CN109003126A - Bidding data processing method, device, electronic equipment and computer-readable medium - Google Patents
Bidding data processing method, device, electronic equipment and computer-readable medium Download PDFInfo
- Publication number
- CN109003126A CN109003126A CN201810713190.XA CN201810713190A CN109003126A CN 109003126 A CN109003126 A CN 109003126A CN 201810713190 A CN201810713190 A CN 201810713190A CN 109003126 A CN109003126 A CN 109003126A
- Authority
- CN
- China
- Prior art keywords
- bidding
- bid
- numerical value
- price
- request
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0273—Determination of fees for advertising
- G06Q30/0275—Auctions
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0611—Request for offers or quotes
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
Abstract
This disclosure relates to a kind of bidding data processing method, device, electronic equipment and computer-readable medium.This method comprises: obtaining bid request to be processed；The numerical value of bidding of the bid request is determined according to sample distribution algorithm；It is bid in commodity transaction platform by the numerical value of bidding.Bidding data processing method, device, electronic equipment and the computer-readable medium of the disclosure can reduce gray real time bid cost, improve the game initiative in real time bid.
Description
Technical field
This disclosure relates to computer information processing field, in particular to a kind of bidding data processing method, device,
Electronic equipment and computer-readable medium.
Background technique
Bid advertisement is that one kind is independently launched by user, is managed independently, the novel network advertisement paid according to advertising results
Form.When there is a advertisement exposure chance on advertisement bidding platform, the advertisement bidding platform meeting multiple advertisers of real time inquiring, advertisement
Main root goes out a price according to the quality of current advertisement exposure in real time and feeds back to advertisement bidding platform, and advertisement bidding platform can be current
The chance of advertisement exposure is given to the highest advertiser of bid, this is known as bid advertisement.
Party in request's platform (Demand Side Platform, DSP) is used as flow purchaser, and it is right in each request to need
Flow is bid.In order to realize maximum revenue, DSP needs go to explore flow market price.In currently existing scheme, DSP sniff
Price process is mainly as follows: sub-fraction flow being marked, high price sniff is fixed to this partial discharge, that is, right
The very high bid of this partial discharge setting (for example, unified 100 yuan of bid), it is flat to collect the corresponding advertisement bidding of this partial discharge
Platform bid after data, win valence fitting of distribution is carried out based on this part marked traffic.
Currently existing scheme is relatively simple in realization, but there are two main disadvantages: 1) flow explores higher cost, at
This risk is larger.2) game initiative is poor, is easy by the game strategies of other game participants discovery one's own side.
Therefore, it is necessary to a kind of new bidding data processing method, device, electronic equipment and computer-readable mediums.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
In view of this, the disclosure provides a kind of bidding data processing method, device, electronic equipment and computer-readable Jie
Matter can reduce gray real time bid cost, improve the game initiative in real time bid.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the one side of the disclosure, a kind of bidding data processing method is proposed, this method comprises: obtaining to be processed competing
Valence request；The numerical value of bidding of the bid request is determined according to sample distribution algorithm；By the numerical value of bidding in commodity transaction
It bids in platform.
In a kind of exemplary embodiment of the disclosure, obtaining bid request to be processed includes: by party in request's platform
Obtain multiple ad-requests；And the multiple ad-request shunt processing with obtain it is to be processed described in bid and ask
It asks.
In a kind of exemplary embodiment of the disclosure, the number of bidding of the bid request is determined according to sample distribution algorithm
Value includes: according to sample distribution formula, is at random the specified numerical value of bidding of the bid request.
It is specified for the bid request at random according to sample distribution formula in a kind of exemplary embodiment of the disclosure
The numerical value of bidding further include: when the numerical value of bidding is more than preset range, the sample distribution formula is normalized
Processing.
In a kind of exemplary embodiment of the disclosure, the sample distribution includes at least one following distribution: uniformly being divided
Cloth, multimode are uniformly distributed, Gaussian Profile, multimode Gaussian Profile and the distribution of time-varying multimode.
In a kind of exemplary embodiment of the disclosure, bid in commodity transaction platform by the numerical value of bidding
It include: to be bid in advertising platform by the numerical value of bidding, and pass through numerical value of bidding described in win valence packet acquisition
The corresponding winning price in the advertising platform.
In a kind of exemplary embodiment of the disclosure, market price analysis is carried out by the winning price.
