CN108960901A - Data processing method, device, medium and electronic equipment - Google Patents
Data processing method, device, medium and electronic equipment Download PDFInfo
- Publication number
- CN108960901A CN108960901A CN201810608231.9A CN201810608231A CN108960901A CN 108960901 A CN108960901 A CN 108960901A CN 201810608231 A CN201810608231 A CN 201810608231A CN 108960901 A CN108960901 A CN 108960901A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- candidate set
- launched
- clicking rate
- data processing
- 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
- G06Q30/0242—Determining effectiveness of advertisements
-
- 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
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
Abstract
The embodiment provides a kind of data processing method, device, medium and electronic equipments.This method comprises: clicking rate is estimated in each advertisement in estimating ad Candidate Set；It is launched based on estimating clicking rate and choosing advertisement from advertisement Candidate Set；Judge whether the exposure frequency for the advertisement being launched reaches predetermined threshold；When determining to reach predetermined threshold, the advertisement that exposure frequency reaches predetermined threshold is removed from advertisement Candidate Set, wherein advertisement Candidate Set is the set for the advertisement that exposure frequency is not up to predetermined threshold.The technical solution of the embodiment of the present invention can guarantee the fairness of spending on ads while improving ad click rate, so as to improve advertisement delivery effect.
Description
Technical field
The embodiment of the present invention is related to big data field, more specifically, the embodiment of the present invention be related to data processing method,
Data processing equipment, computer readable storage medium and electronic equipment.
Background technique
This part intends to provides background or context for the embodiment of the present invention stated in claims.Retouching herein
It states and recognizes it is the prior art not because not being included in this section.
With the development of internet technology, marketing activity on line is carried out in more and more enterprise's selections on the internet, such as
What is that Above-the-line dispensing advertisement becomes focus of attention.
In current technology scheme, in order to guarantee to launch the fairness of advertisement, by being launched at random to each Above-the-line
Advertisement distributes ad traffic.
Summary of the invention
But although this technical solution is more fair to each advertiser, the clicking rate for the advertisement launched is only capable of
It catches up with the average, the dispensing effect of advertisement is poor.
Therefore in the prior art, it is difficult to reach satisfactory advertisement delivery effect.
Thus, it is also very desirable to which a kind of improved data processing method enables to guaranteeing the same of advertisement dispensing justice
The clicking rate of Shi Tigao dispensing advertisement.
In the present context, the embodiment of the present invention is intended to provide a kind of data processing method, data processing equipment, calculating
Machine readable storage medium storing program for executing and electronic equipment.
In the first aspect of the embodiment of the present invention, a kind of data processing method is provided, comprising: estimating ad Candidate Set
In each advertisement estimate clicking rate；Based on it is described estimate clicking rate and choose advertisement from the advertisement Candidate Set launched；
Judge whether the exposure frequency for the advertisement being launched reaches predetermined threshold；When determining to reach the predetermined threshold, from described wide
Accuse removal exposure frequency in Candidate Set and reach the advertisement of the predetermined threshold, wherein the advertisement Candidate Set be exposure frequency not
Reach the set of the advertisement of the predetermined threshold.
In some embodiments of the invention, aforementioned schemes are based on, based on the clicking rate of estimating from the advertisement candidate
Selection advertisement is concentrated to be launched, comprising: to launch data based on history of advertising and calculate each advertisement in the advertisement Candidate Set
Average click-through rate；Calculate the difference for estimating clicking rate Yu the average click-through rate of each advertisement；Based on the difference pair
Each advertisement carries out descending arrangement, and the result based on descending arrangement is chosen advertisement from the advertisement Candidate Set and launched.
In some embodiments of the invention, aforementioned schemes are based on, the result based on descending arrangement is candidate from the advertisement
Concentrate choose advertisement launched, comprising: based on descending arrangement result chosen from the advertisement Candidate Set described in estimate a little
The maximum advertisement of difference for hitting rate and the average click-through rate is launched.
In some embodiments of the invention, aforementioned schemes are based on, based on the clicking rate of estimating from the advertisement candidate
Selection advertisement is concentrated to be launched, comprising: to estimate the maximum advertisement of clicking rate described in choosing from the advertisement Candidate Set and carry out
It launches.
In some embodiments of the invention, aforementioned schemes are based on, each advertisement estimates a little in estimating ad Candidate Set
Hit rate, comprising: from the feature for extracting each advertisement in advertisement Candidate Set in user information, advertising information and contextual information；
Feature based on extracted each advertisement is trained clicking rate prediction model；It is estimated based on the clicking rate after training
Each advertisement estimates clicking rate in model estimating ad Candidate Set.
In some embodiments of the invention, aforementioned schemes are based on, the clicking rate prediction model is Logic Regression Models.
