CN103440584A - Advertisement putting method and system - Google Patents
Advertisement putting method and system Download PDFInfo
- Publication number
- CN103440584A CN103440584A CN2013103290919A CN201310329091A CN103440584A CN 103440584 A CN103440584 A CN 103440584A CN 2013103290919 A CN2013103290919 A CN 2013103290919A CN 201310329091 A CN201310329091 A CN 201310329091A CN 103440584 A CN103440584 A CN 103440584A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- dimensional characteristics
- candidate
- clicking rate
- rate
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An embodiment of the invention discloses an advertisement putting method and system. The method and system aim to resolve the problems that calculating pressure of an advertisement putting server is large, response time is long, and advertisement putting speed is low. The method comprises the steps that historical click rates of various dimension characteristics of all candidate put advertisements are calculated, and weight of all the dimension characteristics is calculated according to the historical click rates of all the dimension characteristics; the dimension characteristics is less than advertisement putting characteristics; click rate prediction calculation is conducted on the historical click rates of all the dimension characteristics and the weight of all the dimension characteristics to obtain click rate prediction values of all the candidate put advertisements; the click rate prediction values of all the candidate put advertisements are mapped into advertisement click rates of all the candidate put advertisements, and advertisement putting is conducted according to the advertisement click rates of all the candidate put advertisements. As overmany advertisement putting characteristics do not need to be considered, calculating amount of the advertisement putting server is reduced, processing pressure of the advertisement putting server is relieved, and the response speed of the advertisement putting server is improved.
Description
Technical field
The embodiment of the present invention relates to the internet advertisement technology field, particularly relates to a kind of advertisement placement method and system.
Background technology
At internet arena, bid advertisement system development in real time is very fast at present, and it is in real time each advertisement putting flow bid that party in request's service platform (Demand Service Platform, DSP) needs, and the highest DSP of bid obtains current advertisement putting chance.Therefore DSP need to be within unusual short time (in 100ms) assess the value of current advertisement putting chance, generally with Cost Per Mille (Cost Per Mille, CPM), pay.
DSP charges with every click cost (Cost Per Click, CPC) towards the advertiser.
Finally, DSP also needs to convert CPM to CPC, calculates the cost of advertisement putting chance.CPM is converted in the process of CPC, the committed step needed is the prediction of ad click rate.
The prediction of clicking rate need to be considered the advertisement putting feature usually, comprises user characteristics (user search keyword, webpage discharge record, ad click record etc.), web page characteristics (Web page classifying, Web Page Key Words etc.), characteristic of advertisement (advertisement classification, advertisement guide page, advertisement keyword etc.).
Although the advertisement putting feature of considering too much can improve the accuracy rate of clicking rate prediction, make advertisement putting more accurate, still, also can cause the calculating pressure of advertisement releasing server excessive, the response time is long, reduced the speed of advertisement putting, the real-time of advertisement putting has been impacted.
Summary of the invention
The embodiment of the present invention discloses a kind of advertisement placement method and system, and to solve, the advertisement releasing server calculating pressure is large, the response time is long and the slow-footed problem of advertisement putting.
In order to address the above problem, the invention discloses a kind of advertisement placement method, comprising:
Add up each candidate and throw in the historical clicking rate of each dimensional characteristics of advertisement, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics; Described each dimensional characteristics is less than the advertisement putting feature;
The weight of the historical clicking rate of described each dimensional characteristics and described each dimensional characteristics is carried out to the clicking rate prediction and calculation, obtain the clicking rate predicted value that described each candidate throws in advertisement;
The clicking rate predicted value that described each candidate is thrown in to advertisement is mapped as respectively described each candidate and throws in the ad click rate of advertisement, and carries out advertisement putting according to the ad click rate that described each candidate throws in advertisement.
Preferably, each candidate of described statistics throws in the historical clicking rate of each dimensional characteristics of advertisement, and calculates the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics, comprising:
Count the historical clicking rate that described each candidate throws in each dimensional characteristics of advertisement from historical advertisement putting daily record;
The historical clicking rate of described each dimensional characteristics is obtained to the weight of described each dimensional characteristics according to the regression model training;
Wherein, described each dimensional characteristics comprises: media, advertising sector, advertisement position size, advertisement position position, adline and ad material;
According to the order of media, adline, advertisement position position, advertising sector, ad material, advertisement position size, described each dimensional characteristics reduces gradually on the impact of described ad click rate.
Preferably, the described weight by the historical clicking rate of described each dimensional characteristics and described each dimensional characteristics is carried out the clicking rate prediction and calculation, obtains the clicking rate predicted value that described each candidate throws in advertisement, comprising:
By
calculate the clicking rate predicted value that described each candidate throws in advertisement;
Wherein, x is described clicking rate predicted value, and bias is the deviation that the factor outside described each dimensional characteristics affects the clicking rate predicted value, the number that n is each dimensional characteristics, w
ibe the weight of i dimensional characteristics, ctr
iit is the historical clicking rate of i dimensional characteristics.
Preferably, the described clicking rate predicted value that described each candidate is thrown in to advertisement is mapped as respectively described each candidate and throws in the ad click rate of advertisement, comprising:
Described each candidate is thrown in to the clicking rate predicted value of advertisement and carry out linear regression calculating, obtain described each candidate and throw in the ad click rate of advertisement.
Preferably, the described clicking rate predicted value that described each candidate is thrown in to advertisement is carried out linear regression calculating, obtains described each candidate and throws in the ad click rate of advertisement, comprising:
Pass through y=ax
3+ bx
2+ cx+d calculates described each candidate and throws in the ad click rate of advertisement;
Wherein, y is described ad click rate, and x is described clicking rate predicted value, and a, b, c, d are regression coefficient.
Preferably, the described ad click rate of throwing in advertisement according to described each candidate carries out advertisement putting, comprising:
The ad click rate that described each candidate is thrown in to advertisement is arranged in order;
Select the candidate of described ad click rate maximum to throw in advertisement and carry out advertisement putting.