In a kind of exemplary embodiment of the disclosure, market price distributional analysis packet is carried out by the winning price
It includes: the winning price being subjected to anti-sampling processing, obtains anti-sampled data；Reject the exceptional value in the anti-sampled data；
And market price distributional analysis is carried out by the anti-sampled data.
In a kind of exemplary embodiment of the disclosure, the winning price is subjected to anti-sampling processing, obtains anti-sampling
Data include: to determine anti-sampling formula according to the sample distribution algorithm；And pass through the anti-sampling formula and the triumph
Price obtains the anti-sampled data.
In a kind of exemplary embodiment of the disclosure, carrying out market price analysis by the anti-sampled data includes:
Win valence forecast analysis is carried out by the anti-sampled data；And win valence distributional analysis is carried out by the anti-sampled data.
According to the one side of the disclosure, a kind of bidding data processing unit is proposed, which includes: request module, is used for
Obtain bid request to be processed；It bids module, for determining the numerical value of bidding of the bid request according to sample distribution algorithm；
Bid module, for being bid in commodity transaction platform by the numerical value of bidding.
In a kind of exemplary embodiment of the disclosure, further includes: analysis module, for carrying out market by winning price
Price analysis.
According to the one side of the disclosure, a kind of electronic equipment is proposed, which includes: one or more processors；
Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, so that one
A or multiple processors realize such as methodology above.
According to the one side of the disclosure, it proposes a kind of computer-readable medium, is stored thereon with computer program, the program
Method as mentioned in the above is realized when being executed by processor.
According to bidding data processing method, device, electronic equipment and the computer-readable medium of the disclosure, can reduce wide
The real time bid cost of quotient is accused, the game initiative in real time bid is improved.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present disclosure, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of system block diagram of bidding data processing method and processing device shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of bidding data processing method shown according to an exemplary embodiment.
Fig. 3 is a kind of flow chart of the bidding data processing method shown according to another exemplary embodiment.
Fig. 4 is a kind of schematic diagram of the bidding data processing method shown according to another exemplary embodiment.
Fig. 5 is a kind of block diagram of the bidding data analytical equipment shown according to another exemplary embodiment.
Fig. 6 is a kind of block diagram of the bidding data analytical equipment shown according to another exemplary embodiment.
Fig. 7 is a kind of schematic diagram of the bidding data processing method shown according to another exemplary embodiment.
Fig. 8 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Fig. 9 is that a kind of computer readable storage medium schematic diagram is shown according to an exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the disclosure, therefore it cannot be used for the protection scope of the limitation disclosure.
In the application, noun and the English word abbreviation being related to are explained as follows:
RTB (RealTime Bidding) be it is a kind of using third party technology on each website of substantial amounts for every
One user advertising shows the technology of bidding that behavior is assessed and bid.Real time bid has been evaded invalid audient and has been reached,
Advertiser or its agency can carry out flow purchase for significant user.The core of RTB is DSP (Demand Side
) and the advertisement trade market ADX (AD Exchange) Platform.
ADX (AD Exchange) is the place for being similar to stock exchange, by ad serving side (site media) and
Flocking together carries out ad traffic transaction for party in request (advertiser or its agency).ADX is important online wide of one of DSP
Accuse one of source resource.ADX, which is one, can allow advertiser in the correct time, and correct media exposure is to suitable user's
Place, the RTB technology used in transaction can allow advertiser or its act on behalf of DSP auction advertisement shown in front of the user each time
Chance.
DSP (Demand Side Platform) is that agency is launched in the advertisement of advertiser, services for advertiser, represents advertisement
Main interests, after advertiser tells the dispensing demand of DSP oneself, DSP can carry out in the market media flow in the ADX of its docking
It selects and purchase and the dispensing of advertisement, and collects the certain commission of advertiser.
Present invention discovery, in traditional price competing method, when DSP ad system receives what ADX was sended over
When flow, the flow knock-down price of partial discharge sniff ADX can be used.DSP ad system can carry out this partial discharge very high
Bid (such as: unified 100 yuan of bid), since price is very high, thus these flows are just easy to competition and win.Because in divalent
In market, after winning flow, last price of deducting fees is the second high price, that is, the bid of second place competitor.And ADX meeting
This price of deducting fees is passed through win notice news DSP ad system.So, by accumulating and handling this part number
The distribution of this flow price in the market is just obtained according to, DSP ad system.In addition, DSP ad system can also utilize the win
Valence information carries out price fitting and bid model training, and then is subsequent flow competitive service.