In some embodiments of the invention, aforementioned schemes, the data processing method further include: from the advertisement are based on
After selection advertisement is launched in Candidate Set, the exposure frequency for the advertisement being launched is updated.
In some embodiments of the invention, aforementioned schemes are based on, advertisement is chosen from the advertisement Candidate Set and is thrown
It puts, comprising: choose advertisement from the advertisement Candidate Set using predetermined impressions as the period and launched；In the end cycle
When, the exposure frequency of each advertisement is reset.
In some embodiments of the invention, aforementioned schemes, the data processing method are based on further include: based on all wide
The predetermined threshold is arranged in the total quantity of announcement and the predetermined impressions.
In the second aspect of the embodiment of the present invention, a kind of data processing equipment is provided, comprising: clicking rate estimates list
Member estimates clicking rate for each advertisement in estimating ad Candidate Set；Unit is launched in advertisement, for estimating click based on described
Rate is chosen advertisement from the advertisement Candidate Set and is launched；Judging unit, the exposure frequency of the advertisement for judging to be launched
Whether predetermined threshold is reached；Advertisement removal unit, for determine reach the predetermined threshold when, from the advertisement Candidate Set
Removal exposure frequency reaches the advertisement of the predetermined threshold, wherein the advertisement Candidate Set is not up to described pre- for exposure frequency
Determine the set of the advertisement of threshold value.
In the third aspect of the embodiment of the present invention, a kind of computer readable storage medium is provided, is stored thereon with meter
Calculation machine program realizes the data processing method as described in above-mentioned first aspect when the computer program is executed by processor.
In the fourth aspect of the embodiment of the present invention, a kind of electronic equipment is provided, comprising: processor；And memory,
It is stored with computer-readable instruction on the memory, is realized when the computer-readable instruction is executed by the processor as above
State data processing method described in first aspect.
Technical solution according to an embodiment of the present invention, on the one hand, click is estimated based on each advertisement in advertisement Candidate Set
Rate is chosen advertisement and is launched, and can select to estimate the higher advertisement of clicking rate and be launched, so as to improve dispensing advertisement
Clicking rate；On the other hand, it is wide that this is removed from advertisement Candidate Set when the exposure frequency for being launched advertisement reaches predetermined threshold
It accuses, can guarantee the fairness of spending on ads, while improving ad click rate so as to improve advertisement delivery effect.
Detailed description of the invention
The following detailed description is read with reference to the accompanying drawings, the above-mentioned and other purposes of exemplary embodiment of the present,
Feature and advantage will become prone to understand.In the accompanying drawings, it shows by way of example rather than limitation of the invention several
Embodiment, in which:
Fig. 1 diagrammatically illustrates the schematic block diagram of exemplary application scene according to some embodiments of the present invention；
Fig. 2 schematically shows the flow diagrams of data processing method according to some embodiments of the present invention；
Fig. 3 schematically shows estimating for each advertisement in estimating ad Candidate Set according to some embodiments of the present invention
The flow diagram of clicking rate；
Fig. 4 schematically shows according to some embodiments of the present invention based on estimating clicking rate from advertisement Candidate Set
Choose the flow diagram that advertisement is launched；
Fig. 5 schematically shows the schematic block diagram of data processing equipment according to some embodiments of the present invention；
Fig. 6 schematically shows the schematic diagram of storage medium according to example embodiment of the present invention；And
Fig. 7 schematically shows the block diagram of the electronic equipment of the example embodiment according to invention.
In the accompanying drawings, identical or corresponding label indicates identical or corresponding part.
Specific embodiment
The principle and spirit of the invention are described below with reference to several exemplary embodiments.It should be appreciated that providing these
Embodiment is used for the purpose of making those skilled in the art can better understand that realizing the present invention in turn, and be not in any way
It limits the scope of the invention.On the contrary, thesing embodiments are provided so that the disclosure is more thorough and complete, and can be by this
Scope of disclosure is completely communicated to those skilled in the art.
One skilled in the art will appreciate that the embodiment of the present invention can be implemented as a kind of system, device, equipment, method or
Computer program product.Therefore, the present disclosure may be embodied in the following forms, it may be assumed that complete hardware, complete software (packet
Include firmware, resident software, microcode etc.) or hardware and software combine form.
It is set according to an embodiment of the invention, proposing a kind of data processing method, data processing equipment, medium and electronics
It is standby.
Herein, it is to be understood that related term advertisement candidate set representations exposure frequency is not up to described pre-
Determine the set of the advertisement of threshold value.It is clear to guest that the exposure frequency of advertisement indicates that an advertisement such as image file is successfully downloaded
The number look in device.In addition, any number of elements in attached drawing is used to example rather than limitation and any name are only used for
It distinguishes, without any restrictions meaning.
