CN107590689A - A kind of ad data recommends method and system - Google Patents
A kind of ad data recommends method and system Download PDFInfo
- Publication number
- CN107590689A CN107590689A CN201710744931.6A CN201710744931A CN107590689A CN 107590689 A CN107590689 A CN 107590689A CN 201710744931 A CN201710744931 A CN 201710744931A CN 107590689 A CN107590689 A CN 107590689A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- targeted advertisements
- characteristic information
- showing advertisement
- 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
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of ad data to recommend method and system.Methods described includes：After user is received to the browse request of targeted advertisements data, obtain the user's characteristic information of the user, the relevance predication model that user's characteristic information input is pre-established, obtain each showing advertisement form of the targeted advertisements data and the degree of correlation of the browse request, the targeted advertisements data recommendation of the showing advertisement form of preparatory condition will be met to the user comprising the degree of correlation, because the embodiment of the present invention is to determine showing advertisement form according to the user's characteristic information of user, and then determine the ad data recommended, therefore interest of the user to the ad data of displaying is improved, improve Consumer's Experience, reduce the low invalid exposure of ad data clicking rate.
Description
Technical field
The present invention relates to areas of information technology, more particularly to a kind of ad data recommends method, and a kind of ad data
Commending system.
Background technology
With the development of network technology, in the production that the progress product introduction of network media promulgating advertisement has been commonly used as businessman
Product publicity measures.The ad data issued on the network media can be including a variety of, if picture-text advertisement, video ads, word are with regarding
Advertisement that frequency combines etc., the advertisement that user can be shown by checking on the network media obtain product information.
At present, some video ads include multiple showing advertisement forms with different advertising creatives, different showing advertisements
Form can produce different the effect of publicity for different user.In the prior art, the network media receives a certain video ads
After playing instruction, a showing advertisement form can be randomly selected from multiple showing advertisement forms of the video ads, then will
The video ads of showing advertisement form comprising selection are illustrated on the network media, but launched and shown using the above method
Video ads are often that user is uninterested, cause advertisement delivery effect poor.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
The ad data for stating problem recommends method and corresponding ad data commending system.
According to one aspect of the present invention, there is provided a kind of ad data recommends method, and methods described includes：
After user is received to the browse request of targeted advertisements data, the user's characteristic information of the user is obtained；
The relevance predication model that user's characteristic information input is pre-established, obtains the targeted advertisements data
The degree of correlation of each showing advertisement form and the browse request；
The targeted advertisements data recommendation of the showing advertisement form of preparatory condition will be met to the user comprising the degree of correlation.
Alternatively, the relevance predication model obtains in the following manner：
Extract the first ad data usage log of record in the first historical period；
History light exposure is found out from the first ad data usage log more than light exposure threshold value comprising multiple
The targeted advertisements data of showing advertisement form, and extract at least one use of targeted advertisements data described in historical viewings
The user's characteristic information at family；
According to multiple showing advertisement forms of the targeted advertisements data and the user characteristics of at least one user
Information, machine learning relevancy algorithm is trained to obtain relevance predication model.
Alternatively, before the user's characteristic information for obtaining the user, methods described also includes：
Judge whether to establish relevance predication model for the targeted advertisements data；
If it is, the step of performing the user's characteristic information of the acquisition user.
If it is not, then using the smooth clicking rate statistical model pre-established, each wide of the targeted advertisements data is calculated
Accuse the smooth clicking rate for showing form, and the targeted advertisements data that the showing advertisement form for meeting default clicking rate condition will be included
Recommend the user.
Alternatively, it is described using the smooth clicking rate statistical model pre-established, calculate each of the targeted advertisements data
The smooth clicking rate of showing advertisement form includes：
The the second ad data usage log recorded in the second historical period before extracting current date；
From the second ad data usage log, each showing advertisement form for extracting the targeted advertisements data is gone through
History light exposure and history click volume；
The smooth clicking rate that the history light exposure of each showing advertisement form and the input of history click volume are pre-established
Statistical model, obtain the smooth clicking rate of each showing advertisement form；The duration of second historical period is gone through more than described first
The duration of history period.
Alternatively, the user's characteristic information for obtaining the user includes：
Extract the daily record that the 3rd ad data of record in the 3rd historical period uses；
In the daily record used from the 3rd ad data, the user's characteristic information of the user is found out.
Alternatively, it is described to give the targeted advertisements data recommendation comprising the showing advertisement form for meeting default degree of correlation condition
The user includes：
Give the targeted advertisements data recommendation of the showing advertisement form comprising maximum relation degree to the user.
Alternatively, the user's characteristic information browses the one or more in information including subscriber identity information and user.
According to another aspect of the present invention, a kind of ad data commending system is additionally provided, the system includes：
Request receiving module, for receiving browse request of the user to targeted advertisements data；
User's characteristic information acquisition module, for obtaining the user's characteristic information of the user；
The degree of correlation obtains module, for the relevance predication model for pre-establishing user's characteristic information input, obtains
To the degree of correlation of each showing advertisement form and the browse request of the targeted advertisements data；
Targeted advertisements data recommendation module, for the target of the showing advertisement form of preparatory condition will to be met comprising the degree of correlation
Ad data recommends the user.
