CN108269123A - Control method and device are launched in advertisement - Google Patents

Control method and device are launched in advertisement Download PDF

Info

Publication number
CN108269123A
CN108269123A CN201711480482.5A CN201711480482A CN108269123A CN 108269123 A CN108269123 A CN 108269123A CN 201711480482 A CN201711480482 A CN 201711480482A CN 108269123 A CN108269123 A CN 108269123A
Authority
CN
China
Prior art keywords
advertisement
account
consumption
predetermined time
plan
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.)
Granted
Application number
CN201711480482.5A
Other languages
Chinese (zh)
Other versions
CN108269123B (en
Inventor
张�雄
王浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba China Co Ltd
Original Assignee
Guangdong Shenma Search Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Shenma Search Technology Co Ltd filed Critical Guangdong Shenma Search Technology Co Ltd
Priority to CN201711480482.5A priority Critical patent/CN108269123B/en
Publication of CN108269123A publication Critical patent/CN108269123A/en
Application granted granted Critical
Publication of CN108269123B publication Critical patent/CN108269123B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0273Determination of fees for advertising
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0277Online advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention provides a kind of advertisement and launches control method and device.Method provided by the invention passes through when launching advertisement according to search key, the consumption information such as budget information and plan actual consumption expense, account actual consumption expense and account balance by obtaining each advertisement to be put in real time, periodically according to the budget information and consumption information, the advertisement filter to be put of budgetary shortfall is fallen, the loss caused by advertiser's pre-mature exhaustion budget of budgetary shortfall causes largely to search for and lose when advertisement is launched can be reduced, and the click-through-rate for launching advertisement entirety can be improved, so that advertisement delivery effect is more preferable.