The invention also discloses a kind of advertisement delivery system, comprising:
Dimensional characteristics information determination module, throw in the historical clicking rate of each dimensional characteristics of advertisement for adding up each candidate, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics; Described each dimensional characteristics is less than the advertisement putting feature;
Clicking rate predictor calculation module, carry out the clicking rate prediction and calculation for the weight of the historical clicking rate by described each dimensional characteristics and described each dimensional characteristics, obtains the clicking rate predicted value that described each candidate throws in advertisement;
The advertisement putting module, be mapped as respectively described each candidate for the clicking rate predicted value of described each candidate being thrown in to advertisement and throw in the ad click rate of advertisement, and carry out advertisement putting according to the ad click rate that described each candidate throws in advertisement.
Preferably, described dimensional characteristics information determination module comprises:
The statistics submodule, for counting from historical advertisement putting daily record the historical clicking rate that described each candidate throws in each dimensional characteristics of advertisement;
The training submodule, obtain the weight of described each dimensional characteristics according to the regression model training for the historical clicking rate by described each dimensional characteristics;
Wherein, described each dimensional characteristics comprises: media, advertising sector, advertisement position size, advertisement position position, adline and ad material;
According to the order of media, adline, advertisement position position, advertising sector, ad material, advertisement position size, described each dimensional characteristics reduces gradually on the impact of described ad click rate.
Preferably, described clicking rate predictor calculation module is passed through
calculate the clicking rate predicted value that described each candidate throws in advertisement;
Wherein, x is described clicking rate predicted value, and bias is the deviation that the factor outside described each dimensional characteristics affects the clicking rate predicted value, the number that n is each dimensional characteristics, w
ibe the weight of i dimensional characteristics, ctr
iit is the historical clicking rate of i dimensional characteristics.
Preferably, described advertisement putting module is passed through y=ax
3+ bx
2+ cx+d calculates described each candidate and throws in the ad click rate of advertisement;
Wherein, y is described ad click rate, and x is described clicking rate predicted value, and a, b, c, d are regression coefficient.
With background technology, compare, the embodiment of the present invention comprises following advantage:
Do not need to consider too much advertisement putting feature, only need to obtain clicking rate and the weight (each dimensional characteristics is less than the advertisement putting feature) of each dimensional characteristics, then utilize clicking rate and the weight calculation of each dimensional characteristics and shine upon to obtain final ad click rate, finally from each candidate, throw in advertisement and select high being thrown in of ad click rate.
Owing to not needing to consider too much advertisement putting feature, weakened the forecasting process of ad click rate, just reduced the calculated amount of advertisement releasing server, alleviated the processing pressure of advertisement releasing server, improved the response speed of advertisement releasing server.
And, count the clicking rate of each dimensional characteristics from historical advertisement putting daily record, and utilize regression model to calculate the weight of each dimensional characteristics, the ad click rate obtained according to the clicking rate of each dimensional characteristics and weight calculation mapping more accurately, more effective.
The accompanying drawing explanation
Fig. 1 is a kind of advertisement placement method process flow diagram in the embodiment of the present invention;
Fig. 2 is a kind of advertisement placement method process flow diagram in the embodiment of the present invention;
Fig. 3 is a kind of advertisement delivery system structural drawing in the embodiment of the present invention;
Fig. 4 is a kind of advertisement delivery system structural drawing in the embodiment of the present invention;
Fig. 5 is a kind of advertisement delivery system structural drawing in the embodiment of the present invention.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, below in conjunction with the drawings and specific embodiments, the present invention is further detailed explanation.
Introduce in detail a kind of advertisement placement method disclosed by the invention and system below by enumerating several specific embodiments.
Embodiment mono-
Introduce in detail the disclosed a kind of advertisement placement method of the embodiment of the present invention.
With reference to Fig. 1, show a kind of advertisement placement method process flow diagram in the embodiment of the present invention.
Each candidate throws in each dimensional characteristics that advertisement has its correspondence, and the advertising sector, the candidate that as the candidate, throw under advertisement throw in the shared advertisement bit position of advertisement and size etc.
It should be noted that, described each dimensional characteristics is less than the advertisement putting feature.
Preferably, can use regression model and the historical clicking rate of adding up each dimensional characteristics obtained, calculate the weight of each dimensional characteristics, the weight of dimensional characteristics is higher, just larger on the impact of clicking rate.
Throw in each dimensional characteristics of advertisement for each candidate, calculate the clicking rate predicted value that each candidate throws in advertisement.For example, each dimensional characteristics that the candidate throws in advertisement AD1 is T1 and T2, and the clicking rate of dimensional characteristics T1 is C1, and weight is W1, and the clicking rate of dimensional characteristics T2 is C2, and weight is W2; Each dimensional characteristics that the candidate throws in advertisement AD2 is T3 and T4, and the clicking rate of dimensional characteristics T3 is C3, and weight is W3, and the clicking rate of dimensional characteristics T4 is C4, and weight is W4.Can be according to the clicking rate C1 of dimensional characteristics T1, weights W 1, and the clicking rate C2 of dimensional characteristics T2, weights W 2 calculates the clicking rate predicted value that the candidate throws in advertisement AD1; Can also be according to the clicking rate C3 of dimensional characteristics T3, weights W 3, and the clicking rate C4 of dimensional characteristics T4, weights W 4 calculates the clicking rate predicted value that the candidate throws in advertisement AD2.
In like manner, can calculate the ad click rate predicted value that each candidate throws in advertisement.
Preferably, the process that above-mentioned ad click rate predicted value is mapped as ad click rate can be used regression formula that the clicking rate predicted value is mapped as to ad click rate.
And can throw in advertisement and to select the large candidate of ad click rate to throw in advertisement to carry out advertisement putting from each candidate.
In sum, the disclosed a kind of advertisement placement method of the embodiment of the present invention, compare with background technology, has the following advantages:
Do not need to consider too much advertisement putting feature, only need to obtain clicking rate and the weight (each dimensional characteristics is less than the advertisement putting feature) of each dimensional characteristics, then utilize clicking rate and the weight calculation of each dimensional characteristics and shine upon to obtain final ad click rate, finally from each candidate, throw in advertisement and select high being thrown in of ad click rate.