Alternatively, the system also includes model training module, and the model training module includes：
First daily record extracting sub-module, for extracting the first ad data usage log recorded in the first historical period；
Targeted advertisements data search submodule, for finding out history exposure from the first ad data usage log
The targeted advertisements data that include multiple showing advertisement forms of the amount more than light exposure threshold value；
User's characteristic information extracting sub-module, for extracting at least one use of targeted advertisements data described in historical viewings
The user's characteristic information at family；
Model obtains submodule, for multiple showing advertisement forms according to the targeted advertisements data and it is described at least
The user's characteristic information of one user, machine learning relevancy algorithm is trained to obtain relevance predication model.
Alternatively, the system also includes model judge module and smooth clicking rate statistical model uses module：
The model judge module, for before the user's characteristic information for obtaining the user, judging whether pin
Relevance predication model is established to the targeted advertisements data；
The user's characteristic information acquisition module, specifically for the degree of correlation corresponding to the targeted advertisements data ought have been established
During forecast model, the user's characteristic information of the user is obtained；
The smooth clicking rate statistical model uses module, for related corresponding to the targeted advertisements data when not setting up
When spending forecast model, using the smooth clicking rate statistical model pre-established, each advertisement exhibition of the targeted advertisements data is calculated
The smooth clicking rate of existing form, and the targeted advertisements data recommendation that the showing advertisement form for meeting default clicking rate condition will be included
To the user.
Alternatively, the smooth clicking rate statistical model is included using module：
Second daily record extracting sub-module, for the second advertisement recorded in the second historical period before extracting current date
Data usage log；
History light exposure and history click volume extracting sub-module, for from the second ad data usage log, carrying
Take the history light exposure and history click volume of each showing advertisement form of the targeted advertisements data；
Smooth clicking rate obtains submodule, for the history light exposure of each showing advertisement form and history click volume to be inputted
The smooth clicking rate statistical model pre-established, obtains the smooth clicking rate of each showing advertisement form；Second history
The duration of period is more than the duration of first historical period.
Alternatively, the user's characteristic information acquisition module includes：
3rd daily record extracting sub-module, the day used for extracting the 3rd ad data recorded in the 3rd historical period
Will；
User's characteristic information searches submodule, described in the daily record that is used from the 3rd ad data, finding out
The user's characteristic information of user.
Alternatively, the targeted advertisements data recommendation module, specifically for by the showing advertisement shape comprising maximum relation degree
The targeted advertisements data recommendation of formula gives the user.
Alternatively, the user's characteristic information browses the one or more in information including subscriber identity information and user.
According to the embodiment of the present invention, after the browse request that user sends to targeted advertisements data is received, according to user
User's characteristic information and historical viewings information, using the relevance predication model pre-established, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request, the showing advertisement form that the degree of correlation meets preparatory condition is extracted, and will
Targeted advertisements data recommendation comprising the showing advertisement form is to user, because the embodiment of the present invention is the user spy according to user
Reference breath determines showing advertisement form, and then determines the ad data recommended, therefore improves ad data of the user to displaying
Interest, improve Consumer's Experience, reduce the low invalid exposure of ad data clicking rate.
The embodiment of the present invention uses what is pre-established when not setting up relevance predication model corresponding to targeted advertisements data
Smooth clicking rate statistical model, calculates the smooth clicking rate of each showing advertisement form of targeted advertisements data, determines smooth point
The rate of hitting meets the showing advertisement form of preparatory condition, and by the targeted advertisements data recommendation comprising the showing advertisement form to use
Family, recommend method so as to propose a kind of ad data of multi-model, for the ad data that light exposure is sufficient, use the degree of correlation
Forecast model calculates the degree of correlation of each showing advertisement form of ad data, for the ad data of light exposure deficiency, using flat
Sliding clicking rate statistical model calculates the degree of correlation of each showing advertisement form of ad data, realizes the recommendation of ad data.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows that a kind of according to embodiments of the present invention 1 ad data recommends the flow chart of method；
Fig. 2 shows that a kind of according to embodiments of the present invention 2 ad data recommends the flow chart of method；
Fig. 3 shows a kind of structured flowchart of according to embodiments of the present invention 1 ad data commending system；
Fig. 4 shows a kind of structured flowchart of according to embodiments of the present invention 2 ad data commending system.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Reference picture 1, show that a kind of according to embodiments of the present invention 1 ad data recommends the flow chart of method, the side
Method can specifically include：
Step 101, after receiving user to the browse request of targeted advertisements data, obtain the user's characteristic information of user.
The network media is provided with advertisement launching platform, and advertisement launching platform carries out pipe to the advertisement position that the network media provides
Reason.Generally in existing bid advertisement dispensing pattern, the flow of the advertisement to be put of advertisement launching platform acquisition media, and to
Advertisement transaction platform sends the request for launching advertisement, and the flow of the advertisement to be put of media is carried in the usual request, and advertisement is handed over
Easy platform obtains the bid advertisement of desired flow from the want advertisement side for providing ad data from mass advertising, and advertisement is needed
The ad data that the side of asking feeds back is ranked up, and the ad data won of bidding is thrown to and provides the media of advertisement putting flow and enters
Row plays.