Description

Control method and device are launched in advertisement
Technical field
Technical field is launched the present invention relates to advertisement more particularly to control method and device are launched in a kind of advertisement.
Background technology
The web advertisement is also referred to as Internet advertising, refers to utilize the side such as ad banner, text link, multimedia on website Method, in internet, publication or releasing advertisements, a kind of high-tech advertising campaign mode of Internet user is transmitted to by network.With It traditional four big communications media (newspaper, magazine, TV, broadcast) advertisement and receives the outdoor advertising shown appreciation for somebody recently and compares, network Advertisement has advantageous advantage, is the important part for implementing Modern Marketing media strategy.
In keyword search advertisement, the comprehensive value of a showing advertisement can be described as platform income, advertiser Profit, the summation of user satisfaction.Wherein, the sum of platform income and advertisement primary benefit are the social benefit calculated in advertising (Efficiency).In current advertisement serving policy, advertiser is one keyword of advertisement selection first, and is the keyword One bid is provided.When the Keywords matching of searching keyword and advertiser selection that user submits, then above-mentioned matched ginseng It is auctioned online with the multiple advertisements bidded, evaluates highest advertisement and be devoted on the advertisement position of result of page searching.
In current advertisement serving policy, due to the budget limit of advertiser, advertiser's pre-mature exhaustion of budgetary shortfall is pre- It calculates, largely search can be caused to lose advertisement dispensing, brought about great losses, and dispensing ad click rate is relatively low, advertisement delivery effect Difference.
Invention content
The present invention provides a kind of advertisement and launches control method and device, to solve in current advertisement serving policy, by In the budget limit of advertiser, advertiser's pre-mature exhaustion budget of budgetary shortfall can cause largely search to lose advertisement dispensing, make Into massive losses, and launch the problem of ad click rate is relatively low, and advertisement delivery effect is poor.
It is an aspect of the invention to provide a kind of advertisements to launch control method, including:
Obtain the budget of at least one advertisement to be put to match with search key and each advertisement to be put Information, the budget information include at least:Plan whole day budget and account whole day budget;
The consumption information of each advertisement to be put is obtained in real time, and the consumption information includes at least:Plan actual consumption Expense, account actual consumption expense and account balance;
Periodically according to the budget information and consumption information, each advertisement to be put is filtered.
Another aspect of the present invention is to provide a kind of advertisement and launches control device, including:
First acquisition module, for obtaining at least one advertisement to be put to match with search key and each institute The budget information of advertisement to be put is stated, the budget information includes at least:Plan whole day budget and account whole day budget;
Second acquisition module, for obtaining the consumption information of each advertisement to be put in real time, the consumption information is at least Including:Plan actual consumption expense, account actual consumption expense and account balance;
Processing module, for periodically according to the budget information and consumption information, to each advertisement to be put into Row filtering.
Control method and device are launched in advertisement provided by the invention, by when launching advertisement according to search key, leading to After budget information and plan actual consumption expense, the account actual consumption expense and account for obtaining each advertisement to be put in real time The consumption information such as remaining sum, periodically according to the budget information and consumption information, to the advertisement filter to be put of budgetary shortfall Fall, it is possible to reduce the damage caused by advertiser's pre-mature exhaustion budget of budgetary shortfall causes largely to search for and lose when advertisement is launched It loses, and the click-through-rate for launching advertisement entirety can be improved, so that advertisement delivery effect is more preferable.
Description of the drawings
Attached drawing herein is incorporated into specification and forms the part of this specification, shows the implementation for meeting the present invention Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is that control method flow chart is launched in the advertisement that the embodiment of the present invention one provides;
Fig. 2 launches control method flow chart for advertisement provided by Embodiment 2 of the present invention;
Fig. 3 is that control method flow chart is launched in the advertisement that the embodiment of the present invention three provides;
Fig. 4 is the structure diagram that control device is launched in the advertisement that the embodiment of the present invention four provides.
Pass through above-mentioned attached drawing, it has been shown that the specific embodiment of the present invention will be hereinafter described in more detail.These attached drawings It is not intended to limit the range of present inventive concept by any mode with word description, but is by reference to specific embodiment Those skilled in the art illustrate idea of the invention.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, example is illustrated in the accompanying drawings.Following description is related to During attached drawing, unless otherwise indicated, the same numbers in different attached drawings represent the same or similar 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 device and method of some aspects being described in detail in claims, of the invention.
Noun according to the present invention is explained first:
Advertiser:Refer to the publisher of advertising campaign, be to sell or publicize oneself production in distribution platform (such as on website) Product and the businessman of service are the suppliers of Alliance marketing advertisement.It is any to promote, sell its product or the businessman of service and make For advertiser.Advertiser's releasing advertisements activity, and according to the total of marketing effectiveness specified in the advertising campaign of distribution platform completion Quantity and unit effect price pay expense to distribution platform.
Click-through-rate (Click-Through-Rate, abbreviation CTR):It is the common term of Internet advertising, refers to dispensing The click arrival rate of advertisement (display advertising, copy, AdWords, arranging advertisement or video ads etc.), i.e., this is wide The actual click number (can be the quantity for reaching target pages for stringent) of announcement divided by the amount of showing of advertisement.CTR is weighing apparatus Measure an important indicator of Internet advertising effect.
Quality degree:Refer to the discreet value of CTR.
Show cost (Cost Per Mile, abbreviation CMP) thousand times:Refer to not be presented to flower needed for 1,000 people for advertisement The cost taken, this is the consistent citation form for weighing showing advertisement effect.
It breasts the tape:Refer to due to being provided with daily budget, the promotion message of client did not had also complete just offline in advance at one day Situation, in the present embodiment, advertiser is provided with daily budget, and breasting the tape refers to that advertiser also at one day and complete just do not consume in advance The situation of the budget of whole day.
In addition, term " first ", " second " etc. are only used for description purpose, and it is not intended that indicating or implying relatively important Property or the implicit quantity for indicating indicated technical characteristic.In the description of following embodiment, " multiple " are meant that two More than a, unless otherwise specifically defined.
These specific embodiments can be combined with each other below, may be at certain for the same or similar concept or process It is repeated no more in a little embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Embodiment one
The dispensing of usual advertisement is an On-line matching (Online Matching) problem, and side is preset more A candidate locations, side are uncertain search keys input by user, and the task that advertisement is launched is exactly to close these search Keyword is matched with efficiency as high as possible with candidate locations.Under business situation, the problem of On-line matching usually in face of it is following about Beam:Advertiser budget is with launching orientation limitation.In the case that advertiser budget is limited, advertisement can only be launched on part searches, At this point, the dispensing orientation limitation of advertiser will result in business flow loss.For example, advertiser 1 has launched the advertisement of whole day, extensively Accuse main 2 advertisements for having launched the morning.If advertisement 1 occupies whole ad placement in the morning and has used up whole pre- It calculates, then the search in 1 afternoon of advertiser can just be thrown without advertisement, so as to cause the loss in revenue of advertisement launching platform.In order to avoid Such case for the advertiser for having risk of breasting the tape, needs to reduce its advertisement dispensing in advance, that is, carries out budget control.
Fig. 1 is that control method flow chart is launched in the advertisement that the embodiment of the present invention one provides.The embodiment of the present invention is for current Advertisement serving policy in, due to the budget limit of advertiser, advertiser's pre-mature exhaustion budget of budgetary shortfall can cause a large amount of Search loses advertisement dispensing, brings about great losses, and launches the problem of ad click rate is relatively low, and advertisement delivery effect is poor, provides Control method is launched in advertisement.Such as Fig. 1, this method is as follows:
Step S101, at least one advertisement to be put and each advertisement to be put that acquisition and search key match Budget information.
Wherein, the budget information of advertisement to be put includes at least:Plan whole day budget and account whole day budget;Account whole day Its preset one day budget of account of advertiser of the advertisement to be put at last in advance;It is that advertiser is advance in advance to plan whole day The advertising plan budget of one day belonging to the advertisement to be put of setting.
In the present embodiment, each advertiser gathers around that there are one independent for paying the account of all kinds of advertising expenditures;It is each wide One or more advertisement dispensing plan (abbreviation advertising plan) can be specified by accusing master, and an advertising plan can include to one Or the dispensing plan of multiple advertisements.Namely each advertiser corresponds to an account, and an account corresponds to one or more Advertising plan, an advertising plan correspond to one or more advertisement.Advertiser can set the account budget of one day in advance, each The advertising plan budget of one day;Advertiser can pre-deposit the certain amount of money of account, and the amount of money being actually stored in needs not be equal to pre- It calculates.
In addition, the industry according to involved by ad content, can classify to advertisement, mutually advertisement of the same trade cluster arrives In same industry classification.For once searching for, same row is belonged to all advertisements to be put that search key matches Industry.
After search key input by user is detected, can obtain one matched with the search key or Multiple advertisements to be put are subsequently launched control method progress advertisement dispensing according to advertisement provided by the invention and are showed.
Step S102, the consumption information of each advertisement to be put is obtained in real time, and consumption information includes at least:Plan actual consumption Expense, account actual consumption expense and account balance.
Wherein, plan actual consumption expense of the advertisement to be put at current time refers to the advertisement meter belonging to advertisement to be put The initial time on the day of is drawn to the actual consumption expense at current time;Advertisement to be put is in the account actual consumption at current time Expense refers to initial time of the corresponding account of advertisement to be put on the day of to the actual consumption expense at current time;It is to be put wide Accuse the real surplus gold at the current time that the account balance at current time refers in the corresponding account of advertisement to be put on the day of Volume.
In addition, in the step, consumption information of each advertisement to be put at each moment can be obtained in real time, and deposited Storage, for subsequently using when, read.
Step S103, periodically each advertisement to be put is filtered according to budget information and consumption information.
In the present embodiment, each advertisement to be put can be calculated current periodically according to budget information and consumption information The plan quality degree threshold value in period and account matter metric threshold;According to plan quality degree threshold value and account matter metric threshold to each Advertisement to be put is filtered.
In the present embodiment, at the time of being denoted as 0~T by one day, one day initial time was 0 moment, when a finish time is T It carves.
Predetermined time can be any moment in current period, for example, it may be the initial time of current period, end Moment etc..The predetermined time is denoted as t moment, t ∈ [0, T], the t moment that the present embodiment is subsequently mentioned is each meant in the step Predetermined time.
The embodiment of the present invention by according to search key launch advertisement when, by obtaining each advertisement to be put in real time The consumption information such as budget information and plan actual consumption expense, account actual consumption expense and account balance, periodically basis Budget information and consumption information fall the advertisement filter to be put of budgetary shortfall, it is possible to reduce because of advertiser's mistake of budgetary shortfall Early exhaust budget cause largely search for lose advertisement launch and caused by loss, and can improve launch advertisement entirety click lead to Rate is crossed, so that advertisement delivery effect is more preferable.
Embodiment two
Fig. 2 launches control method flow chart for advertisement provided by Embodiment 2 of the present invention.On the basis of above-described embodiment one On, in the present embodiment, according to budget information and consumption information, each advertisement to be put is filtered, including:According to budget information And consumption information, each advertisement to be put is calculated in the plan quality degree threshold value of current period and account matter metric threshold;According to each Advertisement to be put is filtered each advertisement to be put in the plan quality degree threshold value of current period and account matter metric threshold. As shown in Fig. 2, this method is as follows:
Step S201, at least one advertisement to be put and each advertisement to be put that acquisition and search key match Budget information.
Wherein, the budget information of advertisement to be put includes at least:Plan whole day budget and account whole day budget;Account whole day Its preset one day budget of account of advertiser of the advertisement to be put at last in advance;It is that advertiser is advance in advance to plan whole day The advertising plan budget of one day belonging to the advertisement to be put of setting.
