) | Recommendation system strategy iteration method and device, storage medium and server | |
| AU2019340705A1 (en) | Optimized execution of fraud detection rules | |
| CN106469332A (en) | A kind of data processing method and device | |
| CN108230003A (en) | The dispensing effect analysis method and device of keyword | |
| CN111415027A (en) | Method and device for constructing component prediction model | |
| CN109409559A (en) | The determination method and device of Production Decline Prediction of Oilfield rate | |
| CN109635996A (en) | Room rate tendency look-forward model construction method, device and storage medium | |
| CN106991039A (en) | Method of testing and device for platform adaptive automotive engine system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201209 Address after: Building 34, yard 8, Dongbei Wangxi Road, Haidian District, Beijing 100193 Applicant after: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT Co.,Ltd. Address before: Room 219-23, 2 / F, block D, comprehensive service area, Nangang Industrial Zone, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin 300480 Applicant before: Didi (China) Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170811 |
|
| RJ01 | Rejection of invention patent application after publication |