Owing to not needing to consider too much advertisement putting feature, weakened the forecasting process of ad click rate, just reduced the calculated amount of advertisement releasing server, alleviated the processing pressure of advertisement releasing server, improved the response speed of advertisement releasing server.
And, count the clicking rate of each dimensional characteristics from historical advertisement putting daily record, and utilize regression model to calculate the weight of each dimensional characteristics, the ad click rate obtained according to the clicking rate of each dimensional characteristics and weight calculation mapping more accurately, more effective.
Embodiment bis-
Introduce in detail the disclosed a kind of advertisement placement method of the embodiment of the present invention.
With reference to Fig. 2, show a kind of advertisement placement method process flow diagram in the embodiment of the present invention.
Wherein, described each dimensional characteristics is less than the advertisement putting feature.Described each dimensional characteristics comprises: media, advertising sector, advertisement position size, advertisement position position, adline and ad material.
According to the order of media, adline, advertisement position position, advertising sector, ad material, advertisement position size, described each dimensional characteristics reduces gradually on the impact of described ad click rate.
Preferably, described step 200 can comprise:
Sub-step 2001 counts the historical clicking rate that described each candidate throws in each dimensional characteristics of advertisement from historical advertisement putting daily record.
Sub-step 2002, obtain the historical clicking rate of described each dimensional characteristics the weight of described each dimensional characteristics according to the regression model training.
Regression model is a kind of mathematical model that statistical relationship is quantitatively described.In the art, can directly utilize regression model to obtain the weight of each dimensional characteristics according to the historical clicking rate training of each dimensional characteristics.The historical clicking rate of each dimensional characteristics that statistics can be obtained is according to regression model, go to estimate and (or) predict the weight of each dimensional characteristics.
Experiment showed, that, in each dimensional characteristics, media have the greatest impact to ad click rate, the affect minimum of advertisement position size on ad click rate.
Preferably, described step 202 can be:
The weight of the historical clicking rate of described each dimensional characteristics and described each dimensional characteristics is carried out to the clicking rate prediction and calculation, obtain the clicking rate predicted value that described each candidate throws in advertisement.
Particularly, can pass through
calculate the clicking rate predicted value that described each candidate throws in advertisement.
Wherein, x is described clicking rate predicted value, and bias is the deviation that the factor outside described each dimensional characteristics affects the clicking rate predicted value, the number that n is each dimensional characteristics, w
ibe the weight of i dimensional characteristics, ctr
iit is the historical clicking rate of i dimensional characteristics.
Those skilled in the art can calculate by prior art the value of above-mentioned bias, and the clicking rate forecasting process that the value of bisa is thrown in advertisement according to actual candidate calculates.
For example, the weight that certain candidate throws in the dimensional characteristics A of advertisement AD1 is-0.8969, and dimensional characteristics B weight is-1.058, and dimensional characteristics C weight is-0.1162, and dimensional characteristics D weight is that-0.4111, bias is-1.653.For certain dispenser meeting, the clicking rate of dimensional characteristics A, dimensional characteristics B, dimensional characteristics C and dimensional characteristics D is respectively 0.134,0.533,0.432,0.101.
Known according to above-mentioned formula, the index of e is 0-(-1.653+(-0.8969 * 0.134)+(1.058 * 0.533)+(0.1162 * 0.432)+(0.4111 * 0.101))=2.428818.
2.428818 powers of e are 11.34546.
X=1/(1+11.34546)=0.081.Be that the clicking rate predicted value that the candidate throws in advertisement AD1 is 0.081.
In like manner, can calculate the clicking rate predicted value that other candidates throw in advertisement.
Preferably, described step 204 can be:
Sub-step 2041, throw in described each candidate the clicking rate predicted value of advertisement and carry out linear regression calculating, obtains described each candidate and throw in the ad click rate of advertisement.
Preferably, described sub-step 2041 can be:
Pass through y=ax
3+ bx
2+ cx+d calculates described each candidate and throws in the ad click rate of advertisement.
Wherein, y is described ad click rate, and x is described clicking rate predicted value, and a, b, c, d are regression coefficient.
Learn a=0 by the linear regression fit result, b=1.255214e-02, c=6.133188e-03, d=4.642903e-05, by the above-mentioned formula about y of the x substitution calculated in above-mentioned steps 202, y=0*0.081
3+ 1.255214e-02*0.081
2+ 6.133188e-03*0.081+4.642903e-05=0.0006255718, the candidate to throw in the ad click rate of advertisement AD1 be 0.0006255718.
In like manner, can calculate the ad click rate that other candidates throw in advertisement.
Sub-step 2042, the ad click rate that described each candidate is thrown in to advertisement is arranged in order.
For example, the ad click rate that the candidate throws in advertisement AD1 is 0.0006255718, and the ad click rate that the candidate throws in advertisement AD2 is 0.0007434625.Can be according to ad click rate order from big to small or order from small to large the candidate thrown in to advertisement arrange.
Sub-step 2043, select the candidate of described ad click rate maximum to throw in advertisement and carry out advertisement putting.
In above-mentioned sub-step 2042, the ad click rate that the candidate throws in advertisement AD2 is greater than the ad click rate that the candidate throws in advertisement AD1, selects the candidate to throw in advertisement AD2 and carries out advertisement putting.
In sum, the disclosed a kind of advertisement placement method of the embodiment of the present invention, compare with background technology, has the following advantages:
Do not need to consider too much advertisement putting feature, only need to obtain clicking rate and the weight (each dimensional characteristics is less than the advertisement putting feature) of each dimensional characteristics, then utilize clicking rate and the weight calculation of each dimensional characteristics and shine upon to obtain final ad click rate, finally from each candidate, throw in advertisement and select high being thrown in of ad click rate.
Owing to not needing to consider too much advertisement putting feature, weakened the forecasting process of ad click rate, just reduced the calculated amount of advertisement releasing server, alleviated the processing pressure of advertisement releasing server, improved the response speed of advertisement releasing server.