In the present embodiment, each advertiser gathers around that there are one independent for paying the account of all kinds of advertising expenditures;It is each wide One or more advertisement dispensing plan (abbreviation advertising plan) can be specified by accusing master, and an advertising plan can include to one Or the dispensing plan of multiple advertisements.Namely each advertiser corresponds to an account, and an account corresponds to one or more Advertising plan, an advertising plan correspond to one or more advertisement.Advertiser can set the account budget of one day in advance, each The advertising plan budget of one day;Advertiser can pre-deposit the certain amount of money of account, and the amount of money being actually stored in needs not be equal to pre- It calculates.
In addition, the industry according to involved by ad content, can classify to advertisement, mutually advertisement of the same trade cluster arrives In same industry classification.For once searching for, same row is belonged to all advertisements to be put that search key matches Industry.
After search key input by user is detected, can obtain one matched with the search key or Multiple advertisements to be put are subsequently launched control method progress advertisement dispensing according to advertisement provided by the invention and are showed.
Step S202, the consumption information of each advertisement to be put is obtained in real time, and consumption information includes at least:Plan actual consumption Expense, account actual consumption expense and account balance.
The realization method of the step is identical with above-mentioned steps S102, and details are not described herein again for the present embodiment.
In the present embodiment, consumption information of each advertisement to be put at each moment can be obtained in real time, and stored;Afterwards Continue periodically by step S203-S208, the process launched to advertisement optimizes.
Step S203, the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put is obtained.
In the present embodiment, at the time of being denoted as 0~T by one day, one day initial time was 0 moment, when a finish time is T It carves.
Wherein, predetermined time can be any moment in current period, for example, it may be during the starting of current period Quarter, finish time etc..The predetermined time is denoted as t moment, t ∈ [0, T], the t moment that the present embodiment is subsequently mentioned each means this Predetermined time in step.
In the step, for industry I, C (I, the t belonging to each advertisement to be put1,t2) advertisement that represents to launch in industry I exists The t of one day1Moment is to t2The expense consumed between moment, it may also be said to be [t of the advertisement launched in industry I at one day1, t2] the period interior expense consumed.
The industry cumulative consumption distribution of the corresponding t moment of each advertisement to be put in the step, that is, advertisement to be put The expense that the advertisement launched in affiliated industry I is consumed within [0, the t] period of one day accounts for the ratio of whole day consumption costs, The distribution of industry cumulative consumption can use F (I, 0, t) to represent, it is clear that F (I, 0, T)=1.
Specifically, the industry cumulative consumption distribution F (I, 0, t) of the corresponding t moment of each advertisement to be put in the step, can With the historical data in the preset time period of the industry I according to belonging to advertisement to be put, it is calculated by the following formula one:
Wherein, C (I, 0, t) is the advertisement launched in industry I in [0, t] the period interior expense consumed of one day, C (I, 0, T) is the expense that the advertisement launched in industry I is consumed in one day.
After step S203 gets the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put, lead to Step S204-S205 is crossed, according to budget information and consumption information, calculates plan quality degree of each advertisement to be put in current period Threshold value.It can be realized according to budget information and consumption information by step S206-S207, calculate each advertisement to be put in current week The account matter metric threshold of phase.
In addition, efficiency is launched in order to improve advertisement, it is special that rts_log_server servers, rts_log_server are set Server reads advertisement primary account number, the real-time incremental consumption data planned from message queue, and is cached.rts_log_ It is updated again in preset database, and empty caching after the periodically cumulative upper incremental data cached of server servers.If Ad_server servers are put, ad_server servers extract the budgets such as advertisement main account, plan letter from preset database Breath, and it is supplied to root_server servers.Root_server servers can be come by sending out request to rts_server The consumption information in presetting database is obtained, and the filtering of advertisement to be put is completed according to the budget information and consumption information of acquisition And dispensing.
Step S204, it is distributed according to the corresponding industry cumulative consumption at each advertising presupposition moment to be put and respectively waits to throw The plan whole day budget of advertisement is put, calculates plan estimated consumption costs of each advertisement to be put in predetermined time.
In the present embodiment, plan estimated consumption costs of each advertisement to be put in t moment, step tool are represented with E (P, t) Body can in the following way be realized by formula two:
Wherein, B (P) is the plan whole day budget of each advertisement to be put, that is to say that the plan P belonging to each advertisement to be put exists The budget of same day whole day;T1Represent effective initial time of plan P, T2Represent effective finish time of plan P.
Step S205, consumption costs is expected according to plan of each advertisement to be put in predetermined time, each advertisement to be put exists The plan actual consumption expense of predetermined time, pre-designed cancellation consumption increment size and the plan quality degree threshold value in a upper period, meter Calculate plan quality degree threshold value of each advertisement to be put in current period.
Wherein, advertisement to be put refers to the advertising plan belonging to advertisement to be put in the plan quality degree threshold value of current period The matter metric threshold of t moment in current period, advertising plan of the plan quality degree threshold value belonging to advertisement to be put is in t The minimum value of quality degree that moment must reach.In the present embodiment, advertisement to be put is treated in the plan quality degree threshold value of t moment Advertisement is launched in the plan quality degree threshold value of the t moment of current period, advertisement to be put is in the meter of the predetermined time of current period Matter metric threshold is drawn as the meaning that the plan quality degree threshold value of advertisement current period to be put represents.
In the present embodiment, when each advertisement to be put is pre- more than the plan in t moment in the plan actual consumption expense of t moment Consumption costs is counted, then needs to promote plan quality degree threshold value;When each advertisement to be put is small in the plan actual consumption expense of t moment In or equal to t moment the estimated consumption costs of plan, then need to reduce plan quality degree threshold value, with by according to respectively waiting to throw Plan quality degree threshold value of the advertisement in current period is put, each advertisement to be put is filtered, so as to reduce because of budgetary shortfall Advertiser's pre-mature exhaustion budget cause largely search for lose advertisement launch and caused by loss.
Specifically, the plan quality degree threshold value of each advertisement current period to be put can be calculated by formula three:
Wherein, Thr (P, t) represents plan quality degree threshold value of each advertisement to be put in current period;Thr (P, t-1) table Showed plan quality degree threshold value of each advertisement to be put within a upper period;Δ P represents pre-designed cancellation consumption increment size;C (P, t) table Show plan actual consumption expense of each advertisement to be put in t moment;E (P, t) represents that each advertisement to be put is pre- in the plan of t moment Count consumption costs.Wherein, the value of Δ P can according to actual needs be set by technical staff.
In addition, for plan quality degree threshold value in intraday a cycle, Thr (P, 0) that is to say, it can be by technology Personnel are set according to actual needs, can also continue the plan quality degree threshold value in the last one period of the previous day.
Optionally, the variation step-length of plan quality degree threshold value, that is to say Δ P, influence whether the degree of fluctuation and receipts of algorithm Hold back speed, it is preferable that Δ P can be set as 0.1%.The bound section too conference of Δ P causes budget control strategy wide Reflect and slows down after accusing main change budget, thus the bound section of Δ P cannot too greatly, it is alternatively possible to set Δ P Value in [0%, 15%].
Above-mentioned steps S203-S205 is according to budget information and consumption information, calculates each advertisement to be put in current period Plan quality degree threshold value a kind of realization method.
Step S206, it is distributed according to the corresponding industry cumulative consumption at each advertising presupposition moment to be put and respectively waits to throw The account whole day budget of advertisement is put, calculates first account estimated consumption costs of each advertisement to be put in predetermined time.
In the present embodiment, first account estimated consumption costs of each advertisement to be put in t moment, the step are represented with E (U, t) Suddenly it specifically can in the following way be realized by formula four:
Wherein, B (U) is the account whole day budget of each advertisement to be put, that is to say that the corresponding account U of each advertisement to be put exists The budget of same day whole day.F (I, 0, t), F (I, 0, t) represent equivalent in meaning with front, and details are not described herein again.
Step S207, consumption costs is expected in the first account of predetermined time according to each advertisement to be put, it is each to be put wide The account actual consumption expense in predetermined time is accused, preset account consumption increment size and the account quality degree threshold in a upper period Value calculates account matter metric threshold of each advertisement to be put in current period.
Wherein, advertisement to be put refers to that the corresponding account of advertisement to be put is being worked as in the account matter metric threshold of current period The matter metric threshold of t moment in the preceding period, account matter metric threshold are necessary in t moment for the corresponding account of advertisement to be put The minimum value of quality degree reached.In the present embodiment, advertisement to be put is in the account matter metric threshold of t moment, advertisement to be put In the account matter metric threshold of the t moment of current period, advertisement to be put is in the account quality degree of the predetermined time of current period Threshold value, advertisement to be put predetermined time account matter metric threshold, with the account quality degree of advertisement current period to be put The meaning that threshold value represents is the same.
In the present embodiment, when each advertisement to be put is pre- more than the account in t moment in the account actual consumption expense of t moment Consumption costs is counted, then needs to promote account matter metric threshold;When each advertisement to be put is small in the account actual consumption expense of t moment In or equal to t moment the estimated consumption costs of account, then need to reduce account matter metric threshold, with by according to respectively waiting to throw Account matter metric threshold of the advertisement in current period is put, each advertisement to be put is filtered, so as to reduce because of budgetary shortfall Advertiser's pre-mature exhaustion budget cause largely search for lose advertisement launch and caused by loss.
Specifically, in the step, account quality degree of each advertisement to be put in current period can be calculated by formula five Threshold value:
Wherein, Thr (U, t) represents account matter metric threshold of each advertisement to be put in current period;Thr(U,t-1) Represented account matter metric threshold of each advertisement to be put within a upper period;Δ U represents pre-designed cancellation consumption increment size;C(P,t) Represent plan actual consumption expense of each advertisement to be put in t moment;E (P, t) represents plan of each advertisement to be put in t moment It is expected that consumption costs.Wherein, the value of Δ U can according to actual needs be set by technical staff.
In addition, for account matter metric threshold in intraday a cycle, Thr (U, 0) that is to say, it can be by technology Personnel are set according to actual needs, can also continue the account matter metric threshold in the last one period of the previous day.
Optionally, the variation step-length of account matter metric threshold, that is to say Δ U, influence whether the degree of fluctuation and receipts of algorithm Hold back speed, it is preferable that Δ U can be set as 0.1%.The bound section too conference of Δ U causes budget control strategy wide Reflect and slows down after accusing main change budget, thus the bound section of Δ U cannot too greatly, it is alternatively possible to set Δ U Value in [0%, 15%].
Above-mentioned steps S203-S207 is according to budget information and consumption information, calculates each advertisement to be put in current period Account matter metric threshold a kind of realization method.
In another embodiment of the invention, step S207 can also be realized in the following way:
According to the account of the distribution of the corresponding industry cumulative consumption at each advertising presupposition moment to be put and each advertisement to be put Family remaining sum and account actual consumption expense calculate second account estimated consumption costs of each advertisement to be put in predetermined time;Root It is expected consumption costs in the estimated consumption costs of the first account of predetermined time and the second account according to each advertisement to be put, it is each to be put Advertisement preset the account consumption increment size and account quality degree in a upper period in the account actual consumption expense of predetermined time Threshold value calculates account matter metric threshold of each advertisement to be put in current period.
Specifically, second account estimated consumption costs of each advertisement to be put in t moment is represented with NE (U, t), according to each The corresponding industry cumulative consumption distribution at advertising presupposition moment to be put and the account balance and account of each advertisement to be put are real Border consumption costs calculates second account estimated consumption costs of each advertisement to be put in predetermined time, can specifically pass through formula Six, it realizes in the following way:
Wherein, M (U, t) represents the account balance of the account U of each advertisement to be put;C (U, t) represents each advertisement to be put Account U is in the account actual consumption expense in t moment;F (I, 0, t), F (I, 0, t) represent equivalent in meaning with front, herein not It repeats again.