But the mode of sniff price above, it is easy to by com-petitors identifying, and the sniff cost paid compared with
It is high.Based on above consideration, present applicant proposes bidding data processing method, this method can be used as the side for exploring flow market price
Method.Bidding data processing method in the application will be described in detail below.
Fig. 1 is a kind of system block diagram of bidding data processing method and processing device shown according to an exemplary embodiment.
As shown in Figure 1, system architecture 100 may include ustomer premises access equipment 101,102,103, network 104 and server
105.Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104
It may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used ustomer premises access equipment 101,102,103 and be interacted with server 105 by network 104, with reception or
Send message etc..Various telecommunication customer end applications, such as web browser can be installed on ustomer premises access equipment 101,102,103
Using, searching class application, instant messaging tools, platform software of bidding etc..Internet advertising can have for example been run on server 105
Transaction platform or the Internet auctions platform etc. system.
Ustomer premises access equipment 101,102,103 can be the various electronic equipments with display screen and supported web page browsing,
Including but not limited to smart phone, tablet computer, pocket computer on knee and desktop computer, server etc..
Server 105 can be to provide the server of various services, for example, to user using ustomer premises access equipment 101,102,
The 103 Internet advertising transaction platforms browsed provide the back-stage management server supported.Server 105 can be to receiving
The data such as inquiry request, bidding request carry out the processing such as analyzing, and processing result (such as winning valence price) is fed back to user terminal
Equipment.
Ustomer premises access equipment 101,102,103 can also for example be handled bid data, ustomer premises access equipment 101,102,103
Multiple bid requests to be processed can for example be obtained；Ustomer premises access equipment 101,102,103 can be for example true according to sample distribution algorithm
Multiple numerical value of bidding of fixed the multiple bid request；Ustomer premises access equipment 101,102,103 can for example pass through the numerical value of bidding
It bids in commodity transaction platform (server 105)；Ustomer premises access equipment 101,102,103 can for example pass through the triumph valence
Lattice carry out market price analysis.
Server 105 can for example receive the bidding data sended over by ustomer premises access equipment 101,102,103, server
105 can for example be comprehensively compared the bidding data that ustomer premises access equipment 101,102,103 sends over, and server 105 can be for example this
The chance of secondary advertisement exposure is given to the highest user equipment of bid.Bidding for second high price for example can be worth conduct by server 105
It deducts fees price, that is, deduct fees price of the bid as actually first place bidders of second place competitor.
Server 105 can be the server of an entity, also may be, for example, multiple server compositions, likewise, user
End equipment 101,102,103 can be the server of an entity, also may be, for example, multiple server compositions.
It should be noted that bidding data processing method provided by the embodiment of the present disclosure can by ustomer premises access equipment 101,
102, it 103 executes, correspondingly, bidding data analytical equipment can be set in ustomer premises access equipment 101,102,103.And it is supplied to
The page end that the page end and feedback that user bids win valence mumber evidence is normally in server 105.
According to bidding data processing method, device, electronic equipment and the computer-readable medium of the disclosure, can reduce wide
The real time bid cost of quotient is accused, the game initiative in real time bid is improved.
Fig. 2 is a kind of flow chart of bidding data processing method shown according to an exemplary embodiment.At bidding data
Reason method 20 includes at least step S202 to S208.
As shown in Fig. 2, obtaining bid request to be processed in S202.Bid request to be processed may be, for example, advertisement
Bid request also may be, for example, the bid request in other auction marketplaces, may be, for example, commodity bid request, physical assets or nothing
The auction bid request of shape assets, the application are not limited.
It in one embodiment, can be for example, obtaining multiple ad-requests by party in request's platform；And it will be the multiple wide
It accuses request and shunt processing to obtain the bid request to be processed.It specifically can be for example, when DSP ad system receives
When flow (the multiple ad-requests) that ADX is sended over, flow is shunted first, and the ratio specifically shunted can configure
(such as separate total flow request in 5% flow), with the flow knock-down price of this partial discharge sniff ADX.Wherein, advertisement is clear
The amount of looking at (ad views) is also referred to as web page browsing amount or impression, refers to that user is visited by banner in a specific time
Ask the number of webpage.
It in one embodiment, also may be, for example, bid request setting flag to be processed, to have label in subsequent tracking
Bid request win valence information.
In S204, the numerical value of bidding of the bid request is determined according to sample distribution algorithm.