And, count the clicking rate of each dimensional characteristics from historical advertisement putting daily record, and utilize regression model to calculate the weight of each dimensional characteristics, the ad click rate obtained according to the clicking rate of each dimensional characteristics and weight calculation mapping more accurately, more effective.
Embodiment tri-
Introduce in detail the disclosed a kind of advertisement delivery system of the embodiment of the present invention.
With reference to Fig. 3, show a kind of advertisement delivery system structural drawing in the embodiment of the present invention.
Described a kind of advertisement delivery system can comprise: dimensional characteristics information determination module 300, and clicking rate predictor calculation module 302, and, advertisement putting module 304.
Below introduce in detail respectively the function of each module and the relation between each module.
Dimensional characteristics information determination module 300, throw in the historical clicking rate of each dimensional characteristics of advertisement for adding up each candidate, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics.
Wherein, described each dimensional characteristics is less than the advertisement putting feature.
Clicking rate predictor calculation module 302, carry out the clicking rate prediction and calculation for the weight of the historical clicking rate by described each dimensional characteristics and described each dimensional characteristics, obtains the clicking rate predicted value that described each candidate throws in advertisement.
Advertisement putting module 304, be mapped as respectively described each candidate for the clicking rate predicted value of described each candidate being thrown in to advertisement and throw in the ad click rate of advertisement, and carry out advertisement putting according to the ad click rate that described each candidate throws in advertisement.
In sum, the disclosed a kind of advertisement delivery system of the embodiment of the present invention, compare with background technology, has the following advantages:
Do not need to consider too much advertisement putting feature, only need to obtain clicking rate and the weight (each dimensional characteristics is less than the advertisement putting feature) of each dimensional characteristics, then utilize clicking rate and the weight calculation of each dimensional characteristics and shine upon to obtain final ad click rate, finally from each candidate, throw in advertisement and select high being thrown in of ad click rate.
Owing to not needing to consider too much advertisement putting feature, weakened the forecasting process of ad click rate, just reduced the calculated amount of advertisement releasing server, alleviated the processing pressure of advertisement releasing server, improved the response speed of advertisement releasing server.
And, count the clicking rate of each dimensional characteristics from historical advertisement putting daily record, and utilize regression model to calculate the weight of each dimensional characteristics, the ad click rate obtained according to the clicking rate of each dimensional characteristics and weight calculation mapping more accurately, more effective.
Embodiment tetra-
Introduce in detail the disclosed a kind of advertisement delivery system of the embodiment of the present invention.
With reference to Fig. 4, show a kind of advertisement delivery system structural drawing in the embodiment of the present invention.
Described a kind of advertisement delivery system can comprise: dimensional characteristics information determination module 400, and clicking rate predictor calculation module 402, and, advertisement putting module 404.
Wherein, described dimensional characteristics information determination module 400 can comprise: statistics submodule 4001, and, training submodule 4002.
Described advertisement putting module 404 can comprise: calculating sub module 4041, and sequence submodule 4042, and, chooser module 4043.
Below introduce in detail respectively the relation between the function of each module, each submodule and each module, each submodule.
Dimensional characteristics information determination module 400, throw in the historical clicking rate of each dimensional characteristics of advertisement for adding up each candidate, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics.
Described each dimensional characteristics is less than the advertisement putting feature.
Preferably, described dimensional characteristics information determination module 400 can comprise:
Statistics submodule 4001, for counting from historical advertisement putting daily record the historical clicking rate that described each candidate throws in each dimensional characteristics of advertisement.
Training submodule 4002, obtain the weight of described each dimensional characteristics according to the regression model training for the historical clicking rate by described each dimensional characteristics.
And described each dimensional characteristics can comprise: media, advertising sector, advertisement position size, advertisement position position, adline and ad material.
According to the order of media, adline, advertisement position position, advertising sector, ad material, advertisement position size, described each dimensional characteristics reduces gradually on the impact of described ad click rate.
Clicking rate predictor calculation module 402, carry out the clicking rate prediction and calculation for the weight of the historical clicking rate by described each dimensional characteristics and described each dimensional characteristics, obtains the clicking rate predicted value that described each candidate throws in advertisement.
Preferably, described clicking rate predictor calculation module 402 can be passed through
calculate the clicking rate predicted value that described each candidate throws in advertisement;
Wherein, x is described clicking rate predicted value, and bias is the deviation that the factor outside described each dimensional characteristics affects the clicking rate predicted value, the number that n is each dimensional characteristics, w
ibe the weight of i dimensional characteristics, ctr
iit is the historical clicking rate of i dimensional characteristics.
Advertisement putting module 404, be mapped as respectively described each candidate for the clicking rate predicted value of described each candidate being thrown in to advertisement and throw in the ad click rate of advertisement, and carry out advertisement putting according to the ad click rate that described each candidate throws in advertisement.
Preferably, described advertisement putting module 404 can be passed through y=ax
3+ bx
2+ cx+d calculates described each candidate and throws in the ad click rate of advertisement.
Wherein, y is described ad click rate, and x is described clicking rate predicted value, and a, b, c, d are regression coefficient.
Preferably, described advertisement putting module 404 can comprise:
Calculating sub module 4041, carry out linear regression calculating for the clicking rate predicted value of described each candidate being thrown in to advertisement, obtains described each candidate and throw in the ad click rate of advertisement.
Sequence submodule 4042, arrange in order for the ad click rate that described each candidate is thrown in to advertisement.
Chooser module 4043, throw in advertisement for the candidate who selects described ad click rate maximum and carry out advertisement putting.
The disclosed a kind of advertisement delivery system of the embodiment of the present invention, except utilizing above-mentioned each module, each submodule to realize the function of advertisement putting, can also be realized according to following composition structure the function of identical advertisement putting.
Described a kind of advertisement delivery system can comprise on line subsystem under subsystem and line.Wherein, on line, subsystem can comprise advertisement putting module 500 and clicking rate prediction module 502; Under line, subsystem can comprise clicking rate statistical module 504 and training module 506, as shown in Figure 5.And, in order to guarantee the real-time of clicking rate statistics, clicking rate statistical module 504 can also be arranged in subsystem on line.