In the present embodiment, when each advertisement to be put is pre- more than the account in t moment in the account actual consumption expense of t moment Consumption costs is counted, then needs to promote account matter metric threshold;When each advertisement to be put is small in the account actual consumption expense of t moment In or equal to t moment the estimated consumption costs of account, then need to reduce account matter metric threshold, with by according to respectively waiting to throw Account matter metric threshold of the advertisement in t moment is put, each advertisement to be put is filtered, so as to reduce the advertisement because of budgetary shortfall Main pre-mature exhaustion budget cause largely search for lose advertisement launch and caused by loss.
Specifically, it is estimated in the estimated consumption costs of the first account of predetermined time and the second account according to each advertisement to be put Consumption costs, each advertisement to be put is in the account actual consumption expense of predetermined time and default account consumption increment size, calculating Each advertisement to be put can calculate each advertisement to be put in current week in the account matter metric threshold of current period by formula seven The account matter metric threshold of phase:
Wherein, NE (U, t) represents second account estimated consumption costs of each advertisement to be put in t moment;Thr (U, t), Thr (U, t-1), E (U, t), the meaning of Δ U and C (U, t) are identical with above-mentioned steps S207, and details are not described herein again.
In the present embodiment, by being updated periodically account matter metric threshold and plan quality degree threshold value.In addition, it calculates each Advertisement to be put in the process of the account matter metric threshold of current period, with calculating the plan of each advertisement to be put in current period The process of matter metric threshold is two relatively independent processes, the two processes can be carried out sequentially or can be parallel It carries out, the present embodiment is not specifically limited the sequence of the two processes.
Step S208, according to each advertisement to be put in the plan quality degree threshold value of current period and account matter metric threshold, Each advertisement to be put is filtered.
In the present embodiment, according to each advertisement to be put in the plan quality degree threshold value of current period and account quality degree threshold Value, is filtered each advertisement to be put, and following manner realization specifically may be used:
Each advertisement to be put is obtained in the account quality degree of predetermined time and plan quality degree;By in each advertisement to be put, Account quality degree is less than the advertisement to be put of account matter metric threshold and/or plan quality degree is less than plan quality degree threshold value Advertisement filter to be put is fallen;It that is to say, remove account quality degree at least one advertisement to be put and be less than account matter metric threshold Advertisement to be put and/or plan quality degree be less than plan quality degree threshold value advertisement to be put.
Control method is launched in the advertisement of the embodiment of the present invention, is disappeared by using budget control algorithm in smooth advertiser budget While consuming rate, its CTR is promoted.In another embodiment of the invention, it can be also used for optimizing the investment for the advertiser that breasts the tape Return rate (ROI), average clicked price, the amount of showing etc..
Optionally, fluctuation or uncertainty are one of search advertisements features, it is also embodied in simultaneously in budget consumption. Ad click is by chance concentrated at the time of occur, and the judgement for being easy to generate mistake in control method is launched in the advertisement of the prior art, And at this time once manslaughtered the showing advertisement of the advertiser of budget abundance or it is excessively tight to the advertisement main control of limited budget thus Its budget is not exhausted, can all cause loss in revenue.Therefore, it in the present embodiment, never breasts the tape for continuous budget in one week wide Master is accused, advertisement provided in an embodiment of the present invention can not be taken to launch control method, advertisement to be put is filtered;For The advertiser of limited budget, when preceding 10% dispensing period or consumption be not up to 10% master budget, use is provided in this embodiment Put-on method;And the advertiser for continuously breasting the tape, it is launched once decontroling, easily budget exhausts in a short period of time, therefore, The advertiser continuously to breast the tape, their account matter metric threshold and plan quality degree threshold value will continue the previous day in the last one period Value, ensure lasting control.
In the present embodiment, optionally, in daily last preset duration, advertisement to be put is not filtered.Wherein, it presets Duration can be 1 hour, 2 hours, 30 minutes etc., can according to actual needs be set by technical staff.By continuous Analysis and optimization, the limitation of budget control algorithm effect maximum come from the accuracy rate that consumption curve is estimated.The inaccuracy estimated Both being likely to cause advertiser budget can not exhaust, it is also possible to budget be caused to consume too fast, effect out of hand.And due to wide It is violent to accuse main budget consumption fluctuation, it is uncertain very big, advertiser budget curve estimate be one than budget control in itself More difficult thing.In the relevant research data of existing budget control, calculating the consumption curve of advertiser needs to analyze Historical data, and estimated using higher-dimension Rating Model.Consume it is too fast with excessively slowly between compare, with greater need for avoiding consuming Slowly, so as to avoid directly consuming loss, therefore, in last daily hour using safeguard measure, not to advertisement to be put into Row filtering.
In the present embodiment, before advertisement dispensing is carried out, by real account quality in advertisement to be put, in t moment Degree falls less than the advertisement filter to be put of the account matter metric threshold of current period;Alternatively, before advertisement dispensing is carried out, will treat Launch it is in advertisement, t moment practical plan quality degree be less than current period plan quality degree threshold value it is to be put wide Announcement filters out;Alternatively, before advertisement dispensing is carried out, by advertisement to be put, it is less than in the real account quality degree of t moment Advertisement to be put in the account matter metric threshold of current period and the practical plan quality degree in t moment are less than current The advertisement to be put of the plan quality degree threshold value in period filters out, so as in the same of smooth advertiser budget wear rate When, promote its CTR.
The embodiment of the present invention by according to search key launch advertisement when, by obtaining each advertisement to be put in real time The consumption information such as budget information and plan actual consumption expense, account actual consumption expense and account balance, periodically basis Budget information and consumption information calculate each advertisement to be put in the plan quality degree threshold value of current period and account quality degree threshold Value;According to each advertisement to be put in the plan quality degree threshold value of current period and account matter metric threshold, to each advertisement to be put It is filtered, it is possible to reduce caused because advertiser's pre-mature exhaustion budget of budgetary shortfall causes largely to search for lose when advertisement is launched Loss, and can improve launch advertisement entirety click-through-rate so that advertisement delivery effect is more preferable.
Embodiment three
If advertisement launching platform shows, advertisement is excessive or the advertisement degree of correlation not enough can all influence user experience, reduces and uses Degree is sick of in the advertisement of the volumes of searches, promotion user at family, the benefit of whole ecological environment is damaged, so as to lose long-term gain.Such as Fruit assumes that the uncorrelated degree of advertisement of acceptable showing advertisement quantity or totality is one to each user whithin a period of time Fixed numerical value, then the advertisement dispensing on different flow is based on user experience and establishes contact.For balanced advertisement search Long-term gain and short-term yield need that the comprehensive value of an advertisement is measured and optimized, to improve the satisfaction of user.
Fig. 3 is that control method flow chart is launched in the advertisement that the embodiment of the present invention three provides.On the basis of above-described embodiment one On, in the present embodiment, as shown in figure 3, this method is as follows:
Step S301, at least one advertisement to be put that acquisition and search key match.
In the present embodiment, the industry according to involved by ad content can classify to advertisement, mutually advertisement of the same trade It clusters in same industry classification.For once searching for, belonged to together with all advertisements to be put that search key matches One industry.
After search key input by user is detected, can obtain one matched with the search key or Multiple advertisements to be put are subsequently launched control method progress advertisement dispensing according to advertisement provided by the invention and are showed.
Step S302, the matter measurement information and bid information of advertisement to be put are obtained.
Wherein, the quality degree information of advertisement to be put includes quality degree of each advertisement to be put in each placement position.
Step S303, according to the matter measurement information and bid information of advertisement to be put, Efficiency-optimized model is established.
Wherein, Efficiency-optimized model is:Meeting the average quality degree for launching advertisement not less than default average quality degree threshold Under the constraints of value, the target for solving advertisement to be put launches strategy so that launches the maximum of the comprehensive income of advertisement.
The problem of Efficiency-optimized model, Formal Representation was as follows:
Object function is:maxI(a,s,p)spaQ (a, p) bid (a) I (a, s, p),
Constraints is:
Wherein, it represents an advertisement to be put with a, represents once to search for s, a placement position of advertisement is represented with p, Q (a, p) refers to that advertisement a launches the quality degree on the p of position, and bid (a) is the bid of advertisement a;I (a, s, p) is indicator function, It is 1 when the advertisement a of s is launched in p-th of placement position, when the advertisement a of s is not launched in p-th of placement position, I (a, s, P) value is 0;Thr is default average quality degree threshold value;Wherein I (a, s, p) is undetermined parameter.
This is a discrete constraint optimization problem, needs to solve using the method for Dynamic Programming, complexity NP-hard Grade.Karush-Kuhn-Tucker optimal conditions (abbreviation KKT conditions) are to solve for the common method of this kind of problem, but Under current context, the solution of KKT conditions is the necessary condition of above problem solution.Use complete KKT conditions, the problem complexity It is still higher.In order to reduce the complexity for solving the problem, using the first condition of KKT, above-mentioned Efficiency-optimized model can turn Turn to the problem of solving following formula extreme value:
Due to the discreteness of variable, this problem is still difficult to resolve.The above problem is further broken into local queue to ask most It is excellent to regulate and control two processes with global parameter, optimal solution is approached by parameter search later.
By factorization, above-mentioned object function can be converted into the form of equation below eight:
maxI(a,,)spaq(a,p)×(bid(a)+α)×I(a,s,p)-α×Thr×∑spaI(a,s, P) formula eight
In the present embodiment, according to the matter measurement information and bid information of advertisement to be put, Efficiency-optimized model, benefit are established Optimized model is:In the case where meeting the average quality degree for launching advertisement and being not less than the constraints of default average quality degree threshold value, ask The target for solving advertisement to be put launches strategy so that launches the maximum of the comprehensive income of advertisement, specifically may be used such as lower section Formula is realized:
The Efficiency-optimized model for including undetermined parameter is established, the following formula may be used in the object function of Efficiency-optimized model Eight represent:
maxI(a,s,p)spaq(a,p)×(bid(a)+α)×I(a,s,p)-α×Thr×∑spaI(a, S, p) formula eight
Wherein, it represents an advertisement to be put with a, represents once to search for s, a placement position of advertisement is represented with p, Q (a, p) refers to that advertisement a launches the quality degree on the p of position, and bid (a) is the bid of advertisement a;I (a, s, p) is indicator function, It is 1 when the advertisement a of s is launched in p-th of placement position, when the advertisement a of s is not launched in p-th of placement position, I (a, s, P) value is 0;Thr is default average quality degree threshold value;α and I (a, s, p) is undetermined parameter.
The constraints of Efficiency-optimized model may be used the following formula nine and represent:
Efficiency-optimized model is:In the case where meeting constraints, the value of one group of undetermined parameter is solved so that object function obtains Maximum.
Step S304, according to Efficiency-optimized model, advertisement dispensing is carried out.
In the present embodiment, according to Efficiency-optimized model, advertisement dispensing is carried out, following manner realization specifically may be used:
Solve one group of parameter value of the undetermined parameter in Efficiency-optimized model so that object function obtains maximum;It will The value for the indicator function that the one group of parameter value solved includes substitutes into Efficiency-optimized model, obtains the object module that parameter determines;Root According to object module, advertisement dispensing is carried out.
Specifically, by the max in above-mentioned formula eightI(a,s,p)spaQ (a, p) × (bid (a)+α) × I (a, s, p) makees For the first part of formula eight, α × Thr × ∑spaSecond parts of the I (a, s, p) as formula eight.First part can be with Regard a kind of new marking mode to advertisement as, as long as the highest advertisement of distribution scoring in the placement position of each advertisement Acquire the optimal solution of first part;And second part is the negative weighting for showing advertisement amount.In the maximum of solution formula eight Process, can be regarded as by the advertisement for scoring forward distribution on ad placement few as possible.
Therefore, the optimal solution of formula eight is acquired by following searching method:
Step 1: for the parameter alpha of setting, on each search s, successively for each placement position p, following locate is carried out Reason:The scoring that each advertisement a to be put corresponds to placement position p is calculated respectively:Q (a, p) (bid (a)+α), will score highest Advertisement to be put is launched to placement position p..