In the ad data that the network media plays, part ad data includes multiple showing advertisement forms, different advertisements
Showing form has different advertising creatives.Advertisement transaction platform can obtain a variety of of ad data from want advertisement side simultaneously
Showing advertisement form, and a variety of showing advertisement forms are together returned into the network media.
In order to improve interest of the user to the ad data of broadcasting, Consumer's Experience is improved, the embodiment of the present invention is receiving
, can be according to the relevant information of user, from targeted advertisements data after user is to the browse request of targeted advertisements data to be viewed
Extract the showing advertisement form more matched with user in multiple showing advertisement forms, and by the showing advertisement shape including matching
The targeted advertisements data of formula are shown, so as to recommend user's viewing.
Described targeted advertisements data can be a variety of, such as video ads data, can be image.
The factors such as the species based on targeted advertisements data, broadcasting opportunity, user is received to targeted advertisements number to be viewed
According to browse request the step of can include it is a variety of, for example, the first, when targeted advertisements data are video ads data, and regards
When frequency ad data intercuts in other videos, above-mentioned steps can be to receive that to intercut video in currently playing video wide
The instruction of data is accused, or detects that first paragraph video playback terminates；Second, when targeted advertisements data are video ads data,
And when needing to click on broadcasting, above-mentioned steps can be to receive clicking operation of the user to targeted advertisements data.
In this step after user is received to the browse request of targeted advertisements data, the user characteristics letter of user can be obtained
Breath, subsequently to carry out the selection and recommendation of the showing advertisement form of targeted advertisements data according to the relevant information of user.Wherein,
User's characteristic information can be including a variety of, and such as subscriber identity information, user browse information, and subscriber identity information can be user
Internet protocol address be ip addresses, the login account of user etc., it can be wide relative to the target that user, which browses information,
Accuse the previous data content for browsing data, data address of data etc..For user in browse network media, the network media can be right
The subscriber identity information of user, user browse the information such as information and are recorded and stored, and store, are receiving such as in the form of daily record
To user to the browse request of targeted advertisements data after, media can extract from designated storage location, to obtain the correlation of user
Information.
Step 102, the relevance predication model for pre-establishing user's characteristic information input, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request.
In the embodiment of the present invention, different ad datas are corresponding with different relevance predication models, in advance for the target
Ad data establishes relevance predication model, and the relevance predication model includes user's characteristic information, each showing advertisement form
Etc. parameter.Media can be recorded to the use information of ad data and generate usage log.Establish relevance predication model
When, information needed can be extracted from the usage log of ad data, related algorithm is instructed using the information needed of extraction
Practice, obtain relevance predication model.
The user's characteristic information got is input in the relevance predication model pre-established by the embodiment of the present invention, is obtained
To the degree of correlation of each the showing advertisement form and browse request of targeted advertisements data.The degree of correlation is bigger, shows user to corresponding
Showing advertisement form is interested, and the recommendation of the corresponding showing advertisement form is bigger.
Step 103, will meet comprising the degree of correlation preparatory condition showing advertisement form targeted advertisements data recommendation to use
Family.
The embodiment of the present invention pre-sets the preparatory condition of the degree of correlation, and each advertisement of targeted advertisements data is being calculated
After the degree of correlation for showing form, determine that the degree of correlation meets the showing advertisement form of preparatory condition, further will be pre- comprising meeting
If the targeted advertisements data recommendation of the showing advertisement form of condition is shown in the media to user.Preparatory condition can be it is a variety of,
Such as degree of correlation is maximum, the degree of correlation is more than threshold value, can be according to being actually configured.
Because the degree of correlation for recommending the targeted advertisements data of user and the browse request of user is larger, therefore user is easy
Interest is produced to targeted advertisements data, so as to improve Consumer's Experience.For needing to click on the ad data played, due to clicking on
The video image of preceding display is user's image interested, therefore methods described of the embodiment of the present invention improves the point of ad data
Rate is hit, reduces the low invalid exposure of ad data clicking rate.
According to the embodiment of the present invention, after the browse request that user sends to targeted advertisements data is received, according to user
User's characteristic information and historical viewings information, using the relevance predication model pre-established, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request, the showing advertisement form that the degree of correlation meets preparatory condition is extracted, and will
Targeted advertisements data recommendation comprising the showing advertisement form is to user, because the embodiment of the present invention is the user spy according to user
Reference breath determines showing advertisement form, and then determines the ad data recommended, therefore improves ad data of the user to displaying
Interest, improve Consumer's Experience, reduce the low invalid exposure of ad data clicking rate.
Reference picture 2, show that a kind of according to embodiments of the present invention 2 ad data recommends the flow chart of method, the side
Method can specifically include：
Step 201, receive browse request of the user to targeted advertisements data.
In the embodiment of the present invention, targeted advertisements data are user's ad data to be browsed.Targeted advertisements data can be
Video data, image data etc., including a variety of showing advertisement forms, different showing advertisement forms have different advertising creatives.
Media receive a variety of showing advertisement forms of the targeted advertisements data when receiving targeted advertisements data.