In one embodiment, determine that the numerical value of bidding of the bid request includes: that basis is adopted according to sample distribution algorithm
Sample distribution formula is at random the specified numerical value of bidding of the bid request.Wherein, the sample distribution includes following at least one
A distribution: being uniformly distributed, and multimode is uniformly distributed, Gaussian Profile, multimode Gaussian Profile and the distribution of time-varying multimode.
In one embodiment, sample distribution algorithm can be the combination of single distribution either a variety of distributions.It takes point
The foundation of cloth can be related to various factors, such as: with KPI Key Performance Indicator (Key Performance Indicator, KPI)
Correlation, can also be for example, with click-through-rate (Click-Through-Rate, CTR) correlation, with conversion ratio (Conversion
Rate, CVR)；It can also be such as: related to the complexity of realization.
Wherein, KPI is to be configured, sampled by the key parameter of the input, output end to organization internal process, counted
Calculate, analysis, measure process performance a kind of target formula weight level of control, be the strategic objective of enterprise is decomposed into it is operable
The tool of target is the basis of enterprise performance management.
Wherein, CTR is the common term of Internet advertising, and referring to the web advertisement, (display advertising/copy/keyword is wide
Announcement/arranging advertisement/video ads etc.) click arrival rate, i.e., the actual click number of the advertisement divided by advertisement the amount of showing.
CTR is an important indicator for measuring Internet advertising effect.
Wherein, CVR is the index of a measurement CPA advertising results, is in brief exactly that user clicks advertisement to as one
Effectively activation or the registration even conversion ratio of paying customer.CPA (Cost Per Action) is a kind of advertisement charge mode,
As the term suggests carrying out charging as index according to behavior (Action).In advertising scenarios, CPA pricing mode refers to be launched by advertisement
Actual effect carrys out charging by the effective questionnaire or order of response, and unlimited spending on ads.
In traditional " fixed high price is explored ", a very high regular price is always gone out to detection flow.And in this Shen
Fixed high price please not be used in embodiment, but go out different bid prices with certain probability.
If final DSP ad system bid is x, selecting the probability density of bid x is f (x), is expressed according to above formula
If fixed bid mechanism, then the mathematic(al) representation of bid mechanism is fixed are as follows:
X=A；A is fixed numbers；
And f (x)=1.
And in this application, x can not be fixed numbers, it can be for example as follows:
minPrice<x<maxPrice；
And f (x) meets a certain distribution.
Wherein minPrice, maxPrice are two constants, and the foundation of range selection various can consider, such as
DSP ad system can for example be more concerned about certain section or the conduct minPrice and maxPrice of more valuable win valence range.
DSP ad system for example can go to generate a bid x according to the probability distribution that probability density is f (x).
In the present embodiment, be only described so that f (x) is to be uniformly distributed as an example (selection of distribution can there are many, including
But it is not limited to multimode is uniformly distributed, multimode Gaussian Profile, time-varying multimode are distributed etc., is uniformly distributed only one such), in order to
Description is convenient, assumes that the value of price can only be integer discrete value in this application.
Using being uniformly distributed, it is assumed that
MinPrice=0, maxPrice=100；
Probability density f (x)=1/ (maxPrice minPrice)=1/100；
And x is integer.
According to above formula, in the bid of DSP ad system, it is all 1/100 that 10 yuan of bid, 50 yuan of probability are identical.
In other words, go to determine the bid of labeled bid request according to 1/100 probability, practical bid can be 10 yuan, 20 yuan,
50 yuan etc., the probability that they are selected is identical, is 1/100.
It in one embodiment, is at random each of the multiple bid request according to the sample distribution formula
The specified numerical value of bidding of bid request further include: public to the sample distribution when the numerical value of bidding is more than preset range
Formula is normalized.Since the price of detection has certain range, if the distribution taken has been more than Price Range, need
Operation distribution is normalized.Probability density function p (x) after final normalization can be carried out for example on the basis of f (x)
Amendment generates, specifically:
In S206, bid in commodity transaction platform by the numerical value of bidding.It can also be for example, obtaining described competing
Valence mumber value corresponding winning price in the commodity transaction platform.It can be for example, passing through number of bidding described in the acquisition of win valence packet
Value corresponding winning price in the commodity transaction platform.
In one embodiment, it is bid in advertising platform by the numerical value of bidding.If with markd competing
Valence request, which is won, to be come, and ADX can will win valence packet and be back in DSP ad system in win message.