Below with reference to several representative embodiments of the invention, the principle and spirit of the present invention are explained in detail.
Summary of the invention
The inventors discovered that, in order to guarantee the fairness of advertisement dispensing, being launched extensively using random in a kind of technical solution
The mode of announcement carries out advertisement dispensing；In another technical solution, in order to improve the clicking rate of advertisement, mould is estimated by clicking rate
Type estimates the clicking rate of advertisement to be put, and selection is estimated the biggish advertisement of clicking rate and launched.However, at the first
In technical solution, although ensure that the fairness that advertisement is launched, the clicking rate for being launched advertisement is lower, is only capable of reaching average
It is horizontal；In second of technical solution, although improving the clicking rate for being launched advertisement, it can be difficult to guaranteeing the public affairs that advertisement is launched
Levelling.
Based on above content, basic thought of the invention is, is estimated by each advertisement in estimating ad Candidate Set
Clicking rate is chosen advertisement and is launched, when the exposure frequency for being launched advertisement reaches predetermined threshold, from advertisement Candidate Set
Except the advertisement.Guarantee the fairness that advertisement is launched by setting the predetermined threshold of exposure frequency, estimates clicking rate by choosing
Higher advertisement is launched to improve the clicking rate of advertisement, is guaranteed extensively while improving ad click rate so as to realize
Accuse the fairness of injected volume.
After introduced the basic principles of the present invention, lower mask body introduces various non-limiting embodiments of the invention.
Application scenarios overview
The schematic block of exemplary application scene according to some embodiments of the present invention is shown referring initially to Fig. 1, Fig. 1
Figure.As shown in Figure 1, the advertisement delivery system may include: advertising database 110, clicking rate estimates module 120 and advertisement is thrown
Amplification module 130.Wherein, be stored with a plurality of advertising information in advertising database 110, clicking rate estimate module 120 for according to
Each advertisement in family information, advertising information, ad spot information and contextual information estimating ad database 110 is estimated a little
Rate is hit, each advertisement of the advertisement putting module 130 for estimating the estimation of module 120 according to clicking rate estimates clicking rate from advertisement
Database 110 obtains advertisement and is launched.
It should be understood that application scenarios shown in FIG. 1 are only that the embodiment of the present invention can be wherein achieved
One example.The scope of application of the embodiment of the present invention is not limited by any aspect of the application scenarios.
Illustrative methods
Below with reference to the application scenarios of Fig. 1, it is described with reference to Figure 2 data processing side according to an exemplary embodiment of the present invention
Method.It should be noted which is shown only for the purpose of facilitating an understanding of the spirit and principles of the present invention for above-mentioned application scenarios, it is of the invention
Embodiment is unrestricted in this regard.On the contrary, the embodiment of the present invention can be applied to applicable any scene.
Referring to shown in Fig. 2, in step S210, each advertisement estimates clicking rate in estimating ad Candidate Set.
In the exemplary embodiment, advertisement Candidate Set is the set for the advertisement that exposure frequency is not up to predetermined threshold.Initial
State, advertisement Candidate Set are the set of all advertisements.The predetermined threshold can be set according to the total quantity of all advertisements.
It, can be by clicking rate prediction model estimating ad Candidate Set when receiving the exposure request of client transmission
Clicking rate is estimated in each advertisement.Clicking rate prediction model can be Logic Regression Models, or FM
(Factorization Machine, disassembler) model can also be other models appropriate such as (Field-aware
Factorization Machine, field perceptual decomposition machine) model, present invention comparison is without particular determination.
In step S220, based on it is described estimate clicking rate and choose advertisement from the advertisement Candidate Set launched.
In the exemplary embodiment, the clicking rate of estimating based on each advertisement in advertisement Candidate Set is selected from advertisement Candidate Set
Advertisement is taken to be launched.Launch for example, can choose from advertisement Candidate Set and to estimate the maximum advertisement of clicking rate.This
Outside, descending arrangement can also be carried out to each advertisement in advertisement Candidate Set based on the size for estimating clicking rate, is arranged based on descending
The advertisement that the result of column chooses ranking results former is launched.
Further, after selection advertisement is launched in advertisement Candidate Set, the exposure time for the advertisement being launched is updated
The exposure frequency for the advertisement that number will be launched adds 1.
In step S230, judge whether the exposure frequency for the advertisement being launched reaches predetermined threshold.