Targeted advertisements data can be the video data for needing to play by clicking operation in the same page, Ke Yishi
Video data in other videos etc. is intercutted, the factor such as the species based on targeted advertisements data, broadcasting opportunity, receives user
The step of to the browse requests of targeted advertisements data to be viewed can include it is a variety of, for example, receiving user to targeted advertisements
The clicking operation of data, or the instruction that video ads data are intercutted in currently playing video is received, or detect
One section of video playback terminates.
Step 202, judge whether to establish relevance predication model for targeted advertisements data.
The embodiment of the present invention is after user is received to the browse request of targeted advertisements data, it is necessary to judge whether to be directed to mesh
Mark ad data establishes relevance predication model, if established, subsequent step can be performed, according to the user characteristics of user
Information, utilize relevance predication model, the degree of correlation of each the showing advertisement form and browse request of calculating targeted advertisements data.
Relevance predication model pre-establishes corresponding to targeted advertisements data, and different ad datas are corresponding with different
Relevance predication model, the relevance predication model can obtain in the following manner：
First, the first ad data usage log of record in the first historical period is extracted.
Media can record to the service condition of the ad data in historical period, form the first ad data and use day
Will, ad data usage log can include much information, such as exposure frequency and number of clicks.The duration of first historical period
It can be configured as needed, such as seven day time.
Secondly, history light exposure is found out from the first ad data usage log more than light exposure threshold value comprising multiple
The targeted advertisements data of showing advertisement form, and extract the user of at least one user of historical viewings targeted advertisements data
Characteristic information.
The ad data of advertising expense is collected for showing number according to advertisement, once, display number increases by one for exposure.This
Step finds out the one or more ad datas for including multiple showing advertisement forms from the first ad data usage log, then
Judge whether the history light exposure in the first historical period of each ad data is more than light exposure threshold value, if it does, explanation is wide
It is more to accuse display number of the data in the historical period, it is determined that to be that the ad data establishes relevance predication model, such as
Fruit is not more than, then carries out relatedness computation using smooth clicking rate (smooth ctr) statistical model pre-established.
In the embodiment of the present invention, targeted advertisements data are that history light exposure includes multiple advertisement exhibitions more than light exposure threshold value
The ad data of existing form.After determining to meet the targeted advertisements data of above-mentioned condition, from the first ad data usage log
In extract the user's characteristic information of at least one user that the targeted advertisements data are browsed in the first historical period, such as user's body
Part information and user browse information etc..
Finally, believed according to the user characteristics of multiple showing advertisement forms of targeted advertisements data and at least one user
Breath, is trained to obtain relevance predication model to machine learning relevancy algorithm.
The targeted advertisements data of the condition of satisfaction are being found out, and are extracting at least the one of historical viewings targeted advertisements data
After the user's characteristic information of individual user, according to multiple showing advertisement forms of targeted advertisements data and the use of at least one user
Family characteristic information, machine learning relevancy algorithm is trained to obtain relevance predication model.Can in relevance predication model
The parameter information such as in the form of including user's characteristic information, multiple showing advertisements.The machine learning relevancy algorithm can include
It is a variety of, if Factorization machine algorithm is FM (Factorization Machine) algorithm.
The embodiment of the present invention uses machine learning method, is preferably entered according to the user's characteristic information of user and ad features
Row ad data is recommended, and improves the showing advertisement form of ad data and the matching degree of user of recommendation, improves user's body
Test.
If step 203, having established relevance predication model corresponding to targeted advertisements data, the user for obtaining user is special
Reference ceases.
If it is determined that having established relevance predication model corresponding to targeted advertisements data, then the user characteristics of user is obtained
Information.User's characteristic information can include a variety of, and the one or more in information are browsed such as subscriber identity information and user, its
In, subscriber identity information can be the Internet protocol address i.e. ip addresses, the login account of user etc. of user, and user browses letter
Breath can be relative to the previous data contents for browsing data of the targeted advertisements data, data address etc..
The user's characteristic information of user can be obtained in several ways, as extracted the recorded in the 3rd historical period the 3rd
The daily record that ad data uses, in the daily record used from the 3rd ad data, find out the user's characteristic information of user.3rd goes through
The duration of history period can be according to being actually configured.The daily record that 3rd ad data uses can be used for all history
Ad data record usage log or the ad data that is used in historical period for a certain user record
Usage log, can be according to being actually configured.
Step 204, the relevance predication model for pre-establishing user's characteristic information input, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request.
The user's characteristic information got is input in relevance predication model by the embodiment of the present invention, passes through model meter
Calculate, obtain the degree of correlation of each the showing advertisement form and browse request of targeted advertisements data.
Step 205, will meet comprising the degree of correlation preparatory condition showing advertisement form targeted advertisements data recommendation to use
Family.
After the degree of correlation of each showing advertisement form and browse request of targeted advertisements data is calculated, correlation will be included
Degree meets the targeted advertisements data recommendation of the showing advertisement form of preparatory condition to user.Preparatory condition can be a variety of, such as will
Targeted advertisements data recommendation comprising the maximum showing advertisement form of the degree of correlation to user, predetermined threshold value will be more than comprising the degree of correlation
Showing advertisement form targeted advertisements data recommendation to user, can be according to being actually configured.Correspondingly, it is described to include
Meet that the step of targeted advertisements data recommendation of the showing advertisement form of default degree of correlation condition is to user can include：It will include
The targeted advertisements data recommendation of the showing advertisement form of maximum relation degree gives the user.