Specifically, for any one placement position p, each advertisement to be put is calculated respectively corresponding to placement position p's Score q (a, p) (bid (a)+α), is ranked up according to the scoring, determines the highest advertisement to be put of scoring, and the highest that will score Advertisement to be put launch to placement position p.
Step 2: for the whole advertisements launched in step 1, score threshold minscore is enumerated, scoring is less than should The advertisement of score threshold is filtered, that is, filters out q (a, p) (bid (a)+α)<The advertisement of minscore, until being launched after filtering The average quality degree of whole advertisements be equal to default average quality degree threshold value.
Step 3: enumerating parameter alpha, and recycle and perform two step of step 1 and step 2, finally determine α, minscore and I One class value of (a, s, p) so that object function obtains maximum, that is to say and is not less than in the average quality degree for meeting dispensing advertisement Under the constraints of default average quality degree threshold value, the target for obtaining advertisement to be put launches strategy so that launches the comprehensive of advertisement Close the maximum of income.
A class value of the α and I (a, s, p) that will eventually determine are substituted into formula eight, obtain object module.
According to object module, carry out advertisement dispensing and following manner realization specifically may be used:
Step 1: according to object module, for known parameters α, on each search s, with q (a, p) (bid (a)+α) into Row sequence, and according to ranking results, the placement position of advertisement is distributed from high to low.
Step 2: for the whole advertisements launched in step 1, for known score threshold minscore, will score small It is filtered in the advertisement of the score threshold, that is, filters out q (a, p) (bid (a)+α)<Then the advertisement of minscore carries out wide It accuses and launches, the average quality degree of whole advertisements launched after this spline filter will not be less than default average quality degree threshold value.
The embodiment of the present invention is by obtaining the matter measurement information and bid information of advertisement to be put;According to advertisement to be put Matter measurement information and bid information, establish Efficiency-optimized model, and Efficiency-optimized model is:In the average quality for meeting dispensing advertisement Under constraints of the degree not less than default average quality degree threshold value, the target for solving advertisement to be put launches strategy so that launches The maximum of the comprehensive income of advertisement;According to Efficiency-optimized model, advertisement dispensing is carried out, can ensure to launch being averaged for advertisement Under the premise of quality degree is not less than default average quality degree threshold value, the comprehensive income for launching advertisement is maximized.
Example IV
Fig. 4 is the structure diagram that control device is launched in the advertisement that the embodiment of the present invention four provides.The embodiment of the present invention carries Control device is launched in the advertisement of confession can perform the process flow that the offer of control method embodiment is launched in advertisement.It as shown in figure 4, should Device 40 includes:First acquisition module 401, the second acquisition module 402 and processing module 403.
Specifically, at least one advertisement to be put that the first acquisition module 401 matches for acquisition with search key, And the budget information of each advertisement to be put, budget information include at least:Plan whole day budget and account whole day budget.
Second acquisition module 402 is used to obtain the consumption information of each advertisement to be put in real time, and consumption information includes at least:Meter Draw actual consumption expense, account actual consumption expense and account balance.
Processing module 403 is used for periodically according to budget information and consumption information, and each advertisement to be put is filtered.
Device provided in an embodiment of the present invention can be specifically used for performing the embodiment of the method that above-described embodiment one is provided, Details are not described herein again for concrete function.
Control method and device are launched in advertisement provided by the invention, by when launching advertisement according to search key, leading to After the budget information for obtaining each advertisement to be put in real time and plan actual consumption expense, account actual consumption expense and account balance Etc. consumption information, periodically according to budget information and consumption information, the advertisement filter to be put of budgetary shortfall is fallen, can be subtracted Few loss caused by advertiser's pre-mature exhaustion budget of budgetary shortfall causes largely to search for and lose when advertisement is launched, and can carry Height launches the click-through-rate of advertisement entirety, so that advertisement delivery effect is more preferable.
Embodiment five
On the basis of above-described embodiment four, in the present embodiment, processing module includes:Computational submodule, acquisition submodule With dispensing submodule.
Wherein, computational submodule is used for according to budget information and consumption information, calculates each advertisement to be put in current period Plan quality degree threshold value and account matter metric threshold.
Acquisition submodule is used to obtain each advertisement to be put in the account quality degree of predetermined time and plan quality degree.
It launches submodule and is less than account matter metric threshold for removing account quality degree at least one advertisement to be put Advertisement to be put and/or plan quality degree are less than the advertisement to be put of plan quality degree threshold value.
In the present embodiment, computational submodule is specifically used for:
Obtain the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put;According to each advertising presupposition to be put The corresponding industry cumulative consumption distribution at moment and the plan whole day budget of each advertisement to be put, calculate each advertisement to be put In the estimated consumption costs of the plan of predetermined time;Consumption costs is expected according to plan of each advertisement to be put in predetermined time, respectively Advertisement to be put is in the plan actual consumption expense of predetermined time, pre-designed cancellation consumption increment size and the plan in a upper period Matter metric threshold calculates plan quality degree threshold value of each advertisement to be put in current period.
Computational submodule is additionally operable to:
Obtain the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put;According to each advertising presupposition to be put The corresponding industry cumulative consumption distribution at moment and the account whole day budget of each advertisement to be put, calculate each advertisement to be put In the estimated consumption costs of the first account of predetermined time;Consumption is expected according to first account of each advertisement to be put in predetermined time Expense, each advertisement to be put preset an account consumption increment size and upper period in the account actual consumption expense of predetermined time Account matter metric threshold, calculate the account matter metric threshold of each advertisement to be put in current period.
Optionally, computational submodule is additionally operable to:
According to the account of the distribution of the corresponding industry cumulative consumption at each advertising presupposition moment to be put and each advertisement to be put Family remaining sum and account actual consumption expense calculate second account estimated consumption costs of each advertisement to be put in predetermined time;Root It is expected consumption costs in the estimated consumption costs of the first account of predetermined time and the second account according to each advertisement to be put, it is each to be put Advertisement preset the account consumption increment size and account quality degree in a upper period in the account actual consumption expense of predetermined time Threshold value calculates account matter metric threshold of each advertisement to be put in current period.
Device provided in an embodiment of the present invention can be specifically used for performing the embodiment of the method that above-described embodiment two is provided, Details are not described herein again for concrete function.
The embodiment of the present invention by according to search key launch advertisement when, by obtaining each advertisement to be put in real time The consumption information such as budget information and plan actual consumption expense, account actual consumption expense and account balance, periodically basis Budget information and consumption information calculate each advertisement to be put in the plan quality degree threshold value of current period and account quality degree threshold Value;According to each advertisement to be put in the plan quality degree threshold value of current period and account matter metric threshold, to each advertisement to be put It is filtered, it is possible to reduce caused because advertiser's pre-mature exhaustion budget of budgetary shortfall causes largely to search for lose when advertisement is launched Loss, and can improve launch advertisement entirety click-through-rate so that advertisement delivery effect is more preferable.
Embodiment six
On the basis of above-described embodiment four, in the present embodiment, control device is launched in advertisement to be included:Third obtains Module, model building module and putting module.
Wherein, third acquisition module is used to obtain the matter measurement information and bid information of advertisement to be put.
Model building module is used for matter measurement information and bid information according to advertisement to be put, establishes benefit optimization mould Type, Efficiency-optimized model are:Meeting the average quality degree for launching advertisement not less than the constraint item for presetting average quality degree threshold value Under part, the target for solving advertisement to be put launches strategy so that launches the maximum of the comprehensive income of advertisement.
Putting module, for according to Efficiency-optimized model, carrying out advertisement dispensing.
Specifically, model building module is specifically used for:
The Efficiency-optimized model for including undetermined parameter is established, the following formula may be used in the object function of Efficiency-optimized model Eight represent:
maxI(a,s,p)spaq(a,p)×(bid(a)+α)×I(a,s,p)-α×Thr×∑spaI(a, S, p) formula eight
Wherein, it represents an advertisement to be put with a, represents once to search for s, a placement position of advertisement is represented with p, Q (a, p) refers to that advertisement a launches the quality degree on the p of position, and bid (a) is the bid of advertisement a;I (a, s, p) is indicator function, It is 1 when the advertisement a of s is launched in p-th of placement position, when the advertisement a of s is not launched in p-th of placement position, I (a, s, P) value is 0;Thr is default average quality degree threshold value;α and I (a, s, p) is undetermined parameter.
The constraints of Efficiency-optimized model may be used the following formula nine and represent:
Efficiency-optimized model is:In the case where meeting constraints, the value of one group of undetermined parameter is solved so that object function obtains Maximum.
Putting module is specifically used for:
Solve one group of parameter value of the undetermined parameter in Efficiency-optimized model so that object function obtains maximum;It will The value for the indicator function that the one group of parameter value solved includes substitutes into Efficiency-optimized model, obtains the object module that parameter determines;Root According to object module, advertisement dispensing is carried out.
Device provided in an embodiment of the present invention can be specifically used for performing the embodiment of the method that above-described embodiment three is provided, Details are not described herein again for concrete function.
Control method and device are launched in advertisement provided by the invention, by when launching advertisement according to search key, leading to After the budget information for obtaining each advertisement to be put in real time and plan actual consumption expense, account actual consumption expense and account balance Etc. consumption information, periodically according to budget information and consumption information, the advertisement filter to be put of budgetary shortfall is fallen, can be subtracted Few loss caused by advertiser's pre-mature exhaustion budget of budgetary shortfall causes largely to search for and lose when advertisement is launched, and can carry Height launches the click-through-rate of advertisement entirety, so that advertisement delivery effect is more preferable.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, only A kind of division of logic function, can there is an other dividing mode in actual implementation, for example, multiple units or component can combine or Person is desirably integrated into another system or some features can be ignored or does not perform.Another point, shown or discussed is mutual Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, device or unit It connects, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit Component may or may not be physical unit, you can be located at a place or can also be distributed to multiple networks On unit.Some or all of unit therein can be selected according to the actual needs to realize the purpose of this embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also That each unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list The form that hardware had both may be used in member is realized, can also be realized in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can be stored in one and computer-readable deposit In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, is used including some instructions so that a computer It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) perform the present invention The part steps of embodiment the method.And aforementioned storage medium includes:USB flash disk, mobile hard disk, read-only memory (Read- Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. it is various The medium of program code can be stored.
Those skilled in the art can be understood that, for convenience and simplicity of description, only with above-mentioned each function module Division progress for example, in practical application, can be complete by different function modules by above-mentioned function distribution as needed Into the internal structure of device being divided into different function modules, to complete all or part of function described above.On The specific work process of the device of description is stated, the corresponding process in preceding method embodiment can be referred to, details are not described herein.
Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice invention disclosed herein Its embodiment.The present invention is directed to cover the present invention any variations, uses, or adaptations, these modifications, purposes or Person's adaptive change follows the general principle of the present invention and including undocumented common knowledge in the art of the invention Or conventional techniques.Description and embodiments are considered only as illustratively, and true scope and spirit of the invention are by following Claims are pointed out.
It should be understood 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 may be made without departing from the scope thereof.The scope of the present invention is only limited by appended claims System.