In the exemplary embodiment, the exposure frequency of the available advertisement being launched, judges the exposure of advertisement being launched
Whether number reaches greatly above-mentioned predetermined threshold.In some embodiments, advertisement can be launched as the period using predetermined impressions to wait
Advertisement in selected works, in such a case, it is possible to which this is arranged according to the total quantity of all advertisements and the predetermined impressions
Predetermined threshold.For example, being equipped with N number of advertisement, predetermined impressions are 1000 times, and when N is even number, which is 1000/
N；When N is odd number, which is 1000/N+1.
In step S240, when determining to reach the predetermined threshold, exposure frequency is removed from the advertisement Candidate Set
Reach the advertisement of the predetermined threshold.
In the exemplary embodiment, when determining that the exposure frequency for the advertisement being launched reaches above-mentioned predetermined threshold, from advertisement
The advertisement that exposure frequency reaches the predetermined threshold is removed in Candidate Set.It, will be every after the advertisement in advertisement Candidate Set has been launched
The exposure frequency of a advertisement is reset, and is started next round and is launched.
The technical solution of example embodiment according to fig. 2, on the one hand, click is estimated based on each advertisement in advertisement Candidate Set
Rate is chosen advertisement and is launched, and can select to estimate the higher advertisement of clicking rate and be launched, so as to improve dispensing advertisement
Clicking rate；On the other hand, it is wide that this is removed from advertisement Candidate Set when the exposure frequency for being launched advertisement reaches predetermined threshold
It accuses, can guarantee the fairness of spending on ads, while improving ad click rate so as to improve advertisement delivery effect.
Fig. 3 schematically shows estimating for each advertisement in estimating ad Candidate Set according to some embodiments of the present invention
The flow diagram of clicking rate.
Referring to shown in Fig. 3, in step s310, advertisement is extracted from user information, advertising information and contextual information
The feature of each advertisement in Candidate Set.
In the exemplary embodiment, user information may include: that userspersonal information such as Sex, Age user browses history
The information such as information, advertising information may include: the information such as advertisement type, ad content, ad material, ad spot information, up and down
Literary information may include: that the information such as scene, release time are launched in advertisement.
It can be from each advertisement in advertisement Candidate Set be extracted in user information, advertising information and contextual information respectively
User's category feature, advertisement category feature and context category feature.Further, can also to user's category feature of each advertisement,
It is combined between advertisement category feature and contextual feature, forms assemblage characteristic.
In step s 320, the feature based on extracted each advertisement is trained clicking rate prediction model.
It in the exemplary embodiment, can user's category feature based on each advertisement of extraction, advertisement category feature and up and down
Literary feature is trained clicking rate prediction model.Clicking rate prediction model can be Logic Regression Models, or other
Machine learning model appropriate such as GBDT (Gradient Boosting Decision Tree, gradient promote decision tree) mould
Type.
It can be by the user class feature vector, commercial paper feature vector and contextual feature vector of each advertisement of extraction
Clicking rate prediction model is input to be trained.It further, can also be by user's category feature of each advertisement of extraction, advertisement
The set of category feature and contextual feature is divided into training sample set and test sample collection, concentrates each advertisement based on training sample
Feature clicking rate prediction model is trained, based on verifying sample set in each advertisement feature to clicking rate prediction model
It is verified, based on the parameter of verification result adjustment clicking rate prediction model, so as to improve the accuracy of model prediction.
In step S330, based on each advertisement in the clicking rate prediction model estimating ad Candidate Set after training
Estimate clicking rate.
In the exemplary embodiment, after training clicking rate prediction model, estimated based on the clicking rate prediction model after training
Each advertisement estimates clicking rate in meter advertisement Candidate Set.The clicking rate of estimating for the advertisement estimated by clicking rate prediction model is got over
Height illustrates that the dispensing effect of the advertisement is better.Selection is estimated the higher advertisement of clicking rate and is launched, and can be improved advertisement dispensing
Effect.
Fig. 4 schematically shows according to some embodiments of the present invention based on estimating clicking rate from advertisement Candidate Set
Choose the flow diagram that advertisement is launched.
Referring to shown in Fig. 4, in step S410, launched based on history of advertising each in the data calculating advertisement Candidate Set
The average click-through rate of advertisement.
In the exemplary embodiment, available the past period such as 1 month history of advertising launches data, the history
Data can be launched for all or part of random history for launching advertisement by launching data.It may include wide that history of advertising, which launches data,
The impressions and number of clicks of announcement, impressions and number of clicks based on advertisement calculate the average click of each advertisement
Rate is equipped with N number of advertisement, then the average click-through rate of each advertisement can be expressed as (m1, m2..., mN)。
In the step s 420, the difference for estimating clicking rate Yu the average click-through rate of each advertisement is calculated.