It in one embodiment, can also be for example, carrying out market price analysis by the winning price.It can for example,
Win valence forecast analysis is carried out by the anti-sampled data；And win valence distributional analysis is carried out by the anti-sampled data.
According to the bidding data processing method of the disclosure, by being at random that each of the multiple bid request is bidded
The specified numerical value of bidding of request, and the numerical value of bidding is launched into the mode bidded into advertisement bidding platform, it can
Gray real time bid cost is reduced, the game initiative in real time bid is improved.
It will be clearly understood that the present disclosure describes how to form and use particular example, but the principle of the disclosure is not limited to
These exemplary any details.On the contrary, the introduction based on disclosure disclosure, these principles can be applied to many other
Embodiment.
Fig. 3 is a kind of flow chart of the bidding data processing method shown according to another exemplary embodiment.It is shown in Fig. 3
Bidding data processing method 30 be to above " by the winning price carry out market price analysis " detailed description,
As shown in figure 3, the winning price is carried out anti-sampling processing, obtains anti-sampled data in S302.It can example
Such as, anti-sampling formula is determined according to the sample distribution algorithm；And it is obtained by the anti-sampling formula with the winning price
Take the anti-sampled data.
In divalent market, the data for the knock-down price x=10 member that DSP ad system receives, are inside DSP ad system
It is generated in the case of these of bid x satisfaction 10 < x < 100 yuan.The data of knock-down price x=50 member, are in DSP ad system
What face generated in the case of these of bid x satisfaction 50 < x < 100 yuan.So the distribution of the quantity of the winner's sample finally obtained
It is not uniformly to be distributed, thus need to correct data, the process of this data correction is referred to as in this application.Due to
The mode of bid can be to the win valence mumber being collected into according to having an impact, and the anti-effect sampled is exactly to allow win to remove this influence
Valence mumber evidence is restored to its true distribution.
In one embodiment, anti-sampling is expanded to data sample, such as to the win valence mumber of x=10 member according to sample
These samples are carried out 10/9 ratio expansion amount by this.Due to not being integer, then can to every sample according still further to 1/9 it is general
Rate replicates and is added sample pool, then the mean value of expansion amount on the whole just meets the requirements.To the win valence data sample of x=50 member,
It needs to carry out 2 times of ratio expansion amounts to these samples, that is, each sample replicates portion again and is added in entire sample pool.
For further, as shown in figure 4, reference axis x is bid, reference axis y is the probability density function f for selecting the bid
(x), the area that curve surrounds is 1, because are as follows:
In Win message analysis win valence mumber according to x ', x ' represent win valence mumber evidence, divalent in the market, its corresponding x that bids must
So meet x ' < x < maxPrice.Therefore in the bid request for winning valence, there is flow (the corresponding figure dash area of following ratio
Area) sample size of x ' can just be contributed:
Thus the anti-logic sampled is replicated and is added according to following ratio to the sample that valence is x ' is won also than more visible
Enter in sample pool, wherein g (x ') is the ratio of sample enlargement.
According to the above analysis, anti-oversampling ratio final in this application are as follows:
By taking equally distributed sampling algorithm as an example, probability distribution that anti-sampling when uses are as follows:
Anti- sampling multiple are as follows:
In S302, the exceptional value in the anti-sampled data is rejected.In some cases, such as x=minPrice or x
When=maxPrice, the anti-oversampling ratio g value calculated is very high, tends to be infinitely great, it is contemplated that these abnormal conditions are existing
Probability in real environment is very low, when encountering this abnormal conditions, directly rejects these abnormal datas.
In S302, market price distributional analysis is carried out by the anti-sampled data.
According to the bidding data processing method of the disclosure, the anti-mode sampled to win valence mumber according to carry out data extending, can
The price distribution for really reflecting bid advertisement is obtained, can be analyzed for the subsequent progress market price and valid data are provided.
It will be appreciated by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as being executed by CPU
Computer program.When the computer program is executed by CPU, above-mentioned function defined by the above method that the disclosure provides is executed
Energy.The program can store in a kind of computer readable storage medium, which can be read-only memory, magnetic
Disk or CD etc..
Further, it should be noted that above-mentioned attached drawing is only the place according to included by the method for disclosure exemplary embodiment
Reason schematically illustrates, rather than limits purpose.It can be readily appreciated that above-mentioned processing shown in the drawings is not indicated or is limited at these
The time sequencing of reason.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device
Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.