Clicking rate statistical module 504 can be according to the clicking rate of historical each dimensional characteristics of advertisement putting record statistics, as certain advertisement of throwing on media A belongs to advertising sector B, the clicking rate that the eigenwert of its media dimension is media A, the clicking rate that the eigenwert of advertising sector dimension is advertising sector B.
Training module 506 can obtain the weight of the clicking rate of the weight of clicking rate of media A and advertising sector B.
As thrown in the advertisement of advertising sector B on media A, clicking rate prediction module 502 is calculated the clicking rate predicted value.
The clicking rate predicted value that advertisement putting module 500 can calculate according to clicking rate prediction module 502, the advertisement that can select current dispenser is sorted from big to small according to the clicking rate predicted value, selects the advertisement of clicking rate maximum and provides corresponding price according to predicted value.
In sum, the disclosed a kind of advertisement delivery system of the embodiment of the present invention, compare with background technology, has the following advantages:
Do not need to consider too much advertisement putting feature, only need to obtain clicking rate and the weight (each dimensional characteristics is less than the advertisement putting feature) of each dimensional characteristics, then utilize clicking rate and the weight calculation of each dimensional characteristics and shine upon to obtain final ad click rate, finally from each candidate, throw in advertisement and select high being thrown in of ad click rate.
Owing to not needing to consider too much advertisement putting feature, weakened the forecasting process of ad click rate, just reduced the calculated amount of advertisement releasing server, alleviated the processing pressure of advertisement releasing server, improved the response speed of advertisement releasing server.
And, count the clicking rate of each dimensional characteristics from historical advertisement putting daily record, and utilize regression model to calculate the weight of each dimensional characteristics, the ad click rate obtained according to the clicking rate of each dimensional characteristics and weight calculation mapping more accurately, more effective.
For system embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, relevant part gets final product referring to the part explanation of embodiment of the method.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is and the difference of other embodiment that between each embodiment, identical similar part is mutually referring to getting final product.
Above to the disclosed a kind of advertisement placement method of the embodiment of the present invention and system, be described in detail, applied specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment is just for helping to understand method of the present invention and core concept thereof; , for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention simultaneously.
Claims (10)
1. an advertisement placement method, is characterized in that, comprising:
Add up each candidate and throw in the historical clicking rate of each dimensional characteristics of advertisement, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics; Described each dimensional characteristics is less than the advertisement putting feature;
The weight of the historical clicking rate of described each dimensional characteristics and described each dimensional characteristics is carried out to the clicking rate prediction and calculation, obtain the clicking rate predicted value that described each candidate throws in advertisement;
The clicking rate predicted value that described each candidate is thrown in to advertisement is mapped as respectively described each candidate and throws in the ad click rate of advertisement, and carries out advertisement putting according to the ad click rate that described each candidate throws in advertisement.
2. method according to claim 1, is characterized in that, each candidate of described statistics throws in the historical clicking rate of each dimensional characteristics of advertisement, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics, comprising:
Count the historical clicking rate that described each candidate throws in each dimensional characteristics of advertisement from historical advertisement putting daily record;
The historical clicking rate of described each dimensional characteristics is obtained to the weight of described each dimensional characteristics according to the regression model training;
Wherein, described each dimensional characteristics comprises: media, advertising sector, advertisement position size, advertisement position position, adline and ad material;
According to the order of media, adline, advertisement position position, advertising sector, ad material, advertisement position size, described each dimensional characteristics reduces gradually on the impact of described ad click rate.
3. method according to claim 1, is characterized in that, the described weight by the historical clicking rate of described each dimensional characteristics and described each dimensional characteristics is carried out the clicking rate prediction and calculation, obtains the clicking rate predicted value that described each candidate throws in advertisement, comprising:
By
calculate the clicking rate predicted value that described each candidate throws in advertisement;
Wherein, x is described clicking rate predicted value, and bias is the deviation that the factor outside described each dimensional characteristics affects the clicking rate predicted value, the number that n is each dimensional characteristics, w
ibe the weight of i dimensional characteristics, ctr
iit is the historical clicking rate of i dimensional characteristics.
4. method according to claim 1, is characterized in that, the described clicking rate predicted value that described each candidate is thrown in to advertisement is mapped as respectively described each candidate and throws in the ad click rate of advertisement, comprising:
Described each candidate is thrown in to the clicking rate predicted value of advertisement and carry out linear regression calculating, obtain described each candidate and throw in the ad click rate of advertisement.
5. method according to claim 4, is characterized in that, the described clicking rate predicted value that described each candidate is thrown in to advertisement is carried out linear regression calculating, obtains described each candidate and throws in the ad click rate of advertisement, comprising:
Pass through y=ax
3+ bx
2+ cx+d calculates described each candidate and throws in the ad click rate of advertisement;
Wherein, y is described ad click rate, and x is described clicking rate predicted value, and a, b, c, d are regression coefficient.
6. method according to claim 1, is characterized in that, the described ad click rate of throwing in advertisement according to described each candidate carries out advertisement putting, comprising:
The ad click rate that described each candidate is thrown in to advertisement is arranged in order;
Select the candidate of described ad click rate maximum to throw in advertisement and carry out advertisement putting.
7. an advertisement delivery system, is characterized in that, comprising:
Dimensional characteristics information determination module, throw in the historical clicking rate of each dimensional characteristics of advertisement for adding up each candidate, and calculate the weight of each dimensional characteristics according to the historical clicking rate of described each dimensional characteristics; Described each dimensional characteristics is less than the advertisement putting feature;
Clicking rate predictor calculation module, carry out the clicking rate prediction and calculation for the weight of the historical clicking rate by described each dimensional characteristics and described each dimensional characteristics, obtains the clicking rate predicted value that described each candidate throws in advertisement;
The advertisement putting module, be mapped as respectively described each candidate for the clicking rate predicted value of described each candidate being thrown in to advertisement and throw in the ad click rate of advertisement, and carry out advertisement putting according to the ad click rate that described each candidate throws in advertisement.