In the exemplary embodiment, the clicking rate of estimating of each advertisement is estimated based on clicking rate prediction model, and is calculated each
The difference of clicking rate Yu above-mentioned average click-through rate is estimated in advertisement, for example, setting based on each wide of clicking rate prediction model estimation
The clicking rate of estimating accused is (pCTR1, pCTR2..., pCTRN), then the difference for estimating clicking rate and average click-through rate of each advertisement
Value is (pCTR1-m1, pCTR2-m2..., pCTRN-mN)。
In step S430, based on the difference to each advertisement carry out descending arrangement, based on descending arrangement result from
Advertisement is chosen in the advertisement Candidate Set to be launched.
In the exemplary embodiment, the difference for estimating clicking rate and average click-through rate based on above-mentioned each advertisement is to each wide
It accuses and carries out descending arrangement, the result based on descending arrangement is chosen advertisement from advertisement Candidate Set and launched.For example, can be based on
The result of descending arrangement is chosen from advertisement Candidate Set to be estimated the maximum advertisement of difference of clicking rate and average click-through rate and is thrown
It puts.In addition, estimating advertisement of the difference of clicking rate and average click-through rate greater than predetermined value in some embodiments, it is also possible to choose
It is launched, which can be set according to the number of ads launched every time.
Exemplary means
After describing the method for exemplary embodiment of the present, next, with reference to Fig. 5 to the exemplary implementation of the present invention
The data processing equipment of example.
In Fig. 5, data processing equipment 500 may include: that clicking rate estimates unit 510, unit 520 is launched in advertisement, is sentenced
Disconnected unit 530 and advertisement removal unit 540.Wherein: clicking rate estimates unit 510 for each wide in estimating ad Candidate Set
That accuses estimates clicking rate；Advertisement is launched unit 520 and is chosen from the advertisement Candidate Set extensively for estimating clicking rate based on described in
Announcement is launched；Whether the exposure frequency for the advertisement that judging unit 530 is used to judge to be launched reaches predetermined threshold；Advertisement removal
Unit 540 is used for when determining to reach the predetermined threshold, and exposure frequency is removed from the advertisement Candidate Set and reaches described pre-
Determine the advertisement of threshold value, wherein the advertisement Candidate Set is the set for the advertisement that exposure frequency is not up to the predetermined threshold.
In some embodiments of the invention, aforementioned schemes are based on, it includes: average click-through rate meter that unit 520 is launched in advertisement
Unit is calculated, for launching the average click-through rate that data calculate each advertisement in the advertisement Candidate Set based on history of advertising；Difference
Computing unit, for calculating the difference for estimating clicking rate Yu the average click-through rate described in each advertisement；Processing unit is launched,
For carrying out descending arrangement to each advertisement based on the difference, the result based on descending arrangement is selected from the advertisement Candidate Set
Advertisement is taken to be launched.
In some embodiments of the invention, aforementioned schemes are based on, processing unit is launched and is configured to: being arranged based on descending
Result chosen from the advertisement Candidate Set described in estimate the maximum advertisement of difference of clicking rate and the average click-through rate into
Row is launched.
In some embodiments of the invention, aforementioned schemes are based on, advertisement is launched unit 520 and is configured as: from described wide
The maximum advertisement of clicking rate is estimated described in choosing in announcement Candidate Set to be launched.
In some embodiments of the invention, aforementioned schemes are based on, it includes: feature extraction list that clicking rate, which estimates unit 510,
Member, for from user information, advertising information and contextual information extract advertisement Candidate Set in each advertisement feature；Training
Unit is trained clicking rate prediction model for the feature based on extracted each advertisement；Estimation unit, for being based on
Each advertisement estimates clicking rate in the clicking rate prediction model estimating ad Candidate Set after training.
In some embodiments of the invention, aforementioned schemes are based on, the clicking rate prediction model is Logic Regression Models.
In some embodiments of the invention, aforementioned schemes, the data processing equipment 500 are based on further include: update single
Member, for updating the exposure frequency for the advertisement being launched after selection advertisement is launched in the advertisement Candidate Set.
In some embodiments of the invention, aforementioned schemes are based on, advertisement is launched unit 520 and is configured as: are thrown with predetermined
Putting number is to choose advertisement from the advertisement Candidate Set in the period to be launched；In the end cycle, by each advertisement
The exposure frequency is reset.
In some embodiments of the invention, aforementioned schemes, the data processing equipment are based on further include: threshold value setting is single
Member, for total quantity and the predetermined impressions setting predetermined threshold based on all advertisements.
Exemplary media
After describing the device of exemplary embodiment of the present, next, being deposited to exemplary embodiment of the present
Storage media is illustrated.
In some embodiments, various aspects of the invention are also implemented as a kind of medium, are stored thereon with program generation
Code is retouched in above-mentioned " illustrative methods " part when said program code is executed by the processor of equipment for realizing this specification
Step in the data processing method for the exemplary embodiments various according to the present invention stated.