Claims (16)

1. control method is launched in a kind of advertisement, which is characterized in that including:
The budget for obtaining at least one advertisement to be put to match with search key and each advertisement to be put is believed Breath, the budget information include at least:Plan whole day budget and account whole day budget;
The consumption information of each advertisement to be put is obtained in real time, and the consumption information includes at least:Plan actual consumption expense, Account actual consumption expense and account balance;
Periodically according to the budget information and consumption information, each advertisement to be put is filtered.
2. according to the method described in claim 1, it is characterized in that, described periodically believe according to the budget information and consumption Breath, is filtered each advertisement to be put, including:
According to the budget information and consumption information, plan quality degree threshold value of each advertisement to be put in current period is calculated With account matter metric threshold;
Each advertisement to be put is obtained in the account quality degree of the predetermined time and plan quality degree;
It is to be put less than the account matter metric threshold to remove account quality degree described at least one advertisement to be put Advertisement and/or the plan quality degree are less than the advertisement to be put of the plan quality degree threshold value.
It is 3. according to the method described in claim 2, it is characterized in that, described according to the budget information and consumption information, calculating Each advertisement to be put current period plan quality degree threshold value, including:
Obtain the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put;
It is distributed according to the corresponding industry cumulative consumption of predetermined time described in each advertisement to be put and each described to be put The plan whole day budget of advertisement calculates plan estimated consumption costs of each advertisement to be put in the predetermined time;
Consumption costs is expected according to plan of each advertisement to be put in the predetermined time, each advertisement to be put is in institute The plan actual consumption expense of predetermined time, pre-designed cancellation consumption increment size and the plan quality degree threshold value in a upper period were stated, Calculate plan quality degree threshold value of each advertisement to be put in current period.
It is 4. according to the method described in claim 2, it is characterized in that, described according to the budget information and consumption information, calculating Each advertisement to be put is specifically included in the account matter metric threshold of current period:
Obtain the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put;
It is distributed according to the corresponding industry cumulative consumption of predetermined time described in each advertisement to be put and each described to be put The account whole day budget of advertisement calculates first account estimated consumption costs of each advertisement to be put in the predetermined time;
According to each advertisement to be put in the estimated consumption costs of the first account of the predetermined time, each advertisement to be put In the account actual consumption expense of the predetermined time, account consumption increment size and the account quality degree in a upper period were preset Threshold value calculates account matter metric threshold of each advertisement to be put in current period.
5. according to the method described in claim 4, it is characterized in that, it is described according to each advertisement to be put when described default The estimated consumption costs of the first account carved, each advertisement to be put the predetermined time account actual consumption expense, in advance If account consumed increment size and the account matter metric threshold in a upper period, each advertisement to be put is calculated current The account matter metric threshold in period, including:
It is distributed according to the corresponding industry cumulative consumption of predetermined time described in each advertisement to be put and each described to be put The account balance of advertisement and account actual consumption expense calculate second account of each advertisement to be put in the predetermined time It is expected that consumption costs;
It is expected to disappear in the estimated consumption costs of the first account of the predetermined time and the second account according to each advertisement to be put Expend use, each advertisement to be put the predetermined time account actual consumption expense, preset account consumption increment size, with And the account matter metric threshold in a upper period, calculate account quality degree threshold of each advertisement to be put in current period Value.
6. it according to the method described in claim 1, at least one waits to throw with what search key matched it is characterized in that, obtaining After putting advertisement, further include:
Obtain the matter measurement information and bid information of the advertisement to be put;
According to the matter measurement information and bid information of the advertisement to be put, Efficiency-optimized model is established, the benefit optimizes mould Type is:In the case where meeting the average quality degree for launching advertisement and being not less than the constraints of default average quality degree threshold value, described in solution The target of advertisement to be put launches strategy so that launches the maximum of the comprehensive income of advertisement;
According to the Efficiency-optimized model, advertisement dispensing is carried out.
7. according to the method described in claim 6, it is characterized in that, the matter measurement information according to the advertisement to be put and Bid information, establishes Efficiency-optimized model, and the Efficiency-optimized model is:It is not less than in the average quality degree for meeting dispensing advertisement Under the constraints of default average quality degree threshold value, the target for solving the advertisement to be put launches strategy so that launches advertisement Comprehensive income maximum, specifically include:
The Efficiency-optimized model for including undetermined parameter is established, the object function of the Efficiency-optimized model can be expressed as:
maxI(a,s,p)spaq(a,p)×(bid(a)+α)×I(a,s,p)-α×Thr×∑spaI(a,s,p)
Wherein, it represents an advertisement to be put with a, represents once to search for s, represent a placement position of advertisement with p, q (a, P) refer to that advertisement a launches the quality degree on the p of position, bid (a) is the bid of advertisement a;I (a, s, p) is indicator function, when s's It is 1 that advertisement a, which is launched in p-th of placement position, when the advertisement a of s is not launched in p-th of placement position, I's (a, s, p) Be worth is 0;Thr is the default average quality degree threshold value;α and I (a, s, p) is undetermined parameter;
The constraints of the Efficiency-optimized model is expressed as:
The Efficiency-optimized model is:In the case where meeting the constraints, the value of undetermined parameter described in one group is solved so that described Object function obtains maximum.
8. the method according to the description of claim 7 is characterized in that according to the Efficiency-optimized model, advertisement dispensing, packet are carried out It includes:
Solve one group of parameter value of the undetermined parameter in the Efficiency-optimized model so that the object function obtains pole Big value;
The value of indicator function that the one group of parameter value solved includes is substituted into the Efficiency-optimized model, parameter is obtained and determines Object module;
According to the object module, advertisement dispensing is carried out.
9. control device is launched in a kind of advertisement, which is characterized in that including:
First acquisition module, for obtaining at least one advertisement to be put for matching with search key and each described treating The budget information of advertisement is launched, the budget information includes at least:Plan whole day budget and account whole day budget;
Second acquisition module, for obtaining the consumption information of each advertisement to be put in real time, the consumption information includes at least: Plan actual consumption expense, account actual consumption expense and account balance;
Processing module, for periodically according to the budget information and consumption information, being carried out to each advertisement to be put Filter.
10. device according to claim 9, which is characterized in that the processing module includes:
Computational submodule, for according to the budget information and consumption information, calculating each advertisement to be put in current period Plan quality degree threshold value and account matter metric threshold;
Acquisition submodule, for obtaining account quality degree and plan quality of each advertisement to be put in the predetermined time Degree;
Submodule is launched, for removing account quality degree described at least one advertisement to be put less than the account quality It spends the advertisement to be put of threshold value and/or the plan quality degree is less than the advertisement to be put of the plan quality degree threshold value.
11. device according to claim 10, which is characterized in that the computational submodule is specifically used for:
Obtain the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put;
It is distributed according to the corresponding industry cumulative consumption of predetermined time described in each advertisement to be put and each described to be put The plan whole day budget of advertisement calculates plan estimated consumption costs of each advertisement to be put in the predetermined time;
Consumption costs is expected according to plan of each advertisement to be put in the predetermined time, each advertisement to be put is in institute The plan actual consumption expense of predetermined time, pre-designed cancellation consumption increment size and the plan quality degree threshold value in a upper period were stated, Calculate plan quality degree threshold value of each advertisement to be put in current period.
12. device according to claim 10, which is characterized in that the computational submodule is additionally operable to:
Obtain the industry cumulative consumption distribution of the corresponding predetermined time of each advertisement to be put;
It is distributed according to the corresponding industry cumulative consumption of predetermined time described in each advertisement to be put and each described to be put The account whole day budget of advertisement calculates first account estimated consumption costs of each advertisement to be put in the predetermined time;
According to each advertisement to be put in the estimated consumption costs of the first account of the predetermined time, each advertisement to be put In the account actual consumption expense of the predetermined time, account consumption increment size and the account quality degree in a upper period were preset Threshold value calculates account matter metric threshold of each advertisement to be put in current period.
13. device according to claim 12, which is characterized in that the computational submodule is additionally operable to:
It is distributed according to the corresponding industry cumulative consumption of predetermined time described in each advertisement to be put and each described to be put The account balance of advertisement and account actual consumption expense calculate second account of each advertisement to be put in the predetermined time It is expected that consumption costs;
It is expected to disappear in the estimated consumption costs of the first account of the predetermined time and the second account according to each advertisement to be put Expend use, each advertisement to be put the predetermined time account actual consumption expense, preset account consumption increment size, with And the account matter metric threshold in a upper period, calculate account quality degree threshold of each advertisement to be put in current period Value.
14. device according to claim 9, which is characterized in that further include:
Third acquisition module, for obtaining the matter measurement information of the advertisement to be put and bid information;
Model building module for the matter measurement information and bid information according to the advertisement to be put, establishes benefit optimization mould Type, the Efficiency-optimized model are:Meeting the average quality degree for launching advertisement not less than the pact for presetting average quality degree threshold value Under the conditions of beam, the target for solving the advertisement to be put launches strategy so that launches the maximum of the comprehensive income of advertisement;
Putting module, for according to the Efficiency-optimized model, carrying out advertisement dispensing.
15. device according to claim 14, which is characterized in that the model building module is specifically used for:
The Efficiency-optimized model for including undetermined parameter is established, the object function of the Efficiency-optimized model can be expressed as:
maxI(a,s,p)spaq(a,p)×(bid(a)+α)×I(a,s,p)-α×Thr×∑spaI(a,s,p)
Wherein, it represents an advertisement to be put with a, represents once to search for s, represent a placement position of advertisement with p, q (a, P) refer to that advertisement a launches the quality degree on the p of position, bid (a) is the bid of advertisement a;I (a, s, p) is indicator function, when s's It is 1 that advertisement a, which is launched in p-th of placement position, when the advertisement a of s is not launched in p-th of placement position, I's (a, s, p) Be worth is 0;Thr is the default average quality degree threshold value;α and I (a, s, p) is undetermined parameter;
The constraints of the Efficiency-optimized model is expressed as:
The Efficiency-optimized model is:In the case where meeting the constraints, the value of undetermined parameter described in one group is solved so that described Object function obtains maximum.
16. device according to claim 15, which is characterized in that the putting module is specifically used for:
Solve one group of parameter value of the undetermined parameter in the Efficiency-optimized model so that the object function obtains pole Big value;
The value of indicator function that the one group of parameter value solved includes is substituted into the Efficiency-optimized model, parameter is obtained and determines Object module;
According to the object module, advertisement dispensing is carried out.
CN201711480482.5A 2017-12-29 2017-12-29 Advertisement putting control method and device Active CN108269123B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711480482.5A CN108269123B (en) 2017-12-29 2017-12-29 Advertisement putting control method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711480482.5A CN108269123B (en) 2017-12-29 2017-12-29 Advertisement putting control method and device