It is flat using what is pre-established if step 206, not setting up relevance predication model corresponding to targeted advertisements data
Sliding clicking rate statistical model, the smooth clicking rate of each showing advertisement form of targeted advertisements data is calculated, and will include and meet in advance
If the targeted advertisements data recommendation of the showing advertisement form of clicking rate condition is to user.
The embodiment of the present invention has pre-established smooth clicking rate computation model, if it is determined that not built for targeted advertisements data
Corresponding relevance predication model is found, then using the smooth clicking rate statistical model pre-established, calculates targeted advertisements data
The smooth clicking rate of each showing advertisement form, and the targeted advertisements that the showing advertisement form for meeting default clicking rate condition will be included
Data recommendation is to user.Default clicking rate condition can be a variety of, and such as clicking rate is maximum, clicking rate is more than predetermined threshold value.
It is described to use the smooth clicking rate statistical model pre-established, each showing advertisement form of calculating targeted advertisements data
Smooth clicking rate the step of can include：
First, the second ad data usage log recorded in the second historical period before extracting current date.
Media can record to the service condition of the ad data in the second historical period before current date, be formed
Second ad data usage log, the second ad data usage log can include much information, such as exposure frequency and click time
Number etc..The duration of second historical period can be configured as needed, and such as the fortnight time, specifically such as, today is No. 20, the
Two historical periods are -19 days on the 6th.
In the embodiment of the present invention, the duration of the second historical period is more than the degree of correlation used in smooth clicking rate statistical model
The duration of first historical period used in forecast model.When a certain ad data exposes abundance in shorter historical time
When, relatedness computation is carried out using relevance predication model, the under-exposure in shorter historical time when a certain ad data
When, usage history time longer smooth clicking rate statistical model carries out relatedness computation, so as to solve showing advertisement form
The problem of number of visits is few, cold start-up.
If a certain showing advertisement form of targeted advertisements data shows form for new, counted using smooth clicking rate
Model calculates the degree of correlation of targeted advertisements data, using the phase of the degree of correlation of the targeted advertisements data showing advertisement form new as this
Guan Du.At this moment in the formula of following smooth clicking rate statistical models, each parameter is the parameter of targeted advertisements data.
If targeted advertisements data are new ad datas, multiple showing advertisements of new targeted advertisements data are given at random
Form assignment, such as assignment 0~1, multiple showing advertisement forms are ranked up based on assignment, the showing advertisement form for sorting forward
It is preferential recommended.
Secondly, from the second ad data usage log, the history of each showing advertisement form of targeted advertisements data is extracted
Light exposure and history click volume.
Smooth clicking rate statistical model includes many kinds of parameters, such as history light exposure and history click volume, therefore is extracting
After second ad data usage log, from the first ad data usage log, each showing advertisement of targeted advertisements data is extracted
The history light exposure and history click volume of form.
Finally, the smooth clicking rate history light exposure of each showing advertisement form and the input of history click volume pre-established
Statistical model, obtain the smooth clicking rate of each showing advertisement form.
After the history light exposure and history click volume of extracting each showing advertisement form of targeted advertisements data, it is inputted
The smooth clicking rate statistical model pre-established, obtains the smooth clicking rate of each showing advertisement form.
The model formation of smooth clicking rate statistical model can be as follows used in the embodiment of the present invention：
Wherein, L is the smooth clicking rate of showing advertisement form, and c is showing advertisement form in the second historical period
History click volume, C are current click volume of the showing advertisement form in current date, and d is showing advertisement form in the second history
History light exposure in period, D are current exposure amount of the showing advertisement form in current date, and α is parameter.
By the above formula, the above-mentioned history light exposure extracted from the second ad data usage log includes the
The current exposure amount in history light exposure and current date in two historical periods, the history click volume of extraction include the second history
The current exposure amount in history click volume and current date in period.
By foregoing description, the ad data that the embodiment of the present invention proposes a kind of multi-model recommends method, for
The sufficient ad data of light exposure, relevance predication model can be used to calculate the correlation of each showing advertisement form of ad data
Degree, for the ad data of light exposure deficiency, smooth clicking rate statistical model can be used to calculate each advertisement exhibition of ad data
The degree of correlation of existing form, so as to realize the recommendation of ad data.
According to the embodiment of the present invention, after the browse request that user sends to targeted advertisements data is received, according to user
User's characteristic information and historical viewings information, using the relevance predication model pre-established, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request, the showing advertisement form that the degree of correlation meets preparatory condition is extracted, and will
Targeted advertisements data recommendation comprising the showing advertisement form is to user, because the embodiment of the present invention is the user spy according to user
Reference breath determines showing advertisement form, and then determines the ad data recommended, therefore improves ad data of the user to displaying
Interest, improve Consumer's Experience, reduce the low invalid exposure of ad data clicking rate.