For example, step S210 as shown in Figure 2 may be implemented when executing said program code in the processor of the equipment,
Each advertisement estimates clicking rate in estimating ad Candidate Set；Step S220 is estimated clicking rate and is waited from the advertisement based on described
Advertisement is chosen in selected works to be launched；Step S230, judges whether the exposure frequency for the advertisement being launched reaches predetermined threshold；Step
Rapid S240 removes exposure frequency from the advertisement Candidate Set and reaches the predetermined threshold when determining to reach the predetermined threshold
The advertisement of value, wherein the advertisement Candidate Set is the set for the advertisement that exposure frequency is not up to the predetermined threshold.
Refering to what is shown in Fig. 6, describing the program for realizing above-mentioned data processing method of embodiment according to the present invention
Product 600, can be using portable compact disc read only memory (CD-ROM) and including program code, and can set in terminal
It is standby, such as run on PC.However, program product of the invention is without being limited thereto.
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.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
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, partially executing on a remote computing or completely long-range
It calculates and is executed on equipment or server.In the situation for being related to remote computing device, remote computing device can be by any number of
The network of class, including local area network (LAN) or wide area network (WAN), are connected to user calculating equipment.
Exemplary computer device
Data processing method, data processing equipment and the storage medium for describing exemplary embodiment of the present it
Afterwards, next, introducing the electronic equipment of an exemplary embodiment of the present invention.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, completely
Software implementation (including firmware, microcode etc.) or hardware and software in terms of combine embodiment, may be collectively referred to as here
Circuit, " module " or " system ".
In some possible embodiments, it is single that electronic equipment according to the present invention can include at least at least one processing
Member and at least one storage unit.Wherein, the storage unit is stored with program code, when said program code is described
When processing unit executes, so that the processing unit executes described in above-mentioned " illustrative methods " part of this specification according to this
Invent the step in the data processing method of various exemplary embodiments.For example, the processing unit can be executed such as institute in Fig. 2
The step S210 shown, each advertisement estimates clicking rate in estimating ad Candidate Set；Step S220 estimates clicking rate based on described
Advertisement is chosen from the advertisement Candidate Set to be launched；Step S230, judges whether the exposure frequency for the advertisement being launched reaches
To predetermined threshold；Step S240 removes exposure frequency from the advertisement Candidate Set and reaches when determining to reach the predetermined threshold
To the advertisement of the predetermined threshold, wherein the advertisement Candidate Set is the advertisement that exposure frequency is not up to the predetermined threshold
Set.
Electronic equipment 700 according to example embodiment of the present invention is described referring to Fig. 7.Electronics shown in Fig. 7 is set
Standby 700 be only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 7, electronic equipment 700 is showed in the form of universal computing device.The component of electronic equipment 700 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 701, at least one above-mentioned storage unit 702, the different system components of connection
The bus 703 of (including storage unit 702 and processing unit 701), display unit 707.
Bus 703 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.
Storage unit 702 may include the readable medium of form of volatile memory, such as random access memory (RAM)
7021 and/or cache memory 7022, it can further include read-only memory (ROM) 7023.
Storage unit 702 can also include program/utility with one group of (at least one) program module 7024
7025, such program module 7024 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Electronic equipment 700 can also be with one or more external equipments 704 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with electronic equipment 700 communicate, and/or with make electricity
Any equipment (such as router, modem etc. that sub- equipment 700 can be communicated with one or more of the other calculating equipment
Deng) communication.This communication can be carried out by input/output (I/O) interface 705.Also, electronic equipment 700 can also pass through
Network adapter 706 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as
Internet) communication.As shown, network adapter 706 is communicated by bus 703 with other modules of electronic equipment 700.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 700, 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..
It should be noted that although being referred to several units/modules or son list of data processing equipment in the above detailed description
Member/module, but it is this division be only exemplary it is not enforceable.In fact, according to an embodiment of the invention, above
The feature and function of two or more units/modules of description can embody in a units/modules.Conversely, retouching above
The feature and function for the units/modules stated can be to be embodied by multiple units/modules with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
Although by reference to several spirit and principle that specific examples describe the present invention, it should be appreciated that, this hair
It is bright to be not limited to disclosed specific embodiment, the feature in these aspects, which cannot combine, not to be meant that yet to the division of various aspects
It is benefited to carry out, it is this to divide the convenience merely to statement.The present invention is directed to cover spirit and scope of the appended claims
Interior included various modifications and equivalent arrangements.
