CN107657487A - A kind of advertisement placement method and device based on verification - Google Patents
A kind of advertisement placement method and device based on verification Download PDFInfo
- Publication number
- CN107657487A CN107657487A CN201710974897.1A CN201710974897A CN107657487A CN 107657487 A CN107657487 A CN 107657487A CN 201710974897 A CN201710974897 A CN 201710974897A CN 107657487 A CN107657487 A CN 107657487A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- information
- candidate locations
- targeted advertisements
- user
- 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
-
- 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
- G06Q30/0277—Online advertisement
Abstract
The disclosure discloses a kind of advertisement placement method and device based on verification, including：After targeted advertisements are launched, the advertised event reported is received；The advertisement identification information carried according to advertised event, calculate advertisement verification code；Advertisement verification code is compared with the advertisement check code in advertisement identification information；If advertisement verification code is consistent with advertisement check code, the advertisement obtained in advertisement identification information issues the time；Advertisement issued into the time to be compared with current time, if advertisement issues the time and the time interval of current time is less than preset value, advertised event is as the rates ground for launching targeted advertisements.The technical scheme that the disclosure provides, when using advertised event as rates ground, can improve the accuracy of charging, the advertised event because receiving forgery is avoided, causes charging and mistake of deducting fees, influences the dispensing of advertisement, due to without manually checking advertised event, also reduce further human cost.
Description
Technical field
This disclosure relates to Internet technical field, more particularly to a kind of advertisement placement method and device.
Background technology
Modern network technology is increasingly becoming the first media, with traditional four big communications media (newspaper, magazine, TV,
Broadcast) advertisement and enjoy the outdoor advertising shown appreciation for somebody to compare recently, the web advertisement has an advantageous advantage, for example, without when
Between, space limitation, the advertisement putting orientations such as time orientation, region orientation, channel orientation can be carried out, showing advertisement is various informative
Change, easily carry out advertising results statistical analysis, change ad content etc. in time can be needed according to client.The web advertisement is real
Apply an important part for Modern Marketing media strategy.
The mode that the web advertisement is launched at present, the advertisement putting for being responsible for receiving client by advertisement releasing server are asked,
Advertisement putting request according to receiving returns to suitable advertising message；And handle advertisement exposure event or click on event, note
Correlation log is recorded, and is exposed or clicks on charging according to advertisement putting type and deduct fees.
Because number of ads is more in advertisement base, advertisement exposure event or click between event and advertisement putting again there is
Time difference, so advertisement exposure event that client reports or the legitimacy for clicking on event can not be determined, what None- identified was forged
Advertisement exposure event clicks on event, and then carries out charging and deduct fees to there may be mistake according to advertisement exposure event or click event
Difference, causes charging and mistake of deducting fees, and influences the dispensing of advertisement.
The content of the invention
In order to solve the advertisement exposure event or click thing that are reported present in correlation technique due to client can not be determined
The legitimacy of part, and then carry out charging and deduct fees to there may be error according to advertisement exposure event or click event, cause charging
With mistake of deducting fees, the dispensing problem of advertisement is influenceed, present disclose provides a kind of advertisement placement method based on verification.
On the one hand, present disclose provides a kind of advertisement placement method based on verification, this method to include：
After targeted advertisements are launched, the advertised event reported is received；
The advertisement identification information carried according to the advertised event, calculate advertisement verification code；
The advertisement verification code is compared with the advertisement check code in the advertisement identification information；
If the advertisement verification code is consistent with the advertisement check code, the advertisement obtained in the advertisement identification information issues
Time；
The advertisement issued into the time to be compared with current time, if the advertisement issue time and current time when
Between interval be less than preset value, then rates ground of the advertised event as the dispensing targeted advertisements.
On the other hand, the disclosure additionally provides a kind of advertisement delivery device based on verification, and the device includes：
Advertised event receiving module, for after targeted advertisements are launched, receiving the advertised event reported；
Identifying code computing module, for the advertisement identification information carried according to the advertised event, calculate advertisement verification code；
Advertisement correction verification module, for the advertisement check code in the advertisement verification code and the advertisement identification information to be carried out
Compare；
Time-obtaining module, for when the advertisement verification code is consistent with the advertisement check code, obtaining the advertisement
Advertisement in identification information issues the time；
Time transfer receiver module, it is compared for the advertisement to be issued into the time with current time, if the advertisement issues
The time interval of time and current time is less than preset value, then the advertised event as launch the chargings of the targeted advertisements according to
According to.
The technical scheme provided by this disclosed embodiment can include the following benefits：
The technical scheme that the disclosure provides, receives the advertised event reported, is verified by comparative advertising identifying code and advertisement
The uniformity of code, verifies to the advertised event received, verifies the legitimacy and available time of advertised event, so that
During using advertised event as rates ground, the accuracy of charging can be improved, the advertised event because receiving forgery is avoided, causes
Charging and mistake of deducting fees, influence the dispensing of advertisement, due to without manually checking advertised event, also reduce further manpower into
This.
It should be appreciated that the general description and following detailed description of the above are only exemplary, this can not be limited
It is open.
Brief description of the drawings
Accompanying drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the present invention
Example, and in specification together for explaining principle of the invention.
Fig. 1 is the schematic diagram of the implementation environment according to involved by the disclosure；
Fig. 2 is a kind of block diagram of server according to an exemplary embodiment；
Fig. 3 is a kind of flow chart of advertisement placement method based on verification according to an exemplary embodiment；
Fig. 4 is a kind of based on verification according to another exemplary embodiment on the basis of Fig. 3 corresponds to embodiment
The flow chart of advertisement placement method；
Fig. 5 is a kind of based on verification according to further example embodiment on the basis of Fig. 3 corresponds to embodiment
The flow chart of advertisement placement method；
Fig. 6 is the flow chart that suitable targeted advertisements are selected on the basis of Fig. 4 corresponds to embodiment；
Fig. 7 is the details flow chart for the step 602 that Fig. 6 corresponds to embodiment；
Fig. 8 is the schematic flow sheet that ad click rate forecast model is established on the basis of Fig. 7 corresponds to embodiment；
Fig. 9 is the details flow chart for the step 603 that Fig. 6 corresponds to embodiment；
Figure 10 is a kind of block diagram of advertisement delivery device based on verification according to an exemplary embodiment；
Figure 11 is that one kind on the basis of Figure 10 corresponds to embodiment according to another exemplary embodiment is based on verification
Advertisement delivery device block diagram.
Figure 12 is the details block diagram for the identifying code computing module that Figure 10 corresponds to embodiment；
Figure 13 is that one kind on the basis of Figure 10 corresponds to embodiment according to further example embodiment is based on verification
Advertisement delivery device block diagram.