Publications (2)

Publication Number Publication Date
CN108269123A true CN108269123A (en) 2018-07-10
CN108269123B CN108269123B (en) 2021-03-12

Family

ID=62773126

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711480482.5A Active CN108269123B (en) 2017-12-29 2017-12-29 Advertisement putting control method and device

Country Status (1)

Country Link
CN (1) CN108269123B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109003140A (en) * 2018-07-26 2018-12-14 腾讯科技(深圳)有限公司 Determination method, equipment and the storage medium that the dispensing of multimedia content is provided funds
CN109829749A (en) * 2018-12-28 2019-05-31 微梦创科网络科技(中国)有限公司 A kind of advertisement placement method and system
CN110264279A (en) * 2019-06-25 2019-09-20 苏州梦嘉信息技术有限公司 Management method and system are launched in a kind of advertisement
CN110348908A (en) * 2019-07-15 2019-10-18 西安点告网络科技有限公司 Budget control method and device is launched in advertisement
CN110490649A (en) * 2019-08-12 2019-11-22 上海漫酷网络技术有限公司 A kind of at the uniform velocity put-on method and system of advertisement dispensing
CN111598631A (en) * 2020-06-05 2020-08-28 上海智子信息科技股份有限公司 Cross-channel keyword price optimization method with effect target oriented
CN111612413A (en) * 2020-04-11 2020-09-01 上海淇玥信息技术有限公司 Advertisement customized delivery platform and method based on account management and electronic equipment
CN111626776A (en) * 2020-05-26 2020-09-04 创新奇智(西安)科技有限公司 Method for training strategy model, method and device for determining advertisement putting strategy
CN111756590A (en) * 2019-03-27 2020-10-09 北京沃东天骏信息技术有限公司 Small flow test method and device for information display flow control
CN111815357A (en) * 2020-07-09 2020-10-23 湖南数客星球信息技术有限公司 Big data intelligent advertisement system and method based on amazon search word bank
CN111861563A (en) * 2020-07-20 2020-10-30 广元量知汇科技有限公司 Advertisement request processing method for digital marketing
CN111861564A (en) * 2020-07-20 2020-10-30 广元量知汇科技有限公司 Digital advertisement transaction system
CN112150181A (en) * 2019-06-28 2020-12-29 腾讯科技(深圳)有限公司 Resource allocation method, device, equipment and storage medium
CN112258239A (en) * 2020-10-30 2021-01-22 北京沃东天骏信息技术有限公司 Method, device, equipment, medium and system for acquiring super-broadcast control effect data
CN112581157A (en) * 2019-09-30 2021-03-30 百度在线网络技术(北京)有限公司 Information delivery control method, device, equipment, system and medium
CN113283941A (en) * 2021-06-09 2021-08-20 北京有竹居网络技术有限公司 Advertisement putting method and device, storage medium and electronic equipment
CN114493660A (en) * 2021-12-24 2022-05-13 北京明略软件***有限公司 Method and device for advertisement budget allocation, electronic equipment and storage medium
CN116167804A (en) * 2023-04-19 2023-05-26 江西时刻互动科技股份有限公司 Advertisement putting method and device, computer readable storage medium and electronic equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101248450A (en) * 2005-06-29 2008-08-20 谷歌公司 Prioritizing ad reviews, by using expected revenue for example, in an advertising system
CN103578013A (en) * 2012-08-06 2014-02-12 风网科技(北京)有限公司 Intelligent positioning device and intelligent positioning method of mobile advertisement platform
CN105528377A (en) * 2014-10-22 2016-04-27 阿里巴巴集团控股有限公司 A processing method, device and system for search results
CN105741133A (en) * 2016-01-26 2016-07-06 电子科技大学 Stepping management method for online advertisement delivery
US20170193560A1 (en) * 2016-01-01 2017-07-06 Facebook, Inc. Pacing a budget for presenting sponsored content while limiting frequency of sponsored content presentation
CN107491986A (en) * 2017-08-02 2017-12-19 北京品友互动信息技术股份公司 For controlling the method and device of advertising budget