Claims (10)
1. a kind of data processing method, comprising:
Each advertisement estimates clicking rate in estimating ad Candidate Set；
Based on it is described estimate clicking rate and choose advertisement from the advertisement Candidate Set launched；
Judge whether the exposure frequency for the advertisement being launched reaches predetermined threshold；
When determining to reach the predetermined threshold, exposure frequency is removed from the advertisement Candidate Set and reaches the predetermined threshold
Advertisement,
Wherein, the advertisement Candidate Set is the set for the advertisement that exposure frequency is not up to the predetermined threshold.
2. data processing method according to claim 1, estimates clicking rate based on described from the advertisement Candidate Set and select
Advertisement is taken to be launched, comprising:
The average click-through rate that data calculate each advertisement in the advertisement Candidate Set is launched based on history of advertising；
Calculate the difference for estimating clicking rate Yu the average click-through rate of each advertisement；
Descending arrangement is carried out to each advertisement based on the difference, the result based on descending arrangement is selected from the advertisement Candidate Set
Advertisement is taken to be launched.
3. data processing method according to claim 2, the result based on descending arrangement is selected from the advertisement Candidate Set
Advertisement is taken to be launched, comprising:
Result based on descending arrangement estimates clicking rate and the average click-through rate described in choosing from the advertisement Candidate Set
The maximum advertisement of difference is launched.
4. data processing method according to claim 1, estimates clicking rate based on described from the advertisement Candidate Set and select
Advertisement is taken to be launched, comprising:
The maximum advertisement of clicking rate is estimated described in choosing from the advertisement Candidate Set to be launched.
5. data processing method according to claim 1, each advertisement estimates clicking rate, packet in estimating ad Candidate Set
It includes:
From the feature for extracting each advertisement in advertisement Candidate Set in user information, advertising information and contextual information；
Feature based on extracted each advertisement is trained clicking rate prediction model；
Clicking rate is estimated based on each advertisement in the clicking rate prediction model estimating ad Candidate Set after training.
6. data processing method according to claim 5, the clicking rate prediction model is Logic Regression Models.
7. data processing method according to claim 1, the data processing method further include:
After selection advertisement is launched in the advertisement Candidate Set, the exposure frequency for the advertisement being launched is updated.
8. data processing method according to any one of claim 1 to 7, chosen from the advertisement Candidate Set advertisement into
Row is launched, comprising:
Advertisement is chosen from the advertisement Candidate Set using predetermined impressions as the period to be launched；
In the end cycle, the exposure frequency of each advertisement is reset.
9. data processing method according to claim 8, the data processing method further include:
The predetermined threshold is arranged in total quantity and the predetermined impressions based on all advertisements.
10. a kind of data processing equipment, comprising:
Clicking rate estimates unit, estimates clicking rate for each advertisement in estimating ad Candidate Set；
Unit is launched in advertisement, for based on it is described estimate clicking rate and choose advertisement from the advertisement Candidate Set launched；
Judging unit, for judging whether the exposure frequency for the advertisement being launched reaches predetermined threshold；
Advertisement removal unit, for removing exposure frequency from the advertisement Candidate Set when determining to reach the predetermined threshold
Reach the advertisement of the predetermined threshold, wherein the advertisement Candidate Set is the advertisement that exposure frequency is not up to the predetermined threshold
Set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810608231.9A CN108960901A (en) | 2018-06-13 | 2018-06-13 | Data processing method, device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810608231.9A CN108960901A (en) | 2018-06-13 | 2018-06-13 | Data processing method, device, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960901A true CN108960901A (en) | 2018-12-07 |
Family
ID=64488488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810608231.9A Pending CN108960901A (en) | 2018-06-13 | 2018-06-13 | Data processing method, device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960901A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109936860A (en) * | 2019-04-24 | 2019-06-25 | 腾讯科技（深圳）有限公司 | Network information flow volume distribution method, assignment of traffic model training method and device |
| CN110473000A (en) * | 2019-07-17 | 2019-11-19 | 深圳市元征科技股份有限公司 | A kind of information recommendation method, server and storage medium |
| CN110532465A (en) * | 2019-08-16 | 2019-12-03 | 北京齐尔布莱特科技有限公司 | A kind of recommended method and recommender system of web site contents |
| CN110543598A (en) * | 2019-09-06 | 2019-12-06 | 腾讯科技（深圳）有限公司 | information recommendation method and device and terminal |
| CN112036929A (en) * | 2020-07-31 | 2020-12-04 | 深圳市彬讯科技有限公司 | Advertisement putting method, device, equipment and storage medium applied to special field |