The embodiment of the present invention uses what is pre-established when not setting up relevance predication model corresponding to targeted advertisements data
Smooth clicking rate statistical model, calculates the smooth clicking rate of each showing advertisement form of targeted advertisements data, determines smooth point
The rate of hitting meets the showing advertisement form of preparatory condition, and by the targeted advertisements data recommendation comprising the showing advertisement form to use
Family, recommend method so as to propose a kind of ad data of multi-model, for the ad data that light exposure is sufficient, use the degree of correlation
Forecast model calculates the degree of correlation of each showing advertisement form of ad data, for the ad data of light exposure deficiency, using flat
Sliding clicking rate statistical model calculates the degree of correlation of each showing advertisement form of ad data, realizes the recommendation of ad data.
Based on the explanation of above method embodiment, present invention also offers corresponding ad data commending system embodiment,
To realize the content described in above method embodiment.
Reference picture 3, a kind of structured flowchart of according to embodiments of the present invention 1 ad data commending system is shown, it is described
Ad data commending system can include：
Request receiving module 301, for receiving browse request of the user to targeted advertisements data.
User's characteristic information acquisition module 302, for obtaining the user's characteristic information of the user.
The degree of correlation obtains module 303, for the user's characteristic information to be inputted into the relevance predication model pre-established,
Obtain each showing advertisement form of the targeted advertisements data and the degree of correlation of the browse request.
Targeted advertisements data recommendation module 304, for the showing advertisement form of preparatory condition will to be met comprising the degree of correlation
Targeted advertisements data recommendation gives the user.
According to the embodiment of the present invention, after the browse request that user sends to targeted advertisements data is received, according to user
User's characteristic information and historical viewings information, using the relevance predication model pre-established, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request, the showing advertisement form that the degree of correlation meets preparatory condition is extracted, and will
Targeted advertisements data recommendation comprising the showing advertisement form is to user, because the embodiment of the present invention is the user spy according to user
Reference breath determines showing advertisement form, and then determines the ad data recommended, therefore improves ad data of the user to displaying
Interest, improve Consumer's Experience, reduce the low invalid exposure of ad data clicking rate.
Reference picture 4, a kind of structured flowchart of according to embodiments of the present invention 2 ad data commending system is shown, it is described
Ad data commending system can include：
Request receiving module 401, for receiving browse request of the user to targeted advertisements data.
Model judge module 402, for judging whether to establish relevance predication model for the targeted advertisements data.
User's characteristic information acquisition module 403, for relevance predication corresponding to the targeted advertisements data ought to have been established
During model, the user's characteristic information of the user is obtained.
The degree of correlation obtains module 404, for the user's characteristic information to be inputted into the relevance predication model pre-established,
Obtain each showing advertisement form of the targeted advertisements data and the degree of correlation of the browse request.
Targeted advertisements data recommendation module 405, for the showing advertisement form of preparatory condition will to be met comprising the degree of correlation
Targeted advertisements data recommendation gives the user.
Smooth clicking rate statistical model uses module 406, for related corresponding to the targeted advertisements data when not setting up
When spending forecast model, using the smooth clicking rate statistical model pre-established, each advertisement exhibition of the targeted advertisements data is calculated
The smooth clicking rate of existing form, and the targeted advertisements data recommendation that the showing advertisement form for meeting default clicking rate condition will be included
To the user.
The embodiment of the present invention, it is preferable that the system also includes model training module, and the model training module includes：
First daily record extracting sub-module, for extracting the first ad data usage log recorded in the first historical period；
Targeted advertisements data search submodule, for finding out history exposure from the first ad data usage log
The targeted advertisements data that include multiple showing advertisement forms of the amount more than light exposure threshold value；
User's characteristic information extracting sub-module, for extracting at least one use of targeted advertisements data described in historical viewings
The user's characteristic information at family；
Model obtains submodule, for multiple showing advertisement forms according to the targeted advertisements data and it is described at least
The user's characteristic information of one user, machine learning relevancy algorithm is trained to obtain relevance predication model.
The embodiment of the present invention, it is preferable that the smooth clicking rate statistical model is included using module 405：
Second daily record extracting sub-module, for the second advertisement recorded in the second historical period before extracting current date
Data usage log；
History light exposure and history click volume extracting sub-module, for from the second ad data usage log, carrying
Take the history light exposure and history click volume of each showing advertisement form of the targeted advertisements data；
Smooth clicking rate obtains submodule, for the history light exposure of each showing advertisement form and history click volume to be inputted
The smooth clicking rate statistical model pre-established, obtains the smooth clicking rate of each showing advertisement form；Second history
The duration of period is more than the duration of first historical period.
The embodiment of the present invention, it is preferable that the user's characteristic information acquisition module 403 includes：
3rd daily record extracting sub-module, the day used for extracting the 3rd ad data recorded in the 3rd historical period
Will；
User's characteristic information searches submodule, described in the daily record that is used from the 3rd ad data, finding out
The user's characteristic information of user.
The embodiment of the present invention, it is preferable that the targeted advertisements data recommendation module 405, specifically for maximum phase will be included
The targeted advertisements data recommendation of Guan Du showing advertisement form gives the user.