Fig. 5 is a kind of block diagram of the bidding data processing unit shown according to another exemplary embodiment.At bidding data
Reason device 50 includes: request module 502, module of bidding 504, module 506 of bidding and analysis module 508.
Request module 502 is for obtaining bid request to be processed；Bid request to be processed may be, for example, advertisement bidding
Request, also may be, for example, the bid request in other auction marketplaces, may be, for example, commodity bid request, physical assets or invisible money
The auction bid request of production, the application are not limited.
Module of bidding 504 is used to determine the numerical value of bidding of the bid request according to sample distribution algorithm；Implement at one
In example, sample distribution algorithm can be the combination of single distribution either a variety of distributions.Take distribution foundation can with it is various
Factor is related, such as: it, can also be for example, with point with KPI Key Performance Indicator (Key Performance Indicator, KPI) correlation
Percent of pass (Click-Through-Rate, CTR) correlation is hit, with conversion ratio (Conversion Rate, CVR)；It can also be such as:
It is related to the complexity of realization.
Bid module 506 is used to bid in commodity transaction platform by the numerical value of bidding.It can also be for example, obtaining
Numerical value corresponding winning price in the commodity transaction platform of bidding；It can be for example, bidding numerical value in advertisement by described
It bids in platform.If winning to come with markd bid request, ADX can will win valence packet and return in win message
Into DSP ad system.
Fig. 6 is a kind of block diagram of the bidding data analytical equipment shown according to another exemplary embodiment.At bidding data
Device 60 is managed on the basis of bidding data processing unit 50 further include: analysis module 602.
Analysis module 602 is used to carry out market price analysis by the winning price.It can be for example, passing through the anti-sampling
Data carry out win valence forecast analysis；And win valence distributional analysis is carried out by the anti-sampled data.
According to the bidding data analytical equipment of the disclosure, by being at random that each of the multiple bid request is bidded
The specified numerical value of bidding of request, and the numerical value of bidding is launched into the mode bidded into advertisement bidding platform, it can
Gray real time bid cost is reduced, the game initiative in real time bid is improved.
Fig. 7 is a kind of schematic diagram of the bidding data analytical equipment shown according to another exemplary embodiment.Fig. 7 is illustrated
The process of bidding data analytical equipment processing data in the application.Bidding data analytical equipment 70 includes: diverter module 702, is adopted
Egf block 704, anti-sampling module 706 win valence statistical module 708 and win valence fitting of distribution module 710.This Shen for ease of description
Please in content, further include bid module 714, ADX platform 712 in Fig. 7.
Diverter module 702, for shunting to the request that ADX is sent, specific shunt ratio is configurable.
Sampling module 704, for selecting the final bid of labeled flow.Fixation bid mechanism in the prior art
In, sampling module 704 is not needed, because being always a fixed price.
Anti- sampling module 706, ADX are issued and are contained win valence information in the win message of DSP, anti-sampling module 706 and sampling
Module 704 is corresponding.Anti- sampling module 706 extracts the relevant win log of labeled flow out from the log of win message first
Log, it is then counter to this partial data to be sampled.The anti-purpose sampled is to correct to data.In the prior art
Fixation bid mechanism in, due to there is no sampling module 704, also just without anti-sampling module 706.
The data that win valence statistical module 708 and the win anti-sampling module 706 of valence fitting of distribution module 710 are sent, to this portion
Divided data is operated, and is obtained final data distribution or won valence model.
Below by way of the signal flow of the dsp system in the application under Fig. 7 introduction:
1) ADX platform sends ad-request to DSP ad system.
2) it after DSP ad system receives ad-request, gives diverter module 702 and is shunted, separated fraction flow,
These flows carry out special marking, can be labeled as Exploration.
3) how the decision of sampling module 704 bids to Exploration flow.
4) result of the Exploration flow with bid information is returned to ADX by dsp system.
Come 5) if this part (Exploration) flow is finally won, ADX can will win valence packet in win message
It is returned as DSP ad system.
6) anti-sampling module 706 extracts win log relevant with Exploration flow, counter to be sampled, to restore number
According to normal distribution.
7) training of price model is carried out based on the data 6) generated by the, and then instructs subsequent DSP ad system
Advertisement launch.
Wherein, sampling module 704 and anti-sampling module 706 are a unified entirety, they are mutual corresponding, samplings
Module 704 can have an impact the data being collected into, and the effect of anti-sampling module 706 is exactly to allow number to remove this influence
It is really distributed according to its is restored to.