| CN112884529A (en) * | 2021-03-24 | 2021-06-01 | 杭州网易云音乐科技有限公司 | Advertisement bidding method, device, equipment and medium |
| CN113822688A (en) * | 2020-06-23 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Advertisement conversion rate estimation method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110258039A1 (en) * | 2010-04-14 | 2011-10-20 | Microsoft Corporation | Evaluating preferences of users engaging with advertisements |
| EP2838063A1 (en) * | 2013-08-16 | 2015-02-18 | Samsung Electronics Co., Ltd | Device and method for calculating advertising expense in multi-screen service system |
| CN104574124A (en) * | 2013-10-10 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method and device for determining exhibition effect of advertisement data |
| CN104636940A (en) * | 2013-11-07 | 2015-05-20 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method, advertisement delivery system, advertisement screening method, advertisement screening device, and server |
-
2018
- 2018-06-13 CN CN201810608231.9A patent/CN108960901A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110258039A1 (en) * | 2010-04-14 | 2011-10-20 | Microsoft Corporation | Evaluating preferences of users engaging with advertisements |
| EP2838063A1 (en) * | 2013-08-16 | 2015-02-18 | Samsung Electronics Co., Ltd | Device and method for calculating advertising expense in multi-screen service system |
| CN104574124A (en) * | 2013-10-10 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method and device for determining exhibition effect of advertisement data |
| CN104636940A (en) * | 2013-11-07 | 2015-05-20 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method, advertisement delivery system, advertisement screening method, advertisement screening device, and server |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109936860A (en) * | 2019-04-24 | 2019-06-25 | 腾讯科技（深圳）有限公司 | Network information flow volume distribution method, assignment of traffic model training method and device |
| CN110473000A (en) * | 2019-07-17 | 2019-11-19 | 深圳市元征科技股份有限公司 | A kind of information recommendation method, server and storage medium |
| CN110532465A (en) * | 2019-08-16 | 2019-12-03 | 北京齐尔布莱特科技有限公司 | A kind of recommended method and recommender system of web site contents |
| CN110543598A (en) * | 2019-09-06 | 2019-12-06 | 腾讯科技（深圳）有限公司 | information recommendation method and device and terminal |
| CN113822688A (en) * | 2020-06-23 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Advertisement conversion rate estimation method and device, storage medium and electronic equipment |
| CN112036929A (en) * | 2020-07-31 | 2020-12-04 | 深圳市彬讯科技有限公司 | Advertisement putting method, device, equipment and storage medium applied to special field |
| CN112036929B (en) * | 2020-07-31 | 2023-08-15 | 深圳市彬讯科技有限公司 | Advertisement putting method, device, equipment and storage medium applied to special field |
| CN112884529A (en) * | 2021-03-24 | 2021-06-01 | 杭州网易云音乐科技有限公司 | Advertisement bidding method, device, equipment and medium |
| CN112884529B (en) * | 2021-03-24 | 2024-04-26 | 杭州网易云音乐科技有限公司 | Advertisement bidding method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108960901A (en) | Data processing method, device, medium and electronic equipment | |
| CN108076154B (en) | Application information recommendation method and device, storage medium and server | |
| CN109615411A (en) | Advertisement placement method and device, electronic equipment based on algorithm model | |
| CN108108821A (en) | Model training method and device | |
| CN105630977B (en) | Application program recommended method, apparatus and system | |
| US20210019375A1 (en) | Computing system including virtual agent bot providing semantic topic model-based response | |
| CN110008973B (en) | Model training method, method and device for determining target user based on model | |
| CN111506801A (en) | Sequencing method and device for sub-applications in application App | |
| WO2016044618A1 (en) | Method and apparatus for predicting customer intentions | |
| JP2015526795A5 (en) | ||
| CN111144952A (en) | Advertisement recommendation method, device, server and storage medium based on user interests | |
| US20200160385A1 (en) | Delivering advertisements based on user sentiment and learned behavior | |
| CN111275205A (en) | Virtual sample generation method, terminal device and storage medium | |
| CN108959558A (en) | Information-pushing method, device, computer equipment and storage medium | |
| WO2020257991A1 (en) | User identification method and related product | |
| CN109460503B (en) | Answer input method, answer input device, storage medium and electronic equipment | |
| CN111782937A (en) | Information sorting method and device, electronic equipment and computer readable medium | |
| CN109885834A (en) | A kind of prediction technique and device of age of user gender | |
| CN107168610A (en) | Pop-up processing method and processing device, storage medium and electronic equipment | |
| CN110148071A (en) | A kind of scenic spot reminding method, device and terminal device | |
| CN117194772B (en) | Content pushing method and device based on user tag | |
| KR102119518B1 (en) | Method and system for recommending product based style space created using artificial intelligence | |
| WO2014108007A1 (en) | Method for interaction and, server and network platform therefor | |
| CN111368195B (en) | Model training method, device, equipment and storage medium | |
| CN116137004B (en) | Attribution method, attribution system and attribution computer for advertisement putting effect |
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 |