The embodiment of the present invention, preferably described user's characteristic information includes subscriber identity information and user is browsed in information
It is one or more.
According to the embodiment of the present invention, after the browse request that user sends to targeted advertisements data is received, according to user
User's characteristic information and historical viewings information, using the relevance predication model pre-established, obtain targeted advertisements data
The degree of correlation of each showing advertisement form and browse request, the showing advertisement form that the degree of correlation meets preparatory condition is extracted, and will
Targeted advertisements data recommendation comprising the showing advertisement form is to user, because the embodiment of the present invention is the user spy according to user
Reference breath determines showing advertisement form, and then determines the ad data recommended, therefore improves ad data of the user to displaying
Interest, improve Consumer's Experience, reduce the low invalid exposure of ad data clicking rate.
The embodiment of the present invention uses what is pre-established when not setting up relevance predication model corresponding to targeted advertisements data
Smooth clicking rate statistical model, calculates the smooth clicking rate of each showing advertisement form of targeted advertisements data, determines smooth point
The rate of hitting meets the showing advertisement form of preparatory condition, and by the targeted advertisements data recommendation comprising the showing advertisement form to use
Family, recommend method so as to propose a kind of ad data of multi-model, for the ad data that light exposure is sufficient, use the degree of correlation
Forecast model calculates the degree of correlation of each showing advertisement form of ad data, for the ad data of light exposure deficiency, using flat
Sliding clicking rate statistical model calculates the degree of correlation of each showing advertisement form of ad data, realizes the recommendation of ad data.
For above-mentioned coding mode judgment means embodiment, because it is substantially similar to embodiment of the method, so retouching
That states is fairly simple, and related part illustrates referring to the part of embodiment of the method shown in Fig. 1-Fig. 2.
Each embodiment in this specification is described by the way of progressive, what each embodiment stressed be with
The difference of other embodiment, between each embodiment identical similar part mutually referring to.
It would have readily occurred to a person skilled in the art that be：Any combination application of above-mentioned each embodiment is all feasible, therefore
Any combination between above-mentioned each embodiment is all embodiment of the present invention, but this specification exists as space is limited,
This is not just detailed one by one.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be realized with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize one in ad data commending system according to embodiments of the present invention
The some or all functions of a little or whole parts.The present invention is also implemented as performing method as described herein
Some or all equipment or program of device (for example, computer program and computer program product).Such realization
The program of the present invention can store on a computer-readable medium, or can have the form of one or more signal.This
The signal of sample can be downloaded from internet website and obtained, and either provided on carrier signal or carried in the form of any other
For.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (14)
1. a kind of ad data recommends method, it is characterised in that methods described includes：
After user is received to the browse request of targeted advertisements data, the user's characteristic information of the user is obtained；
The relevance predication model that user's characteristic information input is pre-established, obtain each wide of the targeted advertisements data
Accuse the degree of correlation for showing form and the browse request；
The targeted advertisements data recommendation of the showing advertisement form of preparatory condition will be met to the user comprising the degree of correlation.
2. according to the method for claim 1, it is characterised in that the relevance predication model obtains in the following manner：
Extract the first ad data usage log of record in the first historical period；
History light exposure is found out from the first ad data usage log and includes multiple advertisements more than light exposure threshold value
Show the targeted advertisements data of form, and extract at least one user of targeted advertisements data described in historical viewings
User's characteristic information；
According to multiple showing advertisement forms of the targeted advertisements data and the user's characteristic information of at least one user,
Machine learning relevancy algorithm is trained to obtain relevance predication model.
3. according to the method for claim 2, it is characterised in that the user's characteristic information for obtaining the user it
Before, methods described also includes：
Judge whether to establish relevance predication model for the targeted advertisements data；
If it is, the step of performing the user's characteristic information of the acquisition user.
If it is not, then using the smooth clicking rate statistical model pre-established, each advertisement exhibition of the targeted advertisements data is calculated
The smooth clicking rate of existing form, and the targeted advertisements data recommendation that the showing advertisement form for meeting default clicking rate condition will be included
To the user.
4. according to the method for claim 3, it is characterised in that described to use the smooth clicking rate pre-established statistics mould
Type, calculating the smooth clicking rate of each showing advertisement form of the targeted advertisements data includes：
The the second ad data usage log recorded in the second historical period before extracting current date；
From the second ad data usage log, the history for extracting each showing advertisement form of the targeted advertisements data exposes
Light quantity and history click volume；
The smooth clicking rate statistics that the history light exposure of each showing advertisement form and the input of history click volume are pre-established
Model, obtain the smooth clicking rate of each showing advertisement form；When the duration of second historical period is more than first history
The duration of section.
5. according to the method for claim 1, it is characterised in that the user's characteristic information for obtaining the user includes：
Extract the daily record that the 3rd ad data of record in the 3rd historical period uses；
In the daily record used from the 3rd ad data, the user's characteristic information of the user is found out.
6. according to the method for claim 1, it is characterised in that described to include the advertisement exhibition for meeting default degree of correlation condition
The targeted advertisements data recommendation of existing form includes to the user：
Give the targeted advertisements data recommendation of the showing advertisement form comprising maximum relation degree to the user.