According to the bidding data analytical equipment of the disclosure, have the advantages that
1) RTB advertising cost is reduced.
2) RTB cost risk is reduced, game initiative is improved.When the flow seller is there are when game strategies or fraudulent policies,
The risk for being identified bidding strategies by the seller is reduced, and improves the initiative of buyer's DSP strategy.
Fig. 8 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
The electronic equipment 200 of this embodiment according to the disclosure is described referring to Fig. 8.The electronics that Fig. 8 is shown
Equipment 200 is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 8, electronic equipment 200 is showed in the form of universal computing device.The component of electronic equipment 200 can wrap
It includes but is not limited to: at least one processing unit 210, at least one storage unit 220, (including the storage of the different system components of connection
Unit 220 and processing unit 210) bus 230, display unit 240 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 210
Row, so that the processing unit 210 executes described in this specification above-mentioned electronic prescription circulation processing method part according to this
The step of disclosing various illustrative embodiments.For example, the processing unit 210 can be executed such as Fig. 2, walked shown in Fig. 3
Suddenly.
The storage unit 220 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 2201 and/or cache memory unit 2202 can further include read-only memory unit (ROM) 2203.
The storage unit 220 can also include program/practical work with one group of (at least one) program module 2205
Tool 2204, such program module 2205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 230 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 200 can also be with one or more external equipments 300 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 200 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 200 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 250.Also, electronic equipment 200 can be with
By network adapter 260 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 260 can be communicated by bus 230 with other modules of electronic equipment 200.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 200, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server or network equipment etc.) executes the above method according to disclosure embodiment.
Fig. 9 schematically shows a kind of computer readable storage medium schematic diagram in disclosure exemplary embodiment.
Refering to what is shown in Fig. 9, describing the program product for realizing the above method according to embodiment of the present disclosure
400, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, the program product of the disclosure is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by one
When the equipment executes, so that the computer-readable medium implements function such as: obtaining bid request to be processed；According to sampling point
Cloth algorithm determines the numerical value of bidding of the bid request；It is bid in commodity transaction platform by the numerical value of bidding.
It will be appreciated by those skilled in the art that above-mentioned each module can be distributed in device according to the description of embodiment, it can also
Uniquely it is different from one or more devices of the present embodiment with carrying out corresponding change.The module of above-described embodiment can be merged into
One module, can also be further split into multiple submodule.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, mobile terminal or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
It is particularly shown and described the exemplary embodiment of the disclosure above.It should be appreciated that the present disclosure is not limited to
Detailed construction, set-up mode or implementation method described herein；On the contrary, disclosure intention covers included in appended claims
Various modifications and equivalence setting in spirit and scope.
In addition, structure shown by this specification Figure of description, ratio, size etc., only to cooperate specification institute
Disclosure, for skilled in the art realises that be not limited to the enforceable qualifications of the disclosure with reading, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the disclosure
Under the technical effect and achieved purpose that can be generated, it should all still fall in technology contents disclosed in the disclosure and obtain and can cover
In the range of.Meanwhile cited such as "upper" in this specification, " first ", " second " and " one " term, be also only and be convenient for
Narration is illustrated, rather than to limit the enforceable range of the disclosure, relativeness is altered or modified, without substantive change
Under technology contents, when being also considered as the enforceable scope of the disclosure.
Claims (14)
1. a kind of bidding data processing method characterized by comprising
Obtain bid request to be processed；
The numerical value of bidding of the bid request is determined according to sample distribution algorithm；And
It is bid in commodity transaction platform by the numerical value of bidding.
2. the method as described in claim 1, which is characterized in that obtaining bid request to be processed includes:
Multiple ad-requests are obtained by party in request's platform；And
The multiple ad-request shunt processing to obtain the bid request to be processed.
3. the method as described in claim 1, which is characterized in that determine bidding for the bid request according to sample distribution algorithm
Numerical value includes:
It is at random the specified numerical value of bidding of the bid request according to sample distribution formula.
4. method as claimed in claim 3, which is characterized in that random to be asked for described bid according to the sample distribution formula
The specified numerical value of bidding is asked to include:
When the numerical value of bidding is more than preset range, the sample distribution formula is normalized.
5. method as claimed in claim 4, which is characterized in that the sample distribution includes at least one following distribution:
It is uniformly distributed, multimode is uniformly distributed, Gaussian Profile, multimode Gaussian Profile and the distribution of time-varying multimode.