8. system according to claim 7, is characterized in that, described dimensional characteristics information determination module comprises:
The statistics submodule, for counting from historical advertisement putting daily record the historical clicking rate that described each candidate throws in each dimensional characteristics of advertisement;
The training submodule, obtain the weight of described each dimensional characteristics according to the regression model training for the historical clicking rate by described each dimensional characteristics;
Wherein, described each dimensional characteristics comprises: media, advertising sector, advertisement position size, advertisement position position, adline and ad material;
According to the order of media, adline, advertisement position position, advertising sector, ad material, advertisement position size, described each dimensional characteristics reduces gradually on the impact of described ad click rate.
9. system according to claim 7, is characterized in that, described clicking rate predictor calculation module is passed through
calculate the clicking rate predicted value that described each candidate throws in advertisement;
Wherein, x is described clicking rate predicted value, and bias is the deviation that the factor outside described each dimensional characteristics affects the clicking rate predicted value, the number that n is each dimensional characteristics, w
ibe the weight of i dimensional characteristics, ctr
iit is the historical clicking rate of i dimensional characteristics.
10. system according to claim 7, is characterized in that, described advertisement putting module is passed through y=ax
3+ bx
2+ cx+d calculates described each candidate and throws in the ad click rate of advertisement;
Wherein, y is described ad click rate, and x is described clicking rate predicted value, and a, b, c, d are regression coefficient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103290919A CN103440584A (en) | 2013-07-31 | 2013-07-31 | Advertisement putting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103290919A CN103440584A (en) | 2013-07-31 | 2013-07-31 | Advertisement putting method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103440584A true CN103440584A (en) | 2013-12-11 |
Family
ID=49694276
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013103290919A Pending CN103440584A (en) | 2013-07-31 | 2013-07-31 | Advertisement putting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103440584A (en) |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761584A (en) * | 2014-01-10 | 2014-04-30 | 合一信息技术(北京)有限公司 | Method and system for carrying out information issue adjustment according to information resource hot spots |
CN104268644A (en) * | 2014-09-23 | 2015-01-07 | 新浪网技术(中国)有限公司 | Method and device for predicting click frequency of advertisement at advertising position |
CN104408644A (en) * | 2014-11-11 | 2015-03-11 | 北京百度网讯科技有限公司 | Method and device for controlling media object display and media object display system |
CN104484372A (en) * | 2014-12-04 | 2015-04-01 | 北京奇虎科技有限公司 | Detecting method and device of business object sending information |
CN104717210A (en) * | 2015-02-13 | 2015-06-17 | 北京集奥聚合科技有限公司 | Method and system for connecting optional media to DSP |
CN104951965A (en) * | 2015-06-26 | 2015-09-30 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method and device |
CN105183772A (en) * | 2015-08-07 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Release information click rate estimation method and apparatus |
CN105205116A (en) * | 2015-09-08 | 2015-12-30 | 百度在线网络技术(北京)有限公司 | Information publishing method and device |
CN105227331A (en) * | 2015-10-16 | 2016-01-06 | 上海晶赞科技发展有限公司 | Information sending control method and device |
CN105260913A (en) * | 2015-10-16 | 2016-01-20 | 上海晶赞科技发展有限公司 | CTR estimation method and system, and DSP server used for Internet advertisement putting |
CN105306230A (en) * | 2015-10-16 | 2016-02-03 | 上海晶赞科技发展有限公司 | Information transmission control method and device |
CN105809487A (en) * | 2016-03-17 | 2016-07-27 | 广州筷子信息科技有限公司 | Advertisement element based advertisement release method and apparatus |
CN105825400A (en) * | 2016-03-16 | 2016-08-03 | 合网络技术(北京)有限公司 | Advertisement material quality measuring method and system |
CN106504011A (en) * | 2015-09-06 | 2017-03-15 | 阿里巴巴集团控股有限公司 | A kind of methods of exhibiting of business object and device |
CN106600303A (en) * | 2015-10-20 | 2017-04-26 | 北京国双科技有限公司 | Method and device for assessment of advertisement putting rationality |
CN106875201A (en) * | 2015-12-11 | 2017-06-20 | 北京国双科技有限公司 | The acquisition methods and device of the visible factor of advertisement |
CN106897892A (en) * | 2015-12-18 | 2017-06-27 | 北京奇虎科技有限公司 | Advertisement placement method and device |
CN108122122A (en) * | 2016-11-29 | 2018-06-05 | 腾讯科技(深圳)有限公司 | Advertisement placement method and system |
CN108154377A (en) * | 2016-12-06 | 2018-06-12 | 北京国双科技有限公司 | Advertisement cheating Forecasting Methodology and device |
CN108256893A (en) * | 2016-12-29 | 2018-07-06 | 北京国双科技有限公司 | The analysis method and device of advertisement delivery effect |
CN108269114A (en) * | 2016-12-30 | 2018-07-10 | 深圳市优朋普乐传媒发展有限公司 | A kind of determining method and device of advertisement inventory |
CN108733847A (en) * | 2018-06-14 | 2018-11-02 | 湖南数魔网络科技有限公司 | A kind of recommendation method of internet hunt advertisement keywords |
CN108769167A (en) * | 2018-05-17 | 2018-11-06 | 北京奇艺世纪科技有限公司 | A kind of the push distribution method and device of business datum |
CN108776907A (en) * | 2018-05-31 | 2018-11-09 | 康键信息技术(深圳)有限公司 | Advertisement intelligent recommends method, server and storage medium |
CN109716379A (en) * | 2016-07-20 | 2019-05-03 | 深圳市东信时代信息技术有限公司 | Optimization method, device and the media advertising system of media advertisement clicking rate |