Embodiment
Here explanation will be performed to exemplary embodiment in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects being described in detail in claims, of the invention.
Fig. 1 is the schematic diagram of the implementation environment according to involved by the disclosure.The implementation environment includes：Server 110 and more
Individual mobile terminal 120.
Interrelational form between server 110 and multiple mobile terminals 120, including the network associate mode of hardware and/or
Agreement, and the data correlation mode come and gone therebetween.Server 110 possesses data-handling capacity, and server 110 can be adopted
The advertisement placement method based on verification provided with the disclosure, to 120 times sending advertisements of mobile terminal, and receives mobile terminal 120
The advertised event reported, the advertised event received is verified, verify the legitimacy and validity of advertised event, so that
During using advertised event as rates ground, the accuracy of charging can be improved, avoids charging and the throwing for erroneous effects advertisement of deducting fees
Put, due to without manually checking advertised event, also reduce further human cost.
Referring to Fig. 2, Fig. 2 is a kind of server architecture schematic diagram provided in an embodiment of the present invention.The server 200 can because with
Put or performance is different and produce bigger difference, one or more central processing units (central can be included
Processing units, CPU) 222 (for example, one or more processors) and memory 232, one or more
Store the storage medium 230 (such as one or more mass memory units) of application program 242 or data 244.Wherein, deposit
Reservoir 232 and storage medium 230 can be of short duration storage or persistently storage.Being stored in the program of storage medium 230 can include
One or more modules (diagram is not shown), each module can include operating the series of instructions in server 200.
Further, central processing unit 222 could be arranged to communicate with storage medium 230, perform storage medium on server 200
Series of instructions operation in 230.Server 200 can also include one or more power supplys 226, one or more
Wired or wireless network interface 250, one or more input/output interfaces 258, and/or, one or more operations
System 241, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..Following Fig. 3-
Described in embodiment illustrated in fig. 9 can be based on the server architecture shown in the Fig. 2 as the step performed by server.
One of ordinary skill in the art will appreciate that hardware can be passed through by realizing all or part of step of following embodiments
To complete, by program the hardware of correlation can also be instructed to complete, described program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only storage, disk or CD etc..
Fig. 3 is a kind of flow chart of advertisement placement method based on verification according to an exemplary embodiment.The base
In the scope of application and executive agent of the advertisement placement method of verification, for example, this method is used for the service of implementation environment shown in Fig. 1
Device 110.As shown in figure 3, the advertisement placement method, can be performed by server 110, may comprise steps of 310- steps
350
In the step 310, after targeted advertisements are launched, the advertised event reported is received；
Specifically, after targeted advertisements are launched, if advertisement exposure is clicked on to user or by user, server 11 receives
The advertised event that mobile terminal 120 reports, the advertised event are displaying event or click on event.The information that advertised event includes can
To have：Using ID (which application), advertisement position, event type (displaying/click), the unique ID of advertisement, IP address, equipment platform
(IOS/ANDROID), network type (4G/WIFI) etc..
Wherein, before step 310, as shown in figure 4, the advertisement placement method based on verification that the disclosure provides can be with
Comprise the following steps 401-404.
In step 401, message identification corresponding to the targeted advertisements is obtained.
Wherein, message identification includes advertiser's mark (advertiser ID), scheduled flag (plan ID), material group mark (element
Material group ID), material mark (material ID), price of deducting fees, advertisement issue timestamp and random number.Advertiser ID, plan ID, material
Group ID, material ID can obtain from database, and price of deducting fees can be calculated according to charging formula, and random number is that advertisement issues
Shi Suiji generations.
For example, charging rate is calculated in the following ways：Assuming that advertisement A, advertisement B, advertisement C, advertisement D according to
ECPM (thousand displaying incomes) sorts successively from high to low, then the price of deducting fees for launching advertisement B is：
If bid mode is CPC (click on every time bid), single click on deduct fees=
It is exactlyECPM=1000*CTR*CPC, wherein CTR are clicking rate predicted value.
If bid mode is CPM (every thousand displaying bid),Also
It is advertisement C eCPM divided by 1000.ECPM=CPM.
In step 402, are combined by coding and obtains the advertisement for described information mark and the random value itself stored
Check code；
Specifically, advertisement check code md5_val=
md5(user_id+plan_id+group_id+material_id+price+time+rand+salt)
Wherein, salt is the random value of itself storage, and user_id is advertiser ID, and plan_id is plan ID,
Group_id is material group ID, and material_id is material ID, price for price of deducting fees, time be advertisement issue at that time when
Between stab, rand is random number.Coding is combined to the random value of message identification and itself storage using MD5 algorithms, obtains md5
Informative abstract value (i.e. md5_val, advertisement check code).
In step 403, described information mark and the advertisement check code are combined to form the advertisement identification information；
Wherein, advertisement identification information can be advertisement ID, ad_id (advertisement ID)=
user_id+plan_id+group_id+material_id+price+time+rand+md5_val
Wherein, user_id is advertiser ID, and plan_id is plan ID, and group_id is material group ID, material_id
For material ID, price is valency of deducting fees, and time issues timestamp at that time for advertisement, and rand is random number, and md5_val is step
The 402 advertisement check codes being calculated.
For example, ad_id can be：
“2159_5042_9172_29327_1.02_1504622460_P83JCe47a929a”
Wherein, 2159 be user_id, and 5042 be plan_id, and 9172 be group_id, and 29327 be material_id,
1.02 be price, and 1504622460 be time, P83JC rand, e47a929a md5_val.
Md5_val=md5 (user_id+plan_id+group_id+material_id+price+time+rand+
salt)。
In step 404, the targeted advertisements are launched in the lump with the corresponding advertisement identification information.
It should be noted that each advertisement has unique ad ID, server 110, can be with advertisement one in lower sending advertisement
Sending advertisement ID is removed, advertisement ID can be also taken when mobile terminal 120 reports.
It is emphasized that the random value of itself storage is salt figure, do not issue, in presence server 110.
In step 320, the advertisement identification information carried according to the advertised event, advertisement verification code is calculated.
Wherein, step 320 specifically includes step 321 and step 322.
In step 321, the described information mark included in the advertisement identification information is obtained；
With reference to step 403, advertisement identification information is made up of message identification and advertisement check code.Message identification can include wide
Accuse main ID (user_id), plan ID (plan_id), material group ID (group_id), material ID (material_id), valency of deducting fees
Lattice (price), advertisement issue timestamp (time) and random number (rand).
In step 322, are combined by coding and obtains the advertisement for described information mark and the random value itself stored
Identifying code.
Specifically, the random value (salt) of message identification and itself storage is passed through into below equation
Md5_val=md5 (user_id+plan_id+group_id+material_id+price+time+rand+
Salt advertisement verification code (md5_val)) is calculated.