6. the method as described in claim 1, which is characterized in that gone out in commodity transaction platform by the numerical value of bidding
Valence includes:
It is bid in advertising platform by the numerical value of bidding；And
By winning numerical value corresponding winning price in the advertising platform of bidding described in the acquisition of valence packet.
7. method as claimed in claim 6, which is characterized in that further include:
Market price analysis is carried out by the winning price.
8. the method for claim 7, which is characterized in that carry out market price distributional analysis packet by the winning price
It includes:
The winning price is subjected to anti-sampling processing, obtains anti-sampled data；
Reject the exceptional value in the anti-sampled data；And
Market price distributional analysis is carried out by the anti-sampled data.
9. method according to claim 8, which is characterized in that the winning price is carried out anti-sampling processing, obtains counter adopt
Sample data include:
Anti- sampling formula is determined according to the sample distribution algorithm；And
The anti-sampled data is obtained by the anti-sampling formula and the winning price.
10. method according to claim 8, which is characterized in that carry out market price analysis bag by the anti-sampled data
It includes:
Win valence forecast analysis is carried out by the anti-sampled data；And
Win valence distributional analysis is carried out by the anti-sampled data.
11. a kind of bidding data processing unit characterized by comprising
Request module, for obtaining bid request to be processed；
It bids module, for determining the numerical value of bidding of the bid request according to sample distribution algorithm；
Bid module, for being bid in commodity transaction platform by the numerical value of bidding.
12. device as claimed in claim 11, which is characterized in that further include:
Analysis module, for carrying out market price analysis by winning price.
13. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-10.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-10 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810713190.XA CN109003126A (en) | 2018-06-29 | 2018-06-29 | Bidding data processing method, device, electronic equipment and computer-readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810713190.XA CN109003126A (en) | 2018-06-29 | 2018-06-29 | Bidding data processing method, device, electronic equipment and computer-readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109003126A true CN109003126A (en) | 2018-12-14 |
Family
ID=64598740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810713190.XA Pending CN109003126A (en) | 2018-06-29 | 2018-06-29 | Bidding data processing method, device, electronic equipment and computer-readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109003126A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734504A (en) * | 2021-04-02 | 2021-04-30 | 北京智慧易科技有限公司 | Intelligent traffic routing method, device and system |
-
2018
- 2018-06-29 CN CN201810713190.XA patent/CN109003126A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734504A (en) * | 2021-04-02 | 2021-04-30 | 北京智慧易科技有限公司 | Intelligent traffic routing method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100792697B1 (en) | Method and system for decideing advertising fee | |
| US8504465B2 (en) | Fuel offering and purchase management system | |
| US8498925B2 (en) | Public offering risk management | |
| US20140025550A1 (en) | Systems and methods for sharing excess profits | |
| JP2009512094A (en) | Products and methods for managing life insurance products | |
| CN101438309A (en) | Distributed architecture for online advertising | |
| KR102020006B1 (en) | Electronic commerce system and method for writing authority of review | |
| US20120290403A1 (en) | Network-advertising, options program (advestor) | |
| KR20180011680A (en) | Investment advice offer method and investment advice offer server | |
| US20110246289A1 (en) | Click marketplace system and method with enhanced click traffic auctions | |
| US7827081B2 (en) | Computer method and system for equity financing by retail investors with collective due diligence funding | |
| CN109003126A (en) | Bidding data processing method, device, electronic equipment and computer-readable medium | |
| WO2000034841A2 (en) | Customer profit sharing conditional purchase offer (cpo) management system | |
| KR102194776B1 (en) | System for determining sales price of Point determining sales price using Artifical Intellegence | |
| US20140108215A1 (en) | System and methods for trading | |
| WO2001033447A1 (en) | Auction fee processing method using computer network system | |
| EP1213688A2 (en) | A system and method for selling contingent information | |
| US20180247372A1 (en) | Method and system for structured settlement auctions and trading and exchange | |
| KR20140133977A (en) | Integrated management system for global marketing and method thereof | |
| KR102485489B1 (en) | Method, device and system for providing a service platform for prepaid long-term products | |
| KR101059597B1 (en) | Method and system for decideing advertising fee | |
| KR20050082392A (en) | Buy-information buying and selling to marketing system | |
| KR20180011682A (en) | Investment advice offer method and investment advice offer server | |
| WO2020213798A1 (en) | System for providing expandable advertisement service by using link exposure | |
| KR20230000437A (en) | System and method for providing trading and corporation informaion on over-the-counter stocks |
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 |