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101248450A (en) * 2005-06-29 2008-08-20 谷歌公司 Prioritizing ad reviews, by using expected revenue for example, in an advertising system
CN103578013A (en) * 2012-08-06 2014-02-12 风网科技(北京)有限公司 Intelligent positioning device and intelligent positioning method of mobile advertisement platform
CN105528377A (en) * 2014-10-22 2016-04-27 阿里巴巴集团控股有限公司 A processing method, device and system for search results
US20170193560A1 (en) * 2016-01-01 2017-07-06 Facebook, Inc. Pacing a budget for presenting sponsored content while limiting frequency of sponsored content presentation
CN105741133A (en) * 2016-01-26 2016-07-06 电子科技大学 Stepping management method for online advertisement delivery
CN107491986A (en) * 2017-08-02 2017-12-19 北京品友互动信息技术股份公司 For controlling the method and device of advertising budget

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈李钢: "基于赞助搜索的关键字广告最优策略研究", 《中国博士学位论文全文数据库 经济与管理科学辑》 *

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109003140A (en) * 2018-07-26 2018-12-14 腾讯科技(深圳)有限公司 Determination method, equipment and the storage medium that the dispensing of multimedia content is provided funds
CN109829749A (en) * 2018-12-28 2019-05-31 微梦创科网络科技(中国)有限公司 A kind of advertisement placement method and system
CN109829749B (en) * 2018-12-28 2021-05-28 微梦创科网络科技(中国)有限公司 Advertisement putting method and system
CN111756590B (en) * 2019-03-27 2022-04-26 北京沃东天骏信息技术有限公司 Small flow test method and device for information display flow control
CN111756590A (en) * 2019-03-27 2020-10-09 北京沃东天骏信息技术有限公司 Small flow test method and device for information display flow control
CN110264279A (en) * 2019-06-25 2019-09-20 苏州梦嘉信息技术有限公司 Management method and system are launched in a kind of advertisement
CN112150181B (en) * 2019-06-28 2024-04-16 腾讯科技(深圳)有限公司 Resource allocation method, device, equipment and storage medium
CN112150181A (en) * 2019-06-28 2020-12-29 腾讯科技(深圳)有限公司 Resource allocation method, device, equipment and storage medium
CN110348908A (en) * 2019-07-15 2019-10-18 西安点告网络科技有限公司 Budget control method and device is launched in advertisement
CN110490649B (en) * 2019-08-12 2024-03-19 上海漫酷网络技术有限公司 Uniform speed advertisement putting method and system
CN110490649A (en) * 2019-08-12 2019-11-22 上海漫酷网络技术有限公司 A kind of at the uniform velocity put-on method and system of advertisement dispensing
CN112581157B (en) * 2019-09-30 2023-10-03 百度在线网络技术(北京)有限公司 Information delivery control method, device, equipment, system and medium
CN112581157A (en) * 2019-09-30 2021-03-30 百度在线网络技术(北京)有限公司 Information delivery control method, device, equipment, system and medium
CN111612413A (en) * 2020-04-11 2020-09-01 上海淇玥信息技术有限公司 Advertisement customized delivery platform and method based on account management and electronic equipment
CN111626776A (en) * 2020-05-26 2020-09-04 创新奇智(西安)科技有限公司 Method for training strategy model, method and device for determining advertisement putting strategy
CN111626776B (en) * 2020-05-26 2024-03-08 创新奇智(西安)科技有限公司 Method for training strategy model, method and device for determining advertisement putting strategy
CN111598631A (en) * 2020-06-05 2020-08-28 上海智子信息科技股份有限公司 Cross-channel keyword price optimization method with effect target oriented
CN111815357A (en) * 2020-07-09 2020-10-23 湖南数客星球信息技术有限公司 Big data intelligent advertisement system and method based on amazon search word bank
CN111861563A (en) * 2020-07-20 2020-10-30 广元量知汇科技有限公司 Advertisement request processing method for digital marketing
CN111861563B (en) * 2020-07-20 2021-06-22 王磊 Advertisement request processing method for digital marketing
CN111861564B (en) * 2020-07-20 2021-07-13 深圳我买家网络科技有限公司 Digital advertisement transaction system
CN111861564A (en) * 2020-07-20 2020-10-30 广元量知汇科技有限公司 Digital advertisement transaction system
CN112258239A (en) * 2020-10-30 2021-01-22 北京沃东天骏信息技术有限公司 Method, device, equipment, medium and system for acquiring super-broadcast control effect data
CN113283941A (en) * 2021-06-09 2021-08-20 北京有竹居网络技术有限公司 Advertisement putting method and device, storage medium and electronic equipment
CN113283941B (en) * 2021-06-09 2023-07-11 北京有竹居网络技术有限公司 Advertisement putting method and device, storage medium and electronic equipment
CN114493660A (en) * 2021-12-24 2022-05-13 北京明略软件***有限公司 Method and device for advertisement budget allocation, electronic equipment and storage medium
CN116167804B (en) * 2023-04-19 2023-07-21 江西时刻互动科技股份有限公司 Advertisement putting method and device, computer readable storage medium and electronic equipment
CN116167804A (en) * 2023-04-19 2023-05-26 江西时刻互动科技股份有限公司 Advertisement putting method and device, computer readable storage medium and electronic equipment

Also Published As

Publication number Publication date
CN108269123B (en) 2021-03-12

Similar Documents

Publication Publication Date Title
CN108269123A (en) Control method and device are launched in advertisement
Athey et al. A structural model of sponsored search advertising auctions
CN103914468B (en) A kind of method and apparatus of impression information search
Zhang et al. Cyclical bid adjustments in search-engine advertising
Edelman et al. Optimal auction design and equilibrium selection in sponsored search auctions
CN105719010A (en) Method and device for processing distribution tasks
US20080301033A1 (en) Method and apparatus for optimizing long term revenues in online auctions
CN106296247B (en) Network information resource online ordering method and device
CN104851023A (en) Real-time bidding online feedback control method and system
CN103136311B (en) The combined optimization of bid and budget allocation in paid search
CN109615442A (en) RTB real time bid method based on excitation video ads
CN112163886B (en) Real-time bidding advertisement resource allocation method based on reinforcement learning
CN104252680B (en) Keyword automatic pricing method and search engine marketing system
US20100250362A1 (en) System and Method for an Online Advertising Exchange with Submarkets Formed by Portfolio Optimization
CN107025575A (en) Brand client KPI predictor methods in sequencing advertisement putting
WO2020104806A1 (en) Real-time bidding
US20140297401A1 (en) Shaping allocations in search advertising auctions
CN116823360B (en) Intelligent advertisement plan generation method and system based on user behaviors
US20100306210A1 (en) Clustering identical or disjoint keyword sets for use with auctions for online advertising space
CN111401943B (en) Multi-source advertisement bidding system and method
Li et al. The impact of reserve price on publisher revenue in real-time bidding advertising markets
CN107133826A (en) Click volume auction mechanism based on the price of discretization first and pro rate model
KR102513416B1 (en) Simultaneous multiple power trading method in a microgrid composed of M producers and N consumers
CN116151894A (en) Real-time bidding global optimization method and system for multi-channel search advertisement
US20120323701A1 (en) Impression allocation system and methods using an auction that considers losing bids

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20200417

Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province

Applicant after: Alibaba (China) Co.,Ltd.

Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 13 layer self unit 01

Applicant before: GUANGZHOU SHENMA MOBILE INFORMATION TECHNOLOGY Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant