CN105491410A - Method and system for distributing network video advertisement putting - Google Patents

Method and system for distributing network video advertisement putting Download PDF

Info

Publication number
CN105491410A
CN105491410A CN201510900752.8A CN201510900752A CN105491410A CN 105491410 A CN105491410 A CN 105491410A CN 201510900752 A CN201510900752 A CN 201510900752A CN 105491410 A CN105491410 A CN 105491410A
Authority
CN
China
Prior art keywords
injected volume
advertisement
video
proportion
normalization
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
CN201510900752.8A
Other languages
Chinese (zh)
Other versions
CN105491410B (en
Inventor
袁树仑
章岑
杨田
周盛
潘柏宇
王冀
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.)
1Verge Internet Technology Beijing Co Ltd
Original Assignee
1Verge Internet Technology Beijing 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 1Verge Internet Technology Beijing Co Ltd filed Critical 1Verge Internet Technology Beijing Co Ltd
Priority to CN201510900752.8A priority Critical patent/CN105491410B/en
Publication of CN105491410A publication Critical patent/CN105491410A/en
Application granted granted Critical
Publication of CN105491410B publication Critical patent/CN105491410B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
    • H04N21/26208—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints
    • H04N21/26241—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints involving the time of distribution, e.g. the best time of the day for inserting an advertisement or airing a children program
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
    • H04N21/26266—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for determining content or additional data repetition rate, e.g. of a file in a DVB carousel according to its importance

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The present application discloses a method and a system for distributing network video advertisement putting. A total amount of putting is preset for an advertisement file; related videos and unrelated videos of the advertisement file are selected; a playing flow of the related videos is a first flow, and the play click-through rate is a first click-through rate; and the method comprises the following steps: calculating a carrying capacity of the related videos to the advertisement file putting according to the first flow and the first click-through rate; when the total amount of putting is greater than the carrying capacity, distributing the amount of putting of the related videos as a first amount of putting, wherein the first amount of putting is equal to the carrying capacity; using a difference between the total amount of putting and the first amount of putting as a second amount of putting; distributing the amount of putting of the unrelated videos as the second amount of putting; putting the advertisement file in the related videos according to the first amount of putting; and putting the advertisement file in the unrelated videos according to the second amount of putting.

Description

The distribution method that a kind of network video advertisement is thrown in and system
Technical field
The application relates to Internet technical field, specifically, relates to distribution method and the system of a kind of network video advertisement input.
Background technology
Current, multimedia technology and spreading network information technology height maturation, the Internet video high number on the Internet, what contain is in extensive range.Internet video with traditional live online compared with, the sense of participation of user is stronger, watches that mode is also freer.User from main separation video, and arbitrarily can drag playing progress rate or time-out as required.Therefore pass through netcast and browsing video, become the custom of thousands of user already.
Throwing in advertisement by Internet video, is business model very ripe in Internet video field.In present stage, the quantity of advertisement and the quantity of video and video playback amount are all very huge.And in a large amount of video playback amounts, efficiently and carry out advertisement putting targetedly, the effect of advertisement putting can be improved significantly, produce larger commercial value.Throwing in advertisement so reasonably distribute, is the target needing emphasis to be optimized.
Existing advertisement putting scheme, does not weigh the relation of the many factors such as spending on ads, advertisement putting specific aim and Consumer's Experience fully, and the space so input effect still has greatly improved, needs further to be optimized.
Summary of the invention
In view of this, technical problems to be solved in this application there is provided distribution method and the system of the input of a kind of network video advertisement, realize, under the prerequisite meeting spending on ads, playing advertisement delivery effect more fully.
In order to solve the problems of the technologies described above, the application has following technical scheme:
The distribution method that network video advertisement is thrown in, sets total injected volume for promotional literature in advance; The associated video of selected described promotional literature and irrelevant video; The broadcasting flow of described associated video is first flow, and playing clicking rate is the first clicking rate; Then described method comprises:
According to described first flow and the first clicking rate, calculate the bearing capacity that described associated video is thrown in for described promotional literature; When described total injected volume is greater than described bearing capacity, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity;
Using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume;
According to described first injected volume, described promotional literature is rendered on associated video; According to described second injected volume, promotional literature is rendered on irrelevant video.
Preferably, the broadcasting flow of described irrelevant video is the second flow, and playing clicking rate is the second clicking rate; Then described method also comprises:
According to described second flow, the second clicking rate and the second injected volume, calculate the minimum of the second input probability parameter; And the minimum throwing in probability parameter using described second is as the input probability parameter of described promotional literature on irrelevant video.
Preferably, described according to described first flow and the first clicking rate, calculate the bearing capacity that described associated video throws in for described promotional literature and be specially:
cf vv*cf ctr*cf prob＝cf click；
Wherein, described cf vvrepresent first flow, cf ctrrepresent the first clicking rate; Cf probfor the input probability parameter of promotional literature on associated video preset; Cf clickfor bearing capacity.
Preferably, the input probability parameter of described promotional literature on associated video is 1.
Preferably, described according to described second flow, the second clicking rate and the second injected volume, the minimum calculating the second input probability parameter is specially:
random vv*random ctr*random prob＝random click；
Wherein, described random vvrepresent the second flow, random ctrrepresent the second clicking rate; Random probit is the minimum of the second input probability parameter; Random clickit is the second injected volume.
Preferably, when an Internet video is as the associated video of multiple promotional literature, then described method also comprises:
The multiple promotional literatures corresponding for this associated video are normalized calculating, obtain the input probability of each promotional literature on this associated video.
Preferably, described normalization calculates and is specially:
The injected volume proportion of each advertisement is calculated according to total injected volume of each promotional literature; And the correlation proportion of each advertisement is calculated according to the relative coefficient of each promotional literature;
Utilize described injected volume proportion and correlation proportion, calculate the normalization proportion of each advertisement;
The normalization proportion of each advertisement is normalized, obtains the normalization probability of each advertisement; And using the normalization probability of each advertisement as the input probability of this advertisement on this associated video.
Preferably, when an Internet video is total to the associated video of n advertisement as advertisement ad1 ~ advertisement adn, then the injected volume proportion of each advertisement of described calculating, and the correlation proportion calculating each advertisement is specially:
si 1 = c l i c k i Σ i = 1 n c l i c k i si 2 = s c o r e i Σ i = 1 n s c o r e i ; i = 1 ~ n Arbitrary integer;
Wherein, si 1the injected volume proportion of adi, si 2adi correlation proportion; Clicki is total injected volume of adi; Scorei is the relative coefficient of adi.
Preferably, the normalization proportion of each advertisement of described calculating, is normalized the normalization proportion of each advertisement, and the normalization probability obtaining each advertisement is specially:
si＝si 1*si 2； p i = s i Σ i = 1 n s i
Wherein, si is the normalization proportion of adi, and pi is the normalization probability of adi.
The distribution system that network video advertisement is thrown in, sets total injected volume for promotional literature in advance; The associated video of selected described promotional literature and irrelevant video; The broadcasting flow of described associated video is first flow, and playing clicking rate is the first clicking rate; Then described system comprises:
Relevant distribution module, for according to described first flow and the first clicking rate, calculates the bearing capacity that described associated video is thrown in for described promotional literature; When described total injected volume is greater than described bearing capacity, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity;
Irrelevant distribution module, for using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume;
Putting module, for rendering to associated video according to described first injected volume by described promotional literature; According to described second injected volume, promotional literature is rendered on irrelevant video.
Preferably, the broadcasting flow of described irrelevant video is the second flow, and playing clicking rate is the second clicking rate; Then described irrelevant distribution module also for:
According to described second flow, the second clicking rate and the second injected volume, calculate the minimum of the second input probability parameter; And the minimum throwing in probability parameter using described second is as the input probability parameter of described promotional literature on irrelevant video.
Preferably, described system also comprises:
Normalization module, during for the associated video of an Internet video as multiple promotional literature, the multiple promotional literatures corresponding for this associated video are normalized calculating, obtain the input probability of each promotional literature on this associated video.
Preferably, described normalization module comprises:
Proportion module, for calculating the injected volume proportion of each advertisement according to total injected volume of each promotional literature; And the correlation proportion of each advertisement is calculated according to the relative coefficient of each promotional literature;
Normalization module, for utilizing described injected volume proportion and correlation proportion, calculates the normalization proportion of each advertisement; The normalization proportion of each advertisement is normalized, obtains the normalization probability of each advertisement; And using the normalization probability of each advertisement as the input probability of this advertisement on this associated video.
Preferably, when an Internet video is total to the associated video of n advertisement as advertisement ad1 ~ advertisement adn, then the injected volume proportion of each advertisement of described calculating, and the correlation proportion calculating each advertisement is specially:
si 1 = c l i c k i Σ i = 1 n c l i c k i ; si 2 = s c o r e i Σ i = 1 n s c o r e i ; i = 1 ~ n Arbitrary integer;
Wherein, si 1the injected volume proportion of adi, si 2adi correlation proportion; Clicki is total injected volume of adi; Scorei is the relative coefficient of adi.
Preferably, the normalization proportion of each advertisement of described calculating, is normalized the normalization proportion of each advertisement, and the normalization probability obtaining each advertisement is specially:
si＝si 1*si 2； p i = s i Σ i = 1 n s i
Wherein, si is the normalization proportion of adi, and pi is the normalization probability of adi.
Compared with prior art, the method and system described in the application, reaches following effect:
Make the injected volume that associated video distributes reach maximum, improve the specific aim of advertisement putting; Under the prerequisite meeting total injected volume, by the input probability parameter of promotional literature on irrelevant video, namely the second input probability parameter is adjusted to minimum, avoids advertisement putting to the interference of user as much as possible, improves Consumer's Experience; Calculated by normalization, achieve the equilibrium assignment of associated video for multiple advertisement.
Certainly, the arbitrary product implementing the application must not necessarily need to reach above-described all technique effects simultaneously.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide further understanding of the present application, and form a application's part, the schematic description and description of the application, for explaining the application, does not form the improper restriction to the application.In the accompanying drawings:
Fig. 1 is method flow diagram described in the embodiment of the present application;
Fig. 2 is method flow diagram described in another embodiment of the application;
Fig. 3 is method flow diagram described in the another embodiment of the application;
Fig. 4 is system configuration schematic diagram described in the embodiment of the present application.
Embodiment
As employed some vocabulary to censure specific components in the middle of specification and claim.Those skilled in the art should understand, and hardware manufacturer may call same assembly with different noun.This specification and claims are not used as with the difference of title the mode distinguishing assembly, but are used as the criterion of differentiation with assembly difference functionally." comprising " as mentioned in the middle of specification and claim is in the whole text an open language, therefore should be construed to " comprise but be not limited to "." roughly " refer to that in receivable error range, those skilled in the art can solve the technical problem within the scope of certain error, reach described technique effect substantially.In addition, " couple " word and comprise directly any and indirectly electric property coupling means at this.Therefore, if describe a first device in literary composition to be coupled to one second device, then represent described first device and directly can be electrically coupled to described second device, or be indirectly electrically coupled to described second device by other devices or the means that couple.Specification subsequent descriptions is implement the better embodiment of the application, and right described description is for the purpose of the rule that the application is described, and is not used to the scope limiting the application.The protection range of the application is when being as the criterion depending on the claims person of defining.
In current business model, be generally manufacturer just first advertisement buy certain injected volume to the operator of Internet video, in the process that then operator is play in its Internet video of runing, throw in this advertisement and reach the injected volume that manufacturer buys.Such as vendor A have purchased 10 with regard to advertisement ad0 to operator B, the injected volume of 000 times/day; And the all-network video that operator B runs, total broadcasting flow is 1,000,000 times/day; Then operator B needs within one day, 1, throws in 10,000 advertisement ad0 in the broadcasting of 000,000 time.
In order to improve the specific aim of advertisement putting, nearly all advertisement putting is not evenly throw in or throw at random, but emphasis by advertisement putting on the partial video relevant to ad content.Further, in order to reduce the impact of advertisement putting on user's normal play video, also input probability parameter can be set, realize probabilisticly in broadcasting carrying out advertisement putting.Throw in probability parameter value between 0 ~ 1, mean that value higher then input probability is higher, under identical broadcasting total amount, operator can bear larger injected volume; But user has to watch more advertisements, causes Consumer's Experience low.Vice versa, reduces to throw in probability parameter then the injected volume that can bear of operator is less, but Consumer's Experience is higher.
Visible, in the process of advertisement putting, always play the factors such as flow, injected volume, video correlation and Consumer's Experience, completely can have an impact to the effect of this business model.And in actual applications, number of ads, injected volume and total to play flow number huge, the analysis of advertisement and video correlation also unusual diversification; These all allow advertisement putting become very complicated.
Present stage is more undesirable for the distribution effects of advertisement putting, and balance is not fully to above-mentioned many factors, so still there is very large optimization space.
In the application, disclosing the distribution method that a kind of network video advertisement is thrown in, by more reasonably distributing the effect improving advertisement putting, ensureing under the prerequisite of injected volume, take into account and throw in specific aim and Consumer's Experience.
Shown in Figure 1, be the specific embodiment of method described in the application.Can in conjunction with following application scenarios at the concrete scheme of the present embodiment: the operator of Internet video sets total injected volume for specific promotional literature in advance.Simultaneously based on the content of this advertisement, distribution coupling is carried out to runed a large amount of Internet videos, the associated video that selected described promotional literature is corresponding.There is certain relevance in advertisement and associated video, the product namely browsing the user of associated video often also corresponding to this advertisement has demand in terms of content.
Such as, the associated video of sports goods series advertisements can be sport category program; Or the associated video of toiletries advertisement can be variety show or TV play.The selected of associated video based on existing large data analysis, can not do concrete restriction at this, and every scheme that can realize similar effect all can be combined under the overall technical architecture of the present embodiment.And other videos beyond associated video, all belong to irrelevant video.
In the present embodiment, illustrating for the ease of explaining, can suppose there is advertisement ad1, total injected volume t of described advertisement ad1 click=1000 times/day.It is v1 ~ v10 respectively that operator runs 10 videos altogether.Wherein v1 and v2 is associated video, and other are non-associated videos.
Obviously, by advertisement putting on associated video, there is better specific aim, more excellent advertising effect can be played.But aforementioned known, associated video often can not carry all injected volumes of this advertisement, so a part of injected volume has to render on irrelevant video.For convenience of explanation, the concept that the present embodiment is set as follows in the de-scription: the broadcasting flow of described associated video is first flow, playing clicking rate is the first clicking rate; The broadcasting flow of described irrelevant video is the second flow, and playing clicking rate is the second clicking rate.
Described in the present embodiment, method comprises the following steps:
Step 101, according to described first flow and the first clicking rate, calculate the bearing capacity that described associated video is thrown in for described promotional literature.
In order to be assigned on associated video by more spending on ads as far as possible, to improve the specific aim of input, in the present embodiment, first-selection will calculate the maximum bearing capacity of associated video for advertisement putting.The account form of bearing capacity is specific as follows:
cf vv*cf ctr*cf prob＝cf click。
Wherein, described cf vvrepresent first flow, cf ctrrepresent the first clicking rate; Cf probfor the input probability parameter of promotional literature on associated video preset; Cf clickfor bearing capacity.
Can think in theory, on large Internet video platform, the broadcasting flow of video and clicking rate are all metastable, float very little.Can with reference to actual value first the previous day so play flow and clicking rate, or the average of previous some days.In the present embodiment, get cf vvnamely the broadcasting flow of video v1 and v2 is 50,000 times/day, cf ctr1.2%.
It should be noted that, cf probit is the input probability parameter set for associated video.Because the user browsing associated video has demand to this advertisement most probably, throw in this advertisement to this part user relatively little on the impact of Consumer's Experience.So cf probcan be arranged to large numerical value as far as possible, in the present embodiment, value is maximum 1.
Then can calculate in theory, cf in the present embodiment clickit is 600 times/day.Namely mean that advertisement ad1 is on associated video v1 and v2, can throw in 600 times/day at most.
Step 102, be greater than described bearing capacity when described total injected volume, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity.
Obvious t click> cf click, illustrate that the bearing capacity of associated video cannot meet whole input demands, remaining part injected volume must be born by irrelevant video.In the present embodiment, the injected volume being assigned to associated video is called as the first injected volume.Make described first injected volume=cf click=600 times/day, many as far as possible to ensure the injected volume on associated video, the specific aim that video is thrown in reaches best.
Step 103, using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume.
The part injected volume that associated video cannot be born, namely the injected volume that must be assigned on irrelevant video is called as the second injected volume.Second injected volume described in the present embodiment=t click-cf click=400 times/day.That is, on irrelevant video v3 ~ v10,400 advertisement ad1 must be thrown in every day.
Step 104, according to described first injected volume, described promotional literature is rendered on associated video; According to described second injected volume, promotional literature is rendered on irrelevant video.
After the concrete numerical value determining described first injected volume and the second injected volume, described promotional literature can be rendered on associated video according to described first injected volume; According to described second injected volume, promotional literature is rendered on irrelevant video.Follow-up in the broadcasting of video, namely can play flow realizes advertisement actual input as carrier.
Carry out the distribution of advertisement putting thus, probability can meet total injected volume t clicksetting, ensure that the first injected volume is maximum as far as possible simultaneously.As seen through the above technical solutions, the beneficial effect that the present embodiment exists is: make the injected volume that associated video distributes reach maximum, improve the specific aim of advertisement putting.
Shown in Figure 2, be another specific embodiment of method described in the application, the present embodiment, on basis embodiment illustrated in fig. 1, is further optimized the advertisement putting of irrelevant video, and Consumer's Experience is improved.Described in the present embodiment, method comprises the following steps:
Step 201, according to described first flow and the first clicking rate, calculate the bearing capacity that described associated video is thrown in for described promotional literature.
Step 202, be greater than described bearing capacity when described total injected volume, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity.
Step 203, using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume.
Step 204, according to described first injected volume, described promotional literature is rendered on associated video; According to described second injected volume, promotional literature is rendered on irrelevant video.
Said process and embodiment illustrated in fig. 1 completely the same.
Step 205, according to described second flow, the second clicking rate and the second injected volume, calculate the minimum of the second input probability parameter; And the minimum throwing in probability parameter using described second is as the input probability parameter of described promotional literature on irrelevant video.
It should be noted that, be different from and throw in advertisement on associated video, after irrelevant video throws in advertisement, the user browsing irrelevant video may not have demand to this advertisement.Otherwise the advertisement on irrelevant video often causes bad impact to Consumer's Experience, user is hindered to play normally and browsing video.So in order to improve Consumer's Experience, under the prerequisite having met the second injected volume, the input probability parameter on irrelevant video should be arranged to lower numerical value as much as possible.
In the present embodiment, by aforementioned the second injected volume calculated, and the second flow obtained by Internet video platform and the second clicking rate, calculate the minimum of the input probability parameter on irrelevant video.Specific as follows:
random vv*random ctr*random prob＝random click；
Wherein, described random vvrepresent the second flow, random ctrrepresent the second clicking rate; Random probit is the minimum of the second input probability parameter; Random clickit is the second injected volume.
This formula is identical principle with the formula of aforementioned calculating associated video bearing capacity.Described second flow also can be identical with previous embodiment with the principle that obtains of the second clicking rate; Or, can first flow be deducted by the total flow of the Internet video platform overall situation and obtain described second flow.
Known with reference to previous embodiment, described second injected volume random click=400, value random from Internet video platform in addition vv=1,100,000 times/day, random ctr=0.1%.
Obviously, irrelevant number of videos is more than associated video, so the second flow is often greater than first flow; But the advertisement putting specific aim on irrelevant video is poor, so the second clicking rate is far below the first clicking rate.
Then by can random be calculated above prob=0.36.Namely mean when certain irrelevant video playback have the probability of 36% to throw in advertisement ad1 along with the broadcasting of this video, the probability of other 64% is then do not throw in any advertisement, and play-overs this video.Just total injected volume t can be met on probability thus click, simultaneously by random probbe set to minimum.
As seen through the above technical solutions, the beneficial effect that the present embodiment exists is: under the prerequisite meeting total injected volume, by the input probability parameter of promotional literature on irrelevant video, namely the second input probability parameter is adjusted to minimum, avoid advertisement putting to the interference of user as much as possible, improve Consumer's Experience.
In the illustrated embodiment of Fig. 1 ~ 2, all data are all for the ease of explaining the mathematical relationship illustrated wherein, and hypothesis produces.In practical situations both, True Data is necessarily complicated.And often there is the situation of a video as the associated video of multiple advertisement.Such as there is the video vn of a sports cast, simultaneously advertisement ad1 and ad2 of two sports goods classes again.Find through overmatching classification, in the associated video of advertisement ad1 and ad2, included video vn.
Under similar complicated situation, the present embodiment, by the basis of Fig. 1 ~ 2 illustrated embodiment, further proposes a solution.With reference to shown in Fig. 3, specific as follows:
The multiple promotional literatures corresponding for this associated video are normalized calculating, obtain the input probability of each promotional literature on this associated video.Described normalization calculates, and specifically according to total injected volume of each promotional literature, and the relative coefficient of each promotional literature and this associated video is normalized calculating, obtains the input probability of each promotional literature on this associated video.
Specifically, the total injected volume determining each advertisement is needed.Suppose total injected volume click1=1000 of advertisement ad1, total injected volume click2=1200 of advertisement ad2.Also need evaluation advertisement ad1 and ad2 for the relative coefficient of video vn, suppose the relative coefficient score1=0.68 of advertisement ad1, the relative coefficient score2=0.95 of advertisement ad2.The process being normalized calculating is on this basis as follows:
Step 301, calculate the injected volume proportion si of each advertisement 1.
Concrete formula is as follows:
n=2 in the present embodiment, in other words i=1 or 2.
Calculate the injected volume proportion s1 of advertisement ad1 1=0.45; The injected volume proportion s2 of advertisement ad2 1=0.55.
Step 302, calculate the correlation proportion si of each advertisement 2.
Concrete formula is as follows:
n=2 in the present embodiment, in other words i=1 or 2.
Calculate the correlation proportion s1 of advertisement ad1 2=0.42; The correlation proportion s2 of advertisement ad2 2=0.58.
Step 303, calculate the normalization proportion si of each advertisement.
Concrete formula is as follows:
Si=si 1* si 2; I=1 or 2 in the present embodiment.
The i.e. normalization proportion s1=0.45*0.42 ≈ 0.19 of advertisement ad1;
The normalization proportion s2=0.55*0.58 ≈ 0.32 of advertisement ad2.
Step 304, calculate the normalization Probability p i of each advertisement.
Concrete formula is as follows:
n=2 in the present embodiment, in other words i=1 or 2.
Finally calculate, p1=37.2%, p2=62.8%.That is to say bright, if throw in advertisement as associated video, video vn is that the probability of 37.2% throws in advertisement ad1 once playing, and the probability of 62.8% throws in advertisement ad2.Thus, the equilibrium assignment of associated video for multiple advertisement is achieved.
As seen through the above technical solutions, the beneficial effect that the present embodiment exists is: calculated by normalization, achieve the equilibrium assignment of associated video for multiple advertisement, make the overall technical architecture of the application more complete, open more abundant.
Shown in Figure 4, be the specific embodiment of system described in the application.System described in the present embodiment is for realizing the method described in the illustrated embodiment of Fig. 1 ~ 3.Its technical scheme is consistent with Fig. 1 ~ 3 illustrated embodiment in essence.Corresponding description in previous embodiment is equally applicable in the present embodiment.In the present embodiment, set total injected volume for promotional literature in advance; The associated video of selected described promotional literature and irrelevant video; The broadcasting flow of described associated video is first flow, and playing clicking rate is the first clicking rate; The broadcasting flow of described irrelevant video is the second flow, and playing clicking rate is the second clicking rate.
Then described system comprises:
Relevant distribution module 401, for according to described first flow and the first clicking rate, calculates the bearing capacity that described associated video is thrown in for described promotional literature; When described total injected volume is greater than described bearing capacity, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity.
Irrelevant distribution module 402, for using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume.
Described irrelevant distribution module 402 also for: according to described second flow, the second clicking rate and the second injected volume, calculate the minimum of the second input probability parameter; And the minimum throwing in probability parameter using described second is as the input probability parameter of described promotional literature on irrelevant video.
Putting module 403, for rendering to associated video according to described first injected volume by described promotional literature; According to described second injected volume, promotional literature is rendered on irrelevant video.
Normalization module 404 (not shown), during for the associated video of an Internet video as multiple promotional literature, the multiple promotional literatures corresponding for this associated video are normalized calculating, obtain the input probability of each promotional literature on this associated video.
As seen through the above technical solutions, the beneficial effect that the present embodiment exists is: make the injected volume that associated video distributes reach maximum, improve the specific aim of advertisement putting; Under the prerequisite meeting total injected volume, by the input probability parameter of promotional literature on irrelevant video, namely the second input probability parameter is adjusted to minimum, avoids advertisement putting to the interference of user as much as possible, improves Consumer's Experience; Calculated by normalization, achieve the equilibrium assignment of associated video for multiple advertisement.
Those skilled in the art should understand, the embodiment of the application can be provided as method, device or computer program.Therefore, the application can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the application can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disc store, CD-ROM, optical memory etc.) of computer usable program code.
Above-mentioned explanation illustrate and describes some preferred embodiments of the application, but as previously mentioned, be to be understood that the application is not limited to the form disclosed by this paper, should not regard the eliminating to other embodiments as, and can be used for other combinations various, amendment and environment, and can in invention contemplated scope described herein, changed by the technology of above-mentioned instruction or association area or knowledge.And the change that those skilled in the art carry out and change do not depart from the spirit and scope of the application, then all should in the protection range of the application's claims.

Claims (15)

1. a distribution method for network video advertisement input, is characterized in that, set total injected volume in advance for promotional literature; The associated video of selected described promotional literature and irrelevant video; The broadcasting flow of described associated video is first flow, and playing clicking rate is the first clicking rate; Then described method comprises:
According to described first flow and the first clicking rate, calculate the bearing capacity that described associated video is thrown in for described promotional literature; When described total injected volume is greater than described bearing capacity, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity;
Using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume;
According to described first injected volume, described promotional literature is rendered on associated video; According to described second injected volume, promotional literature is rendered on irrelevant video.
2. method according to claim 1, it is characterized in that, the broadcasting flow of described irrelevant video is the second flow, and playing clicking rate is the second clicking rate; Then described method also comprises:
According to described second flow, the second clicking rate and the second injected volume, calculate the minimum of the second input probability parameter; And the minimum throwing in probability parameter using described second is as the input probability parameter of described promotional literature on irrelevant video.
3. method according to claim 1, is characterized in that, described according to described first flow and the first clicking rate, calculates the bearing capacity that described associated video throws in for described promotional literature and is specially:
cf vv*cf ctr*cf prob＝cf click；
Wherein, described cf vvrepresent first flow, cf ctrrepresent the first clicking rate; Cf probfor the input probability parameter of promotional literature on associated video preset; Cf clickfor bearing capacity.
4. method according to claim 3, it is characterized in that, the input probability parameter of described promotional literature on associated video is 1.
5. method according to claim 2, it is characterized in that, described according to described second flow, the second clicking rate and the second injected volume, the minimum calculating the second input probability parameter is specially:
random vv*random ctr*random prob＝random click；
Wherein, described random vvrepresent the second flow, random ctrrepresent the second clicking rate; Random probit is the minimum of the second input probability parameter; Random clickit is the second injected volume.
6. method according to Claims 1 to 5 any one, is characterized in that, when an Internet video is as the associated video of multiple promotional literature, then described method also comprises:
The multiple promotional literatures corresponding for this associated video are normalized calculating, obtain the input probability of each promotional literature on this associated video.
7. method according to claim 6, is characterized in that, described normalization calculates and is specially:
The injected volume proportion of each advertisement is calculated according to total injected volume of each promotional literature; And the correlation proportion of each advertisement is calculated according to the relative coefficient of each promotional literature;
Utilize described injected volume proportion and correlation proportion, calculate the normalization proportion of each advertisement;
The normalization proportion of each advertisement is normalized, obtains the normalization probability of each advertisement; And using the normalization probability of each advertisement as the input probability of this advertisement on this associated video.
8. method according to claim 7, is characterized in that, when an Internet video is as the associated video of advertisement ad1 ~ advertisement adn n advertisement altogether, then and the injected volume proportion of each advertisement of described calculating, and the correlation proportion calculating each advertisement is specially:
si 1 = c l i c k i Σ i = 1 n c l i c k i ; si 2 = s c o r e i Σ i = 1 n s c o r e i ; I=1 ~ n arbitrary integer;
Wherein, si 1the injected volume proportion of adi, si 2adi correlation proportion; Clicki is total injected volume of adi; Scorei is the relative coefficient of adi.
9. method according to claim 8, it is characterized in that the normalization proportion of each advertisement of described calculating is normalized the normalization proportion of each advertisement, the normalization probability obtaining each advertisement is specially:
s i = si 1 * si 2 ; p i = s i Σ i = 1 n s i
Wherein, si is the normalization proportion of adi, and pi is the normalization probability of adi.
10. a distribution system for network video advertisement input, is characterized in that, set total injected volume in advance for promotional literature; The associated video of selected described promotional literature and irrelevant video; The broadcasting flow of described associated video is first flow, and playing clicking rate is the first clicking rate; Then described system comprises:
Relevant distribution module, for according to described first flow and the first clicking rate, calculates the bearing capacity that described associated video is thrown in for described promotional literature; When described total injected volume is greater than described bearing capacity, then distributing injected volume to described associated video is the first injected volume, and described first injected volume equals bearing capacity;
Irrelevant distribution module, for using the difference of described total injected volume and the first injected volume as the second injected volume; Be then the second injected volume to described irrelevant video distribution injected volume;
Putting module, for rendering to associated video according to described first injected volume by described promotional literature; According to described second injected volume, promotional literature is rendered on irrelevant video.
11. systems according to claim 10, it is characterized in that, the broadcasting flow of described irrelevant video is the second flow, and playing clicking rate is the second clicking rate; Then described irrelevant distribution module also for:
According to described second flow, the second clicking rate and the second injected volume, calculate the minimum of the second input probability parameter; And the minimum throwing in probability parameter using described second is as the input probability parameter of described promotional literature on irrelevant video.
12. according to claim 10 or 11 system, it is characterized in that, described system also comprises:
Normalization module, during for the associated video of an Internet video as multiple promotional literature, the multiple promotional literatures corresponding for this associated video are normalized calculating, obtain the input probability of each promotional literature on this associated video.
13., according to system described in claim 12, is characterized in that, described normalization module comprises:
Proportion module, for calculating the injected volume proportion of each advertisement according to total injected volume of each promotional literature; And the correlation proportion of each advertisement is calculated according to the relative coefficient of each promotional literature;
Normalization module, for utilizing described injected volume proportion and correlation proportion, calculates the normalization proportion of each advertisement; The normalization proportion of each advertisement is normalized, obtains the normalization probability of each advertisement; And using the normalization probability of each advertisement as the input probability of this advertisement on this associated video.
14., according to system described in claim 13, is characterized in that, when an Internet video is total to the associated video of n advertisement as advertisement ad1 ~ advertisement adn, then and the injected volume proportion of each advertisement of described calculating, and the correlation proportion calculating each advertisement is specially:
si 1 = c l i c k i Σ i = 1 n c l i c k i ; si 2 = s c o r e i Σ i = 1 n s c o r e i ; I=1 ~ n arbitrary integer;
Wherein, si 1the injected volume proportion of adi, si 2adi correlation proportion; Clicki is total injected volume of adi; Scorei is the relative coefficient of adi.
15., according to system described in claim 14, is characterized in that, the normalization proportion of each advertisement of described calculating, are normalized the normalization proportion of each advertisement, and the normalization probability obtaining each advertisement is specially:
s i = si 1 * si 2 ; p i = s i Σ i = 1 n s i
Wherein, si is the normalization proportion of adi, and pi is the normalization probability of adi.
CN201510900752.8A 2015-12-09 2015-12-09 A kind of distribution method and system that network video advertisement is launched Expired - Fee Related CN105491410B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510900752.8A CN105491410B (en) 2015-12-09 2015-12-09 A kind of distribution method and system that network video advertisement is launched

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510900752.8A CN105491410B (en) 2015-12-09 2015-12-09 A kind of distribution method and system that network video advertisement is launched

Publications (2)

Publication Number Publication Date
CN105491410A true CN105491410A (en) 2016-04-13
CN105491410B CN105491410B (en) 2018-10-23

Family

ID=55678074

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510900752.8A Expired - Fee Related CN105491410B (en) 2015-12-09 2015-12-09 A kind of distribution method and system that network video advertisement is launched

Country Status (1)

Country Link
CN (1) CN105491410B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107197337A (en) * 2017-05-05 2017-09-22 中广热点云科技有限公司 The method of the stage conveying additional data of streaming media
WO2018149371A1 (en) * 2017-02-15 2018-08-23 腾讯科技（深圳）有限公司 Flow and service allocation method and apparatus for push information order, and storage medium
CN108965936A (en) * 2017-05-17 2018-12-07 腾讯科技（深圳）有限公司 A kind of control method for playing back of media information, server and computer storage medium
CN110322264A (en) * 2018-03-30 2019-10-11 广州市动景计算机科技有限公司 Ad traffic control method and device
CN116151889A (en) * 2023-04-04 2023-05-23 上员品牌数智科技(深圳)有限公司 Intelligent video advertisement delivery system and method based on big data

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542438A (en) * 2011-12-31 2012-07-04 北京亿赞普网络技术有限公司 Network advertising serving scheduling system and scheduling method
CN102592235A (en) * 2011-12-28 2012-07-18 北京品友互动信息技术有限公司 Internet advertisement serving system
CN102708496A (en) * 2012-01-09 2012-10-03 合一网络技术(北京)有限公司 Adaptive video advertisement release method and device
WO2014078995A1 (en) * 2012-11-21 2014-05-30 Google Inc. System and method for calculating predicted measure of content performance
CN104636954A (en) * 2014-12-08 2015-05-20 北京掌阔技术有限公司 Data mining method and data mining device for advertising media putting quantity

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102592235A (en) * 2011-12-28 2012-07-18 北京品友互动信息技术有限公司 Internet advertisement serving system
CN102542438A (en) * 2011-12-31 2012-07-04 北京亿赞普网络技术有限公司 Network advertising serving scheduling system and scheduling method
CN102708496A (en) * 2012-01-09 2012-10-03 合一网络技术(北京)有限公司 Adaptive video advertisement release method and device
WO2014078995A1 (en) * 2012-11-21 2014-05-30 Google Inc. System and method for calculating predicted measure of content performance
CN104636954A (en) * 2014-12-08 2015-05-20 北京掌阔技术有限公司 Data mining method and data mining device for advertising media putting quantity

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018149371A1 (en) * 2017-02-15 2018-08-23 腾讯科技（深圳）有限公司 Flow and service allocation method and apparatus for push information order, and storage medium
CN107197337A (en) * 2017-05-05 2017-09-22 中广热点云科技有限公司 The method of the stage conveying additional data of streaming media
CN107197337B (en) * 2017-05-05 2019-07-05 中广热点云科技有限公司 The method of the stage conveying additional data of streaming media
CN108965936A (en) * 2017-05-17 2018-12-07 腾讯科技（深圳）有限公司 A kind of control method for playing back of media information, server and computer storage medium
CN108965936B (en) * 2017-05-17 2021-05-11 腾讯科技（深圳）有限公司 Media information playing control method, server and computer storage medium
CN110322264A (en) * 2018-03-30 2019-10-11 广州市动景计算机科技有限公司 Ad traffic control method and device
CN116151889A (en) * 2023-04-04 2023-05-23 上员品牌数智科技(深圳)有限公司 Intelligent video advertisement delivery system and method based on big data
CN116151889B (en) * 2023-04-04 2023-06-20 上员品牌数智科技(深圳)有限公司 Intelligent video advertisement delivery system and method based on big data

Also Published As

Publication number Publication date
CN105491410B (en) 2018-10-23

Similar Documents

Publication Publication Date Title
CN105491410A (en) Method and system for distributing network video advertisement putting
CA2700030C (en) Touchpoint customization system
WO2010078539A2 (en) Advertising profiling and targeting system
CN110225361A (en) Direct broadcasting room recommended method, storage medium, electronic equipment and system
US20100262465A1 (en) Method and system for awarding user points in response to user interest
CN108476344A (en) The content selection of networked media device
CN108965936A (en) A kind of control method for playing back of media information, server and computer storage medium
CN104967690A (en) Information push method and device
Abdollahpouri et al. Multiple stakeholders in music recommender systems
Weber Reconfiguring Chinese propaganda and control modalities: a case study of Shanghai's television system
Chalaby Global streamers: Placing the transnational at the heart of TV culture
KR20130041305A (en) Access to media bites
CN108769817A (en) Program commending method and system
Esser Audio-visual content in the EU: Production and scheduling
Sadq Analysising Netflix‟ s Strategy
Abiola Reviewing Nollywood
Kenny et al. Securing the future of UK animation
Song et al. Development of New Variables Affecting Movie Success and Prediction of Weekly Box Office Using Them Based on Machine Learning
Breiner The economics of accountability journalism: what price is right
Medina et al. Market Structure and Innovation Policies in Spain
Feng et al. Goodwill and system dynamics modeling for film investment decision by interactive efforts
Brousseau The economics of music production: The narrow paths for record companies to enter the digital era
Team Disintermediating the Broadcast Industry by Establishing a Blockchain-Based Television Ecosystem
CN108540853A (en) Advertisement placement method and device
Berbeglia Strategies and Implications of Entertainment Media Consumption

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 100080 A 5 C, block A, China International Steel Plaza, 8 Haidian Avenue, Haidian District, Beijing.

Applicant after: Youku network technology (Beijing) Co., Ltd.

Address before: 100080 A 5 C, block A, China International Steel Plaza, 8 Haidian Avenue, Haidian District, Beijing.

Applicant before: 1Verge Inc.

GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20181023

Termination date: 20181209