In a step 330, the advertisement verification code is compared with the advertisement check code in the advertisement identification information；
Specifically, in the advertisement verification code and advertised event that are calculated after advertised event is reported advertisement ID advertisement school
Code is tested to be compared.Each character of advertisement verification code is compared one by one with each character of advertisement check code, it is determined that extensively
It is whether consistent (identical) with advertisement check code to accuse identifying code.
In step 340, if the advertisement verification code is consistent with the advertisement check code, the advertisement identification information is obtained
In advertisement issue the time；
In step 350, the advertisement issued into the time to be compared with current time, if the advertisement issue the time with
The time interval of current time is less than preset value, then the advertised event is as the rates ground for launching the targeted advertisements.
Specifically, if it is identical with advertisement check code to obtain advertisement verification code after step 330 comparison, then it represents that what is reported is wide
Reporting events be it is legal report, otherwise it is assumed that being that invalid report discards, not as rates ground.After confirmation is legal report,
Obtain the advertisement entrained by advertisement ID and issue the time (time), advertisement issued into the time is compared with current time.It is if wide
Announcement issues the time and the time interval of current time is more than or equal to preset value (such as 2 hours), then it represents that the advertised event reported
It is expired, it can be discarded as invalid report, i.e., not be re-used as rates ground.It is opposite, if advertisement issue the time with
The time interval of current time is less than preset value, then it is assumed that the advertised event reported is validity event, and the advertised event reported is made
For the foundation of charging.
Further, after above-mentioned steps 350, as shown in figure 5, the advertisement putting side based on verification that the disclosure provides
The further comprising the steps of 501-503 of method.
In step 501, the advertised event of all rates grounds as the targeted advertisements is filtered out；
In step 502, the displaying number or number of clicks of the targeted advertisements are counted according to the selection result；
In step 503, corresponding advertising resource is deducted according to the displaying number or number of clicks of the targeted advertisements.
Specifically, can be verified using above-mentioned steps 310-350 to each advertised event of targeted advertisements, filter out
Can be as the advertised event of rates ground.Then data statistics is carried out to the advertised event as rates ground, counts mesh
Mark the displaying number or number of clicks of advertisement.If bid mode is CPM, deducted fees for displaying number, if bid mode
Then deducted fees for CPC for number of clicks.Mode of deducting fees is as follows：
According to the price of deducting fees (price) of this displaying/click, the points of deduction advertisement main account；
The agent belonging to advertiser is found, the cash, virtual gold, consumption of agent's account are deducted by system Set scale
Certificate；It is indivisible to be not counted the small change calculating according to 2 significant digits, detain less according to priority buckle up.Priority：Cash ＞ consumption vouchers ＞
Virtual gold.
Such as：100 yuan of consumption, ratio of withholing 1:1:1.Three kinds of remaining sums detain 33.33 yuan respectively, amount to 99.99 yuan, also have
0.01 yuan of few button.According to 0.01 yuan of priority buckle up cash account.
Wherein, the points of advertisement main account, consumption voucher and virtual gold can turn into virtual resource.Agent's account shows
Gold can be exchange resource.Advertising resource includes resource allocation and exchange resource.
Wherein, before step 503, the method that the disclosure provides also includes：The exchange resource is received, according to the friendship
Change resource and generate corresponding virtual resource.
Specifically, the remaining sum composition of agent's account can include cash, virtual gold, consumption voucher, only cash is agency
The exchange resource that business really provides, virtual gold and consumption voucher are all the virtual resources that system is returned and rewarded；Such as agent's account
600 yuan of family cash, virtual 300 yuan of gold, 100 yuan of consumption voucher, and agent only needs the RTB platforms to server 110 (competing in real time
Valency platform) 600 yuan of expense is paid, 300 yuan of virtual gold and 100 yuan of consumption vouchers can be produced.Cash, virtual gold, consumption voucher this
Three kinds of remaining sums also may be converted into corresponding virtual resource and transfer advertisement main account (such as consumption points).
The technical scheme that disclosure above-mentioned example embodiment provides, server receive the advertised event reported, pass through ratio
Compared with advertisement verification code and the uniformity of advertisement check code, the advertised event received is verified, verifies the conjunction of advertised event
Method and available time, so as to when using advertised event as rates ground, the accuracy of charging be improved, avoided because connecing
The advertised event of forgery is received, causes charging and mistake of deducting fees, influences the dispensing of advertisement, due to without manually checking advertisement thing
Part, it also reduce further human cost.
On the basis of above-mentioned example embodiment, before step 401 obtains message identification corresponding to targeted advertisements, this
The step of open embodiment also includes how to select suitable targeted advertisements, as shown in fig. 6, specifically may comprise steps of
601-604。
In step 601, advertisement putting request is received, triggering obtains the characteristic of advertisement information of every candidate locations；
Wherein, advertisement putting request includes user's characteristic information.It should be noted that every kind of advertisement has suitable people
Group, such as sanitary napkin advertisement are properly pushed to the women in menstrual period.First stage milk powder advertisement be adapted to be pushed to baby's monthly age 0~
The peppery mother of 6 months.Thus, it is (namely suitable that directional user's information corresponding to every bid advertisement can be stored in database in advance
The characteristics of with the user of push), directional user's information can include orientation identity, pregnant week, baby's monthly age, residing city, interest
Hobby etc..According to advertisement putting request carry user's characteristic information, can be filtered out from database directional user's information with
The bid advertisement of user's characteristic information matching is as candidate locations.And then the characteristic of advertisement information of candidate locations can be obtained.
Characteristic of advertisement information includes advertisement static nature information and advertisement dynamic feature information；Wherein, advertisement static nature
Information includes location advertising, the affiliated industry of advertisement and adline；Advertisement dynamic feature information includes advertisement in different user group
In historic click-through rate.Location advertising is advertisement position to be put (such as information flow the 3rd), can be asked from advertisement putting
Middle acquisition, the affiliated industry of advertisement, the historic click-through rate of adline and advertisement in different user group can be stored in number in advance
According in storehouse.
In step 602, according to the characteristic of advertisement information of every candidate locations and advertisement putting request instruction
User's characteristic information, calculate every candidate locations clicking rate predicted value；
Wherein, user's characteristic information includes user state information and user preference information.User state information includes user
Identity status information, mood states information, it is presently at least one of menstrual period session information；User preference information includes readding
Read at least one of preference, shopping preferences and Matrix.
Such as：User's characteristic information includes age of user, residing city, marital status (married, unmarried), user identity mould
Formula (note menstrual period, standby pregnant, pregnancy, peppery mother), user whether have baby's (be, be no), mood states information (it is sad, unhappy, one
As, it is happy or super happy), the residing stage in menstrual period (menstrual period, safe period, easy pregnancy period and post-ovulatory phase).In addition, user characteristics is believed
Breath can also include mobile terminal operating system (iso, android) used in user, hobby (shopping, parent-offspring dotey,
House property, investment, automobile, at home life, aesthetic nursing, education go abroad, travel, health of losing weight etc.).
Specifically, as shown in fig. 7, the clicking rate predicted value that step 602 calculates every candidate locations can include following step
Rapid 701-702.
In step 701, the user's characteristic information and the characteristic of advertisement information of every candidate locations are subjected to group one by one
Code is compiled in collaboration with, builds new feature vector corresponding to every candidate locations；
0,1 coding (OHE, One-Hot-Encoding can be for user's characteristic information and advertisement static nature information
One-hot coding), such as marital status feature has two values, it is unmarried and married, represented with a bivector, vector value 0
Or 1, it is assumed that first dimension represents unmarried, and second dimension represents married, because a user only has a state, then
It is 1 that its vector, which only has the value of a dimension, such as unmarried：[1,0], it is married：[0,1].
Advertisement static nature information for the user's characteristic information after OHE and after OHE do "AND" (while 1 to be just 1,
Otherwise it is 0) computing, a new vector can be obtained.
Advertisement dynamic feature information includes advertisement the historic click-through rate in different user group, that is, user and advertisement are handed over
The feedback clicking rate of fork, floating-point encoding mode can be used.Clicking rate be a floating number, it is necessary to by its discretization, that is, adopt
With wait frequency division method, floating number is mapped in segment, such as according to [0,0.001), [0.001,0.002), [0.002,
0.003), [0.003,1] is mapped to this 4 segments, corresponding 4 dimensional vectors, when the size of some clicking rate (floating number)
When in current interval section, the value of current dimension is 1, and remaining is 0.As current feedback clicking rate be 0.00243 when, after mapping
Obtained vector is [0,0,1,0].
By corresponding to the new vector sum advertisement dynamic feature information obtained after above-mentioned AND operation vector composition new feature to
Amount.
In a step 702, ad click rate new feature vector input corresponding to every candidate locations pre-established is pre-
Model is surveyed, obtains clicking rate predicted value corresponding to every candidate locations.
Wherein, ad click rate forecast model can be Logic Regression Models.Logistic regression (Logistic
Regression) model is the disaggregated model for predicting binary class result, is widely used in numerous areas, is applied to
Response variable is the situation of two classification (0 does not click on/1 click) variable, and its target is that the probability of one of two-value is taken to response variable
Modeling, rather than directly predict its value.Logic Regression Models can describe 0/1 probability problem well, therefore can be used for
Ad click rate forecast model.
So-called ad click rate forecast model is the data target for quantifying click event, and clicking rate forecast model is built
It is vertical to include different users, characteristic of advertisement information, and these characteristic informations are exactly the reason for causing ad click rate difference, to pass through
Existing information data trains Logic Regression Models parameter.New user characteristics and characteristic of advertisement input are had already passed through into instruction afterwards
Experienced Logic Regression Models, so as to export ad click rate.The characteristics of due to different user, is different, even same use
Family, in different times, residing condition, mood etc. are all different, thus prior art according only to the keyword that user searches for
User shows advertisement, can not accurately meet different user different times are to advertisement the needs of, so as to cause advertising resource
Waste.
Further, as shown in figure 8, the foundation of ad click rate forecast model may comprise steps of 901-904.
In step 801, from history advertisement putting daily record, every log recording of acquisition launches advertisement, launched
History corresponding to advertisement launches user, and the history launches click situation of the user to launched advertisement；
Specifically, history advertisement putting daily record can be obtained from the storage medium 230 of server 110.History advertisement is
Refer to the advertisement launched before judging user to the clicking rate of certain advertisement, be a relative concept.Additionally need explanation
, the information (such as ID i.e. Customs Assigned Number) of certain user, the information of certain advertisement are have recorded in every advertisement putting daily record (such as
Advertisement ID is advertisement numbering), and the action (such as ad-request, issue, show, clicking on) that advertisement is corresponding.Therefore, to launching
ETL (data warehouse technologys, for describing data from source terminal by extracting (extract), conversion are done in daily record
(transform) (load), is loaded to the process of destination), it can get and launch extensively from every advertisement putting daily record
Accuse ID, ID corresponding to advertisement ID, and the ID and correspond to the click situation that user corresponds to advertisement to advertisement ID.Its
In, after an advertising display, if two label values, displaying-click can be stamped by being clicked：1, show-do not click on：0.
In step 802, the history is obtained to launch historic user characteristic information corresponding to user and launch advertisement pair
The history characteristic of advertisement information answered；
Specifically, after advertisement ID and ID is got from daily record is launched, user can be got according to ID
Historic user characteristic information corresponding to ID, the history characteristic of advertisement information according to corresponding to advertisement ID can get advertisement ID.
Wherein, historic user characteristic information includes historic user status information and historic user preference information.Further,
Historic user status information is included in the identity status information, mood states information, residing menstrual period session information of historic user
It is at least one；Historic user preference information includes reading at least one of preference, shopping preferences and Matrix.
For example, the identity status information of historic user can include age of user, residing city, marital status (
Wedding, it is unmarried), user identity pattern (note menstrual period, standby pregnant, pregnancy, peppery mother), user whether have baby's (be, be no).Mood states are believed
Breath can be sad, unhappy, general, happy or super happy.The residing stage in menstrual period include the menstrual period, safe period, the easy pregnancy period and
Post-ovulatory phase.These information can be inputted after historic user logins 120 software APP of mobile terminal, then be uploaded to
Server 110 is stored.
History characteristic of advertisement information includes history advertisement dynamic feature information and history advertisement static nature information.It is optional
, the history advertisement static nature information includes：History location advertising, the affiliated industry of history advertisement and history adline；
The history advertisement dynamic feature information includes history advertisement the historic click-through rate in different user group.Wherein, history advertisement
Historic click-through rate in different user group (such as menstrual period customer group, 18 years old customer group) can record according to history advertisement putting
Calculate.
In step 803, the historic user characteristic information and history characteristic of advertisement information are combined coding, built
History feature vector；
Wherein, the method for building history feature vector is referred to the process of above-mentioned structure new feature vector.Pass through difference
OHE one-hot codings are carried out to historic user characteristic information and history advertisement static nature information, by the historic user feature after OHE
History advertisement static nature information after information and OHE does AND operation, obtains history assemblage characteristic vector；History advertisement is moved
State characteristic information carries out floating-point encoding and obtains history behavioral characteristics vector；By history assemblage characteristic vector and history behavioral characteristics
Vector composition history feature vector.
In step 804, user is launched to the click situation of launched advertisement and history spy according to the history
Sign vector, trains Logic Regression Models, obtains ad click rate forecast model.
Wherein, the expression-form of Logic Regression Models is formula：
A represents characteristic of advertisement, and u represents user characteristics, and c represents other features (such as temporal characteristics, contextual feature etc.).
X is characterized vector, that is, the history feature vector that a, u, c feature are formed.Y=1 represents that click, y=0 represent not click on.W is
Coefficient vector, that is, need the parameter solved, wTRepresent transposition.By corresponding to all history feature vector sums constructed
(it is 1 to click on to label value, does not click on 0) to be used as training set to train above-mentioned Logic Regression Models, passes through Maximum Likelihood Estimation Method, ladder
(these methods belong to prior art and will not be repeated here) such as decline, stochastic gradient descent, quasi-Newton methods is spent it is estimated that mould
Shape parameter w, bring obtained parameter w into above formulas and can be obtained by ad click rate forecast model.
In step 603, the displaying according to corresponding to the clicking rate predicted value of every candidate locations and each candidate locations
Resource, calculate the displaying probability of every candidate locations；
Wherein, showing resource can be bid of the advertiser to certain bid advertisement, and more than advertisement residual or account
Volume.Server 110 is according to the clicking rate predicted values of each candidate locations, bid, and advertisement residual or the account of advertiser
The information such as family remaining sum, displaying probability corresponding to each candidate locations can be calculated.Displaying probability is bigger to represent that the advertisement is thrown
The possibility put is bigger.
Specifically, as shown in figure 9, the process for calculating displaying probability may comprise steps of 901-903.
In step 901, advertisement providing is obtained to launch the showing resource that every candidate locations provide；
Can be obtained according to the ID of each candidate locations from database prestore it is corresponding with candidate locations ID
Information, including advertiser is to the bid of the advertisement, the account balance of advertiser or advertisement residual.
In step 902, according to clicking rate predicted value and showing resource corresponding to every candidate locations, dispensing every is estimated
Feedback resources caused by candidate locations；
Specifically, every candidate locations production of dispensing is estimated by the eCPM (thousand displaying incomes) for calculating every candidate locations
Raw feedback resources.Thousand times displaying income can be calculated using below equation：
When being bid with CPC (clicking on price every time), eCPM=1000*CTR*CPC, wherein CTR are clicking rate predicted value.
During with CPM (every thousand displaying prices) bid：ECPM=CPM.
In step 903, the feedback resources according to caused by every candidate locations of the dispensing calculate every candidate locations
Show probability.
Specifically, a displaying probability for being used to control different feedback resources (such as thousand times displaying incomes) to bring can be set
The displaying probability coefficent (μ) of gap.Wherein, show that probability coefficent is bigger, then the displaying probability that thousand displaying income gaps are brought
Gap is bigger.In a kind of exemplary embodiment, every is calculated according to the eCPM of each candidate locations and displaying probability coefficent
The displaying probability of candidate locations can be calculated using equation below：
Wherein, Pi is the displaying probability of i-th candidate locations, and eCPMi is thousand displaying incomes of i-th candidate locations, μ
To show probability coefficent, n represents a shared n bar advertisements.
It should be noted that if the advertiser's residual or account balance of a certain advertisement are less, cause the advertisement
When residue displaying (dispensing) number is relatively low, then corresponding reduction of speed coefficient can be multiplied by the displaying probability of the advertisement.Such as table 1 below institute
Show, for remaining displaying number and corresponding reduction of speed coefficient example.
The remaining displaying number of table 1 and corresponding reduction of speed coefficient example
| Residue displaying number | Reduction of speed coefficient |
| >20000 | 1 (not doing reduction of speed) |
| <=20000 | 0.5 |
| <=10000 | 0.2 |
| <=5000 | 0.1 |
From table 1 it follows that when remaining displaying number it is more (>20000) when, reduction of speed coefficient is 1, that is, does not do and drop
Speed, residue displaying number it is few (<=20000) when, for different remaining displaying numbers, reduction of speed coefficient can be set respectively
Value.Reduction of speed coefficient is corresponding with residue displaying number, and residue displaying number is fewer, and reduction of speed coefficient is smaller.Wherein, reduction of speed coefficient and residue
The corresponding relation of displaying number can be set in advance according to historical experience.
In one embodiment, every candidate is calculated according to the feedback resources of every candidate locations and corresponding reduction of speed coefficient
The displaying probability of advertisement, using equation below：
Wherein, Pi is the displaying probability of i-th advertisement, and eCPMi is thousand displaying incomes of i-th advertisement, and μ is default
Probability coefficent is shown, σ i are the reduction of speed coefficient of i-th advertisement, and n is the sum of advertisement bar number.
In step 604, it is wide from the candidate by table of random numbers method according to the displaying probability of every candidate locations
The targeted advertisements to be put are selected in announcement.
Specifically, according to the displaying probability of every candidate locations, obtain corresponding with the displaying probability of every candidate locations
Numerical intervals, by generating random number, the numerical intervals according to where random number, candidate locations corresponding to the numerical intervals are selected to make
For the targeted advertisements launched to user.
As an example it is assumed that the displaying probability in the presence of three candidate locations A, B, C is respectively 0.1,0.3,0.6.It can incite somebody to action
Displaying probability is multiplied by 100, obtains 10,30,60, numerical intervals that can be using 1-10 as advertisement A, using 11-40 as advertisement B's
Numerical intervals, the numerical intervals using 41-100 as advertisement C afterwards can be by generating a random number, and judgement is scolded at random
In which numerical intervals, just advertisement is shown to user corresponding to selection.
For example, the random number of generation is 32, fall the section 11-40 in advertisement B, then advertisement B can be launched to user, to wide
B is accused to be shown.Assuming that the random number of generation falls section 41-100 in advertisement C for 61, then return to advertisement C and be shown.
By way of generating random number, it is ensured that every candidate locations have the possibility being launched, rather than every time
The high advertisement of displaying probability is all launched, so as to avoid launching identical advertisement every time, makes the advertisement variation of dispensing, it is rich
Rich types of adverstising.
Following is embodiment of the present disclosure, can be used for performing that the above-mentioned server 110 of the disclosure performs based on verification
Advertisement placement method embodiment.For the details not disclosed in embodiment of the present disclosure, it refer to the disclosure and be based on verification
Advertisement placement method embodiment.
Figure 10 is a kind of block diagram of advertisement delivery device based on verification according to an exemplary embodiment, and this is based on
The advertisement delivery device of verification can be used in the server 110 of implementation environment shown in Fig. 1, perform Fig. 3-Fig. 9 it is any shown in
The all or part of step of advertisement placement method based on verification.As shown in Figure 10, the device includes but is not limited to：Advertisement thing
Part receiving module 1010, identifying code computing module 1020, advertisement correction verification module 1030, time-obtaining module 1040, Time transfer receiver
Module 1050.
Advertised event receiving module 1010, for after targeted advertisements are launched, receiving the advertised event reported；
Identifying code computing module 1020, for the advertisement identification information carried according to the advertised event, calculate advertisement and test
Demonstrate,prove code；
Advertisement correction verification module 1030, for by the advertisement check code in the advertisement verification code and the advertisement identification information
It is compared；
Time-obtaining module 1040, for when the advertisement verification code is consistent with the advertisement check code, described in acquisition
Advertisement in advertisement identification information issues the time；
Time transfer receiver module 1050, it is compared for the advertisement to be issued into the time with current time, if the advertisement
The time interval for issuing time and current time is less than preset value, then the advertised event is as the meter for launching the targeted advertisements
Take foundation.
The function of modules and the implementation process of effect specifically refer to the above-mentioned advertisement based on verification and thrown in said apparatus
The implementation process that step is corresponded in method is put, will not be repeated here.
Advertised event receiving module 1010 such as can be some physical arrangement input/output interface 258 in Fig. 2.
Identifying code computing module 1020, advertisement correction verification module 1030, time-obtaining module 1040, Time transfer receiver module 1050
Can also be functional module, for performing the corresponding step in the above-mentioned advertisement placement method based on verification.It is appreciated that these
Module can by hardware, software, or a combination of both realize.When realizing in hardware, these modules may be embodied as
One or more hardware modules, such as one or more application specific integrated circuits.When being realized with software mode, these modules can be with
It is embodied as the one or more computer programs performed on the one or more processors, such as Fig. 2 institute of central processing unit 222
The program being stored in memory 232 performed.
Optionally, as shown in figure 11, the advertisement delivery device based on verification that the disclosure provides also includes：
Message identification acquisition module 1110, for obtaining message identification corresponding to the targeted advertisements；
Check code computing module 1120, encoded for being combined to the random value of described information mark and itself storage
To the advertisement check code；
Advertisement and identifier forms module 1130, for described information mark and the advertisement check code are combined to be formed it is described wide
Accuse identification information；
Advertisement putting module 1140, for the targeted advertisements to be thrown in the lump with the corresponding advertisement identification information
Put.
Optionally, as shown in figure 12, the identifying code computing module 1020 includes：
Message identification acquiring unit 1021, for obtaining the described information included in the advertisement identification information mark；
Assembly coding unit 1022, obtained for being combined coding to the random value of described information mark and itself storage
The advertisement verification code.
Optionally, as shown in figure 13, the advertisement delivery device based on verification that the disclosure provides also includes：
Characteristic information acquisition module 1310, for receiving advertisement putting request, triggering obtains the advertisement of every candidate locations
Characteristic information；
Clicking rate computing module 1320, thrown for the characteristic of advertisement information according to every candidate locations and the advertisement
The user's characteristic information of request instruction is put, calculates the clicking rate predicted value of every candidate locations；
Probability evaluation entity 1330 is shown, it is wide for the clicking rate predicted value according to every candidate locations and each candidate
Showing resource corresponding to announcement, calculate the displaying probability of every candidate locations；
Targeted advertisements selecting module 1340, for the displaying probability according to every candidate locations, pass through the table of random numbers
Method selects the targeted advertisements to be put from the candidate locations.
Optionally, the clicking rate computing module 1320 includes：
New vectorial construction unit, for the user's characteristic information and the characteristic of advertisement information of every candidate locations to be carried out
Assembly coding one by one, build new feature vector corresponding to every candidate locations；
Clicking rate estimates unit, for the advertisement point for pre-establishing new feature vector input corresponding to every candidate locations
Rate forecast model is hit, obtains clicking rate predicted value corresponding to every candidate locations.
Optionally, the user's characteristic information includes user state information and user preference information；The User Status letter
Breath includes user identity status information, mood states information, is presently at least one of menstrual period session information；The user
Preference information includes reading at least one of preference, shopping preferences and Matrix.
Optionally, the advertisement delivery device based on verification that the disclosure provides also includes：
Advertised event screening module, for filtering out the advertised event of all rates grounds as the targeted advertisements；
Number statistical module, for counting the displaying number or number of clicks of the targeted advertisements according to the selection result；
Resource deducts module, is provided for deducting corresponding advertisement according to the displaying number or number of clicks of the targeted advertisements
Source.
Optionally, the advertising resource includes exchange resource and virtual resource；The advertisement based on verification that the disclosure provides
Delivery device also includes：
Resource receiving module, for receiving the exchange resource, corresponding virtual resource is generated according to the exchange resource.
Optionally, the disclosure also provides a kind of electronic equipment, and the electronic equipment can be used for the clothes of implementation environment shown in Fig. 1
It is engaged in device 110, performs all or part of step of any shown advertisement placement methods based on verification of Fig. 3-Fig. 9.It is described
Device includes：
Processor；
For storing the memory of processor-executable instruction；
Wherein, the processor is configured as performing the advertisement placement method based on verification described in above-described embodiment.
The concrete mode of the computing device operation of electronic equipment is about being somebody's turn to do based on the wide of verification in the embodiment
Accuse in the embodiment of put-on method and perform detailed description, explanation will be not set forth in detail herein.
In the exemplary embodiment, a kind of storage medium is additionally provided, the storage medium is computer-readable recording medium,
Such as can be the provisional and non-transitorycomputer readable storage medium for including instruction.The storage medium is stored with computer
Program, the computer program can be performed by the central processing unit 222 of server 200 to complete the above-mentioned advertisement putting based on verification
Method.
It should be appreciated that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and
And various modifications and changes can be being performed without departing from the scope.The scope of the present invention is only limited by appended claim.
Claims (16)
- A kind of 1. advertisement placement method based on verification, it is characterised in that including：After targeted advertisements are launched, the advertised event reported is received；The advertisement identification information carried according to the advertised event, calculate advertisement verification code；The advertisement verification code is compared with the advertisement check code in the advertisement identification information；If the advertisement verification code is consistent with the advertisement check code, when obtaining the advertisement in the advertisement identification information and issuing Between；The advertisement issued into the time to be compared with current time, if the advertisement was issued between time and the time of current time Every less than preset value, then the advertised event is as the rates ground for launching the targeted advertisements.
- 2. according to the method for claim 1, it is characterised in that described before the advertised event reported is received, the side Method also includes：Obtain message identification corresponding to the targeted advertisements；Are combined by coding and obtains the advertisement check code for described information mark and the random value itself stored；Described information mark and the advertisement check code are combined to form the advertisement identification information；The targeted advertisements are launched in the lump with the corresponding advertisement identification information.
- 3. according to the method for claim 2, it is characterised in that the advertisement identification information carried according to advertised event, Calculating advertisement verification code includes：Obtain the described information mark included in the advertisement identification information；Are combined by coding and obtains the advertisement verification code for described information mark and the random value itself stored.
- 4. according to the method for claim 2, it is characterised in that before message identification corresponding to the acquisition targeted advertisements, Methods described also includes：Advertisement putting request is received, triggering obtains the characteristic of advertisement information of every candidate locations；According to the characteristic of advertisement information of every candidate locations and the user's characteristic information of advertisement putting request instruction, meter Calculate the clicking rate predicted value of every candidate locations；According to showing resource corresponding to the clicking rate predicted value of every candidate locations and each candidate locations, every candidate is calculated The displaying probability of advertisement；According to the displaying probability of every candidate locations, selected by table of random numbers method from the candidate locations to be put The targeted advertisements.
- 5. according to the method for claim 4, it is characterised in that the characteristic of advertisement information according to every candidate locations and The user's characteristic information of the advertisement putting request instruction, the clicking rate predicted value of every candidate locations is calculated, including：The user's characteristic information and the characteristic of advertisement information of every candidate locations are subjected to assembly coding one by one, build every time Select new feature vector corresponding to advertisement；The ad click rate forecast model that new feature vector input corresponding to every candidate locations is pre-established, obtains every time Select clicking rate predicted value corresponding to advertisement.
- 6. according to the method for claim 4, it is characterised in that the user's characteristic information includes user state information and use Family preference information；The user state information includes user identity status information, mood states information, is presently in the stage in menstrual period At least one of information；The user preference information includes reading at least one of preference, shopping preferences and Matrix.
- 7. according to the method for claim 1, it is characterised in that described advertisement is issued into the time to be compared with current time Right, if the advertisement issues the time and the time interval of current time is less than preset value, the advertised event is as dispensing institute After the rates ground for stating targeted advertisements, methods described also includes：Filter out the advertised event of all rates grounds as the targeted advertisements；The displaying number or number of clicks of the targeted advertisements are counted according to the selection result；Corresponding advertising resource is deducted according to the displaying number or number of clicks of the targeted advertisements.
- 8. according to the method for claim 4, it is characterised in that the advertising resource includes exchange resource and virtual resource； Before the corresponding advertising resource according to the displaying number or number of clicks of targeted advertisements deduction, methods described also includes：The exchange resource is received, corresponding virtual resource is generated according to the exchange resource.
- A kind of 9. advertisement delivery device based on verification, it is characterised in that including：Advertised event receiving module, for after targeted advertisements are launched, receiving the advertised event reported；Identifying code computing module, for the advertisement identification information carried according to the advertised event, calculate advertisement verification code；Advertisement correction verification module, for the advertisement verification code and the advertisement check code in the advertisement identification information to be compared It is right；Time-obtaining module, for when the advertisement verification code is consistent with the advertisement check code, obtaining the advertisement and identifier Advertisement in information issues the time；Time transfer receiver module, it is compared for the advertisement to be issued into the time with current time, if the advertisement issues the time It is less than preset value with the time interval of current time, then the advertised event is as the rates ground for launching the targeted advertisements.
- 10. device according to claim 9, it is characterised in that described device also includes：Message identification acquisition module, for obtaining message identification corresponding to the targeted advertisements；Check code computing module, for the random value of described information mark and itself storage is combined coding obtain it is described wide Accuse check code；Advertisement and identifier forms module, and the advertisement and identifier letter is formed for described information mark and the advertisement check code to be combined Breath；Advertisement putting module, for the targeted advertisements to be launched in the lump with the corresponding advertisement identification information.
- 11. device according to claim 10, it is characterised in that the identifying code computing module includes：Message identification acquiring unit, for obtaining the described information included in the advertisement identification information mark；Assembly coding unit, the advertisement is obtained for being combined coding to the random value of described information mark and itself storage Identifying code.
- 12. device according to claim 10, it is characterised in that described device also includes：Characteristic information acquisition module, for receiving advertisement putting request, triggering obtains the characteristic of advertisement information of every candidate locations；Clicking rate computing module, refer to for the characteristic of advertisement information according to every candidate locations and advertisement putting request The user's characteristic information shown, calculate the clicking rate predicted value of every candidate locations；Probability evaluation entity is shown, for corresponding to the clicking rate predicted value according to every candidate locations and each candidate locations Showing resource, calculate the displaying probability of every candidate locations；Targeted advertisements selecting module, for the displaying probability according to every candidate locations, by table of random numbers method from described The targeted advertisements to be put are selected in candidate locations.
- 13. device according to claim 12, it is characterised in that the clicking rate computing module includes：New vectorial construction unit, for the user's characteristic information and the characteristic of advertisement information of every candidate locations to be carried out one by one Assembly coding, build new feature vector corresponding to every candidate locations；Clicking rate estimates unit, for the ad click rate for pre-establishing new feature vector input corresponding to every candidate locations Forecast model, obtain clicking rate predicted value corresponding to every candidate locations.
- 14. device according to claim 12, it is characterised in that the user's characteristic information include user state information and User preference information；The user state information includes user identity status information, mood states information, is presently in menstrual period rank At least one of segment information；The user preference information includes reading at least one in preference, shopping preferences and Matrix Kind.
- 15. device according to claim 9, it is characterised in that described device also includes：Advertised event screening module, for filtering out the advertised event of all rates grounds as the targeted advertisements；Number statistical module, for counting the displaying number or number of clicks of the targeted advertisements according to the selection result；Resource deducts module, for deducting corresponding advertising resource according to the displaying number or number of clicks of the targeted advertisements.
- 16. device according to claim 12, it is characterised in that the advertising resource includes exchange resource and virtual money Source；Described device also includes：Resource receiving module, for receiving the exchange resource, corresponding virtual resource is generated according to the exchange resource.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710974897.1A CN107657487A (en) | 2017-10-19 | 2017-10-19 | A kind of advertisement placement method and device based on verification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710974897.1A CN107657487A (en) | 2017-10-19 | 2017-10-19 | A kind of advertisement placement method and device based on verification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107657487A true CN107657487A (en) | 2018-02-02 |
Family
ID=61119021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710974897.1A Pending CN107657487A (en) | 2017-10-19 | 2017-10-19 | A kind of advertisement placement method and device based on verification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107657487A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109285263A (en) * | 2018-10-17 | 2019-01-29 | 重庆扬升信息技术有限公司 | One kind being based on the with no paper conference voting prediction technique of big data |
| CN110009426A (en) * | 2019-04-09 | 2019-07-12 | 科达集团股份有限公司技术分公司 | A kind of advertisement bid optimization method based on eCPM conjugate gradient descent method fitting technique |
| CN110163664A (en) * | 2019-04-29 | 2019-08-23 | 成都品果科技有限公司 | A kind of advertising display feedback method and device |
| CN110310155A (en) * | 2019-06-28 | 2019-10-08 | 河北工业职业技术学院 | Advertisement placement method, device and server |
| CN110648156A (en) * | 2018-06-27 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Advertisement processing method, device and equipment |
| CN110781605A (en) * | 2019-11-05 | 2020-02-11 | 恩亿科(北京)数据科技有限公司 | Advertisement putting model testing method and device, computer equipment and storage medium |
| CN111340540A (en) * | 2020-02-24 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Monitoring method, recommendation method and device of advertisement recommendation model |
| CN112232872A (en) * | 2020-10-15 | 2021-01-15 | 苏州龙盈软件开发有限公司 | Overseas advertisement delivery management method, platform and system |
| CN112241899A (en) * | 2019-07-19 | 2021-01-19 | 上海哔哩哔哩科技有限公司 | Advertisement charging method, device and system and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030870A (en) * | 2007-01-26 | 2007-09-05 | 卢斌 | Advertisement accounting method and system based on advertisement feedback telecommunication |
| US20080027809A1 (en) * | 2006-07-27 | 2008-01-31 | Storm Timothy C | Method Of Using A Subdomain Portion Of A Domain Name To Pass A Unique Tracking Code |
| CN101808049A (en) * | 2010-03-25 | 2010-08-18 | 盈世信息科技(北京)有限公司 | Mail transmission method and system |
| CN105631711A (en) * | 2015-12-30 | 2016-06-01 | 合一网络技术(北京)有限公司 | Advertisement putting method and apparatus |
-
2017
- 2017-10-19 CN CN201710974897.1A patent/CN107657487A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080027809A1 (en) * | 2006-07-27 | 2008-01-31 | Storm Timothy C | Method Of Using A Subdomain Portion Of A Domain Name To Pass A Unique Tracking Code |
| CN101030870A (en) * | 2007-01-26 | 2007-09-05 | 卢斌 | Advertisement accounting method and system based on advertisement feedback telecommunication |
| CN101808049A (en) * | 2010-03-25 | 2010-08-18 | 盈世信息科技(北京)有限公司 | Mail transmission method and system |
| CN105631711A (en) * | 2015-12-30 | 2016-06-01 | 合一网络技术(北京)有限公司 | Advertisement putting method and apparatus |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648156A (en) * | 2018-06-27 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Advertisement processing method, device and equipment |
| CN109285263A (en) * | 2018-10-17 | 2019-01-29 | 重庆扬升信息技术有限公司 | One kind being based on the with no paper conference voting prediction technique of big data |
| CN110009426A (en) * | 2019-04-09 | 2019-07-12 | 科达集团股份有限公司技术分公司 | A kind of advertisement bid optimization method based on eCPM conjugate gradient descent method fitting technique |
| CN110163664A (en) * | 2019-04-29 | 2019-08-23 | 成都品果科技有限公司 | A kind of advertising display feedback method and device |
| CN110310155A (en) * | 2019-06-28 | 2019-10-08 | 河北工业职业技术学院 | Advertisement placement method, device and server |
| CN112241899A (en) * | 2019-07-19 | 2021-01-19 | 上海哔哩哔哩科技有限公司 | Advertisement charging method, device and system and readable storage medium |
| CN110781605A (en) * | 2019-11-05 | 2020-02-11 | 恩亿科(北京)数据科技有限公司 | Advertisement putting model testing method and device, computer equipment and storage medium |
| CN110781605B (en) * | 2019-11-05 | 2023-08-25 | 恩亿科(北京)数据科技有限公司 | Advertisement putting model testing method and device, computer equipment and storage medium |
| CN111340540A (en) * | 2020-02-24 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Monitoring method, recommendation method and device of advertisement recommendation model |
| CN111340540B (en) * | 2020-02-24 | 2023-06-06 | 腾讯科技（深圳）有限公司 | Advertisement recommendation model monitoring method, advertisement recommendation method and advertisement recommendation model monitoring device |
| CN112232872A (en) * | 2020-10-15 | 2021-01-15 | 苏州龙盈软件开发有限公司 | Overseas advertisement delivery management method, platform and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107657486A (en) | A kind of advertisement placement method and device | |
| CN107657487A (en) | A kind of advertisement placement method and device based on verification | |
| US8417558B2 (en) | Systems and methods for identifying offered incentives that will achieve an objective | |
| CN107977859A (en) | Advertisement placement method, device, computing device and storage medium | |
| US20190019213A1 (en) | Predicting the effectiveness of a marketing campaign prior to deployment | |
| CN107767175A (en) | A kind of information based on Information rate launches processing method and processing device | |
| US20140278795A1 (en) | Systems and methods to predict purchasing behavior | |
| EP2178041A1 (en) | Dynamic geo-location parameter for determining an impact of online behavior on offline sales | |
| TW200923817A (en) | Monetizing rich media advertising interaction | |
| CN103918001A (en) | Understanding effects of a communication propagated through a social networking system | |
| CN106570718A (en) | Information releasing method and releasing system | |
| CN104035926A (en) | Internet information release method and system | |
| CN108009862B (en) | Method and device for early warning of balance of advertising expense | |
| US20210241314A1 (en) | Method and system for optimizing user grouping for advertisement | |
| EP2359328A1 (en) | A system for providing information concerning the effectiveness of advertising | |
| CN107741986A (en) | User's behavior prediction and corresponding information recommend method and apparatus | |
| CN105590240A (en) | Discrete calculating method of brand advertisement effect optimization | |
| CN108965938A (en) | Potential paying customer prediction technique and system in smart television | |
| CN110515904B (en) | Quality prediction model training method, quality prediction method and device for media file | |
| CN105608604A (en) | Continuous calculation method of brand advertisement effectiveness optimization | |
| CN106611321A (en) | An identification method and apparatus for fake handset numbers | |
| CN108154379B (en) | Media information publishing method and device | |
| Zhao et al. | Shapley value methods for attribution modeling in online advertising | |
| US20150227963A1 (en) | Systems, methods, and apparatus for budget allocation | |
| CN110163683B (en) | Value user key index determination method, advertisement delivery method and device |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 361000 Area 1F-D1, Huaxun Building A, Software Park, Xiamen Torch High-tech Zone, Xiamen City, Fujian Province Applicant after: Xiamen Meishao Co., Ltd. Address before: Software Park Siming District of Xiamen city in Fujian province 361008 two sunrise Road No. 22 Room 102, unit G03 Applicant before: XIAMEN MEIYOU INFORMATION SCIENCE & TECHNOLOGY Co.,Ltd. |