CN109858942A (en) * | 2018-11-06 | 2019-06-07 | 北京奇虎科技有限公司 | Promotion message methods of exhibiting, device, electronic equipment and readable storage medium storing program for executing |
CN110288377A (en) * | 2019-05-24 | 2019-09-27 | 北京派瑞威行互联技术有限公司 | Optimization method and device, storage medium and electronic device are launched in advertisement |
CN110533479A (en) * | 2019-09-04 | 2019-12-03 | 北京深演智能科技股份有限公司 | A kind of mark distributing method, device and electronic equipment |
CN111160983A (en) * | 2019-12-31 | 2020-05-15 | 众安在线财产保险股份有限公司 | Advertisement putting effect evaluation method and device, computer equipment and storage medium |
CN111754287A (en) * | 2020-02-14 | 2020-10-09 | 北京沃东天骏信息技术有限公司 | Article screening method, apparatus, device and storage medium |
CN111967901A (en) * | 2020-07-31 | 2020-11-20 | 深圳市彬讯科技有限公司 | Advertisement merchant sequencing method and device, computer equipment and storage medium |
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 |
CN112348602A (en) * | 2021-01-07 | 2021-02-09 | 浙江争游网络科技有限公司 | Automatic advertisement putting management system based on big data |
CN112348564A (en) * | 2020-09-27 | 2021-02-09 | 北京淇瑀信息科技有限公司 | Method and device for automatically managing advertisement delivery and electronic equipment |
CN112396473A (en) * | 2020-12-23 | 2021-02-23 | 上海苍苔信息技术有限公司 | CPM system and method for improving CTR value |
CN112990967A (en) * | 2021-03-09 | 2021-06-18 | 广州筷子信息科技有限公司 | Advertisement creative analysis method and system |
CN113724016A (en) * | 2021-09-09 | 2021-11-30 | 北京有竹居网络技术有限公司 | Method, device, medium and equipment for acquiring attention degree of multimedia resource |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090070424A (en) * | 2007-12-27 | 2009-07-01 | (주) 디엔에이소프트 | Internet advertising billing system and method thereof |
CN102592235A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertisement serving system |
-
2013
- 2013-07-31 CN CN2013103290919A patent/CN103440584A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090070424A (en) * | 2007-12-27 | 2009-07-01 | (주) 디엔에이소프트 | Internet advertising billing system and method thereof |
CN102592235A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertisement serving system |
Non-Patent Citations (2)
Title |
---|
付凌晖 等: "多项式回归的建模方法比较研究", 《数理统计与管理》, vol. 23, no. 1, 30 November 2004 (2004-11-30) * |
纪文迪 等: "广告点击率估算技术综述", 《华东师范大学学报(自然科学版)》, no. 3, 31 May 2013 (2013-05-31) * |
Cited By (48)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761584A (en) * | 2014-01-10 | 2014-04-30 | 合一信息技术(北京)有限公司 | Method and system for carrying out information issue adjustment according to information resource hot spots |
CN103761584B (en) * | 2014-01-10 | 2017-05-24 | 合一信息技术(北京)有限公司 | Method and system for carrying out information issue adjustment according to information resource hot spots |
CN104268644A (en) * | 2014-09-23 | 2015-01-07 | 新浪网技术(中国)有限公司 | Method and device for predicting click frequency of advertisement at advertising position |
CN104408644A (en) * | 2014-11-11 | 2015-03-11 | 北京百度网讯科技有限公司 | Method and device for controlling media object display and media object display system |
CN104484372A (en) * | 2014-12-04 | 2015-04-01 | 北京奇虎科技有限公司 | Detecting method and device of business object sending information |
CN104717210A (en) * | 2015-02-13 | 2015-06-17 | 北京集奥聚合科技有限公司 | Method and system for connecting optional media to DSP |
CN104717210B (en) * | 2015-02-13 | 2018-06-26 | 北京集奥聚合科技有限公司 | A kind of method and system by free media access DSP |
CN104951965A (en) * | 2015-06-26 | 2015-09-30 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method and device |
CN105183772A (en) * | 2015-08-07 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Release information click rate estimation method and apparatus |
CN106504011B (en) * | 2015-09-06 | 2019-11-05 | 阿里巴巴集团控股有限公司 | A kind of methods of exhibiting and device of business object |
CN106504011A (en) * | 2015-09-06 | 2017-03-15 | 阿里巴巴集团控股有限公司 | A kind of methods of exhibiting of business object and device |
CN105205116A (en) * | 2015-09-08 | 2015-12-30 | 百度在线网络技术(北京)有限公司 | Information publishing method and device |
CN105227331A (en) * | 2015-10-16 | 2016-01-06 | 上海晶赞科技发展有限公司 | Information sending control method and device |
CN105260913A (en) * | 2015-10-16 | 2016-01-20 | 上海晶赞科技发展有限公司 | CTR estimation method and system, and DSP server used for Internet advertisement putting |
CN105306230A (en) * | 2015-10-16 | 2016-02-03 | 上海晶赞科技发展有限公司 | Information transmission control method and device |
CN105227331B (en) * | 2015-10-16 | 2018-10-30 | 上海晶赞科技发展有限公司 | information sending control method and device |
CN105306230B (en) * | 2015-10-16 | 2018-09-11 | 上海晶赞科技发展有限公司 | information sending control method and device |
CN106600303A (en) * | 2015-10-20 | 2017-04-26 | 北京国双科技有限公司 | Method and device for assessment of advertisement putting rationality |
CN106875201A (en) * | 2015-12-11 | 2017-06-20 | 北京国双科技有限公司 | The acquisition methods and device of the visible factor of advertisement |
CN106897892A (en) * | 2015-12-18 | 2017-06-27 | 北京奇虎科技有限公司 | Advertisement placement method and device |
CN105825400A (en) * | 2016-03-16 | 2016-08-03 | 合网络技术(北京)有限公司 | Advertisement material quality measuring method and system |
CN105809487A (en) * | 2016-03-17 | 2016-07-27 | 广州筷子信息科技有限公司 | Advertisement element based advertisement release method and apparatus |
CN109716379A (en) * | 2016-07-20 | 2019-05-03 | 深圳市东信时代信息技术有限公司 | Optimization method, device and the media advertising system of media advertisement clicking rate |
CN108122122A (en) * | 2016-11-29 | 2018-06-05 | 腾讯科技(深圳)有限公司 | Advertisement placement method and system |
CN108154377A (en) * | 2016-12-06 | 2018-06-12 | 北京国双科技有限公司 | Advertisement cheating Forecasting Methodology and device |
CN108154377B (en) * | 2016-12-06 | 2022-03-15 | 北京国双科技有限公司 | Advertisement cheating prediction method and device |
CN108256893A (en) * | 2016-12-29 | 2018-07-06 | 北京国双科技有限公司 | The analysis method and device of advertisement delivery effect |
CN108269114A (en) * | 2016-12-30 | 2018-07-10 | 深圳市优朋普乐传媒发展有限公司 | A kind of determining method and device of advertisement inventory |
CN108769167A (en) * | 2018-05-17 | 2018-11-06 | 北京奇艺世纪科技有限公司 | A kind of the push distribution method and device of business datum |
CN108776907A (en) * | 2018-05-31 | 2018-11-09 | 康键信息技术(深圳)有限公司 | Advertisement intelligent recommends method, server and storage medium |
CN108733847A (en) * | 2018-06-14 | 2018-11-02 | 湖南数魔网络科技有限公司 | A kind of recommendation method of internet hunt advertisement keywords |
CN109858942A (en) * | 2018-11-06 | 2019-06-07 | 北京奇虎科技有限公司 | Promotion message methods of exhibiting, device, electronic equipment and readable storage medium storing program for executing |
CN109858942B (en) * | 2018-11-06 | 2023-12-15 | 三六零科技集团有限公司 | Popularization information display method and device, electronic equipment and readable storage medium |
CN110288377A (en) * | 2019-05-24 | 2019-09-27 | 北京派瑞威行互联技术有限公司 | Optimization method and device, storage medium and electronic device are launched in advertisement |
CN110533479A (en) * | 2019-09-04 | 2019-12-03 | 北京深演智能科技股份有限公司 | A kind of mark distributing method, device and electronic equipment |
CN110533479B (en) * | 2019-09-04 | 2020-11-06 | 北京深演智能科技股份有限公司 | Identification distribution method and device and electronic equipment |
CN111160983A (en) * | 2019-12-31 | 2020-05-15 | 众安在线财产保险股份有限公司 | Advertisement putting effect evaluation method and device, computer equipment and storage medium |
CN111754287A (en) * | 2020-02-14 | 2020-10-09 | 北京沃东天骏信息技术有限公司 | Article screening method, apparatus, device and storage medium |
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 |
CN111967901A (en) * | 2020-07-31 | 2020-11-20 | 深圳市彬讯科技有限公司 | Advertisement merchant sequencing method and device, computer equipment and storage medium |
CN111967901B (en) * | 2020-07-31 | 2023-08-11 | 深圳市彬讯科技有限公司 | Advertisement merchant ordering method, advertisement merchant ordering device, computer equipment and storage medium |
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 |
CN112348564A (en) * | 2020-09-27 | 2021-02-09 | 北京淇瑀信息科技有限公司 | Method and device for automatically managing advertisement delivery and electronic equipment |
CN112396473A (en) * | 2020-12-23 | 2021-02-23 | 上海苍苔信息技术有限公司 | CPM system and method for improving CTR value |
CN112348602A (en) * | 2021-01-07 | 2021-02-09 | 浙江争游网络科技有限公司 | Automatic advertisement putting management system based on big data |
CN112348602B (en) * | 2021-01-07 | 2021-04-06 | 浙江争游网络科技有限公司 | Automatic advertisement putting management system based on big data |
CN112990967A (en) * | 2021-03-09 | 2021-06-18 | 广州筷子信息科技有限公司 | Advertisement creative analysis method and system |
CN113724016A (en) * | 2021-09-09 | 2021-11-30 | 北京有竹居网络技术有限公司 | Method, device, medium and equipment for acquiring attention degree of multimedia resource |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103440584A (en) | Advertisement putting method and system | |
US9846884B2 (en) | Click conversion score | |
CN103914468B (en) | A kind of method and apparatus of impression information search | |
US9767479B2 (en) | System and method for deploying ads based on a content exposure interval | |
US20130332264A1 (en) | Method and system for determining touchpoint attribution | |
KR20160096122A (en) | Methods and systems for creating a data-driven attribution model for assigning attribution credit to a plurality of events | |
US20170061515A1 (en) | Systems and methods for setting allocations and prices for content in an online marketplace | |
CN106156878A (en) | Ad click rate antidote and device | |
CN104268644A (en) | Method and device for predicting click frequency of advertisement at advertising position | |
CN102929959A (en) | Book recommendation method based on user actions | |
CN106407210A (en) | Display method and device of business object | |
CN106504011A (en) | A kind of methods of exhibiting of business object and device | |
WO2009021445A1 (en) | Method and device for managing advertisement | |
CN110020173A (en) | Method, apparatus and electronic equipment for Optimizing Search sequence | |
CN105260913A (en) | CTR estimation method and system, and DSP server used for Internet advertisement putting | |
US20140122253A1 (en) | Systems and methods for implementing bid adjustments in an online advertisement exchange | |
CN106447386A (en) | Network advertisement examination method and system | |
US9558506B2 (en) | System and method for exploring new sponsored search listings of uncertain quality | |
JP2012507779A (en) | Auction method and system using bid price according to period and fixed unit price associated with click and exposure, advertisement providing method and system, and charging method and system | |
CN107958353A (en) | A kind of ETC networking quantity of operation evaluation methods and computer-readable storage medium | |
CN103020081B (en) | Keyword method and system is thrown in outside standing | |
KR20200113370A (en) | How to Implement a Sales Forecasting System on the Broadcast of YouTube Creators for Sale of Goods | |
TW201709124A (en) | Method and Apparatus for Information Presentation Based on Service Object | |
US20170178248A1 (en) | Classification Structure and Uses Thereof | |
CN104731819A (en) | Advertisement keyword extraction method and advertisement keyword extraction device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131211 |
|
RJ01 | Rejection of invention patent application after publication |