7. according to the method for claim 1, it is characterised in that the user's characteristic information includes subscriber identity information and use
Family browses the one or more in information.
8. a kind of ad data commending system, it is characterised in that the system includes：
Request receiving module, for receiving browse request of the user to targeted advertisements data；
User's characteristic information acquisition module, for obtaining the user's characteristic information of the user；
The degree of correlation obtains module, for the relevance predication model for pre-establishing user's characteristic information input, obtains institute
State each showing advertisement form of targeted advertisements data and the degree of correlation of the browse request；
Targeted advertisements data recommendation module, for the targeted advertisements of the showing advertisement form of preparatory condition will to be met comprising the degree of correlation
Data recommendation gives the user.
9. system according to claim 8, it is characterised in that the system also includes model training module, the model
Training module includes：
First daily record extracting sub-module, for extracting the first ad data usage log recorded in the first historical period；
Targeted advertisements data search submodule is big for finding out history light exposure from the first ad data usage log
In the targeted advertisements data for including multiple showing advertisement forms of light exposure threshold value；
User's characteristic information extracting sub-module, for extracting at least one user of targeted advertisements data described in historical viewings
User's characteristic information；
Model obtains submodule, for multiple showing advertisement forms according to the targeted advertisements data and described at least one
The user's characteristic information of user, machine learning relevancy algorithm is trained to obtain relevance predication model.
10. system according to claim 9, it is characterised in that the system also includes model judge module and smooth point
Hit rate statistical model and use module：
The model judge module, for before the user's characteristic information for obtaining the user, judging whether to be directed to institute
State targeted advertisements data and establish relevance predication model；
The user's characteristic information acquisition module, specifically for relevance predication corresponding to the targeted advertisements data ought have been established
During model, the user's characteristic information of the user is obtained；
The smooth clicking rate statistical model uses module, for pre- when not setting up the degree of correlation corresponding to the targeted advertisements data
When surveying model, using the smooth clicking rate statistical model pre-established, each showing advertisement shape of the targeted advertisements data is calculated
The smooth clicking rate of formula, and by the targeted advertisements data recommendation comprising the showing advertisement form for meeting default clicking rate condition to institute
State user.
11. system according to claim 10, it is characterised in that the smooth clicking rate statistical model uses module bag
Include：
Second daily record extracting sub-module, for the second ad data recorded in the second historical period before extracting current date
Usage log；
History light exposure and history click volume extracting sub-module, for from the second ad data usage log, extracting institute
State the history light exposure and history click volume of each showing advertisement form of targeted advertisements data；
Smooth clicking rate obtains submodule, advance for the history light exposure of each showing advertisement form and history click volume to be inputted
The smooth clicking rate statistical model established, obtains the smooth clicking rate of each showing advertisement form；Second historical period
Duration be more than first historical period duration.
12. system according to claim 8, it is characterised in that the user's characteristic information acquisition module includes：
3rd daily record extracting sub-module, the daily record used for extracting the 3rd ad data recorded in the 3rd historical period；
User's characteristic information searches submodule, in the daily record that is used from the 3rd ad data, finding out the user
User's characteristic information.
13. system according to claim 8, it is characterised in that：
The targeted advertisements data recommendation module, specifically for by the targeted advertisements of the showing advertisement form comprising maximum relation degree
Data recommendation gives the user.
14. system according to claim 8, it is characterised in that the user's characteristic information include subscriber identity information and
User browses the one or more in information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710744931.6A CN107590689B (en) | 2017-08-25 | 2017-08-25 | Advertisement data recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710744931.6A CN107590689B (en) | 2017-08-25 | 2017-08-25 | Advertisement data recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107590689A true CN107590689A (en) | 2018-01-16 |
| CN107590689B CN107590689B (en) | 2021-01-08 |
Family
ID=61043026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710744931.6A Active CN107590689B (en) | 2017-08-25 | 2017-08-25 | Advertisement data recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590689B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416610A (en) * | 2018-01-19 | 2018-08-17 | 阿里巴巴集团控股有限公司 | Frequency control method is launched in user's history feedback information forming method and advertisement |
| CN110059254A (en) * | 2019-04-24 | 2019-07-26 | 秒针信息技术有限公司 | A kind of message push method and device |
| CN110381377A (en) * | 2019-07-23 | 2019-10-25 | 秒针信息技术有限公司 | A kind of detection method, device, electronic equipment and storage medium that information plays |
| CN110555736A (en) * | 2019-09-05 | 2019-12-10 | 广东聚宝屋传媒有限公司 | control method and device for advertising based on published demand information |
| CN110796465A (en) * | 2018-08-03 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Resource display equipment determining method, advertisement display screen determining method and device |
| CN110992096A (en) * | 2019-12-03 | 2020-04-10 | 秒针信息技术有限公司 | Prediction model training method and device and media identification prediction method and device |
| CN111144937A (en) * | 2019-12-20 | 2020-05-12 | 北京达佳互联信息技术有限公司 | Advertisement material determination method, device, equipment and storage medium |
| CN111626805A (en) * | 2019-02-28 | 2020-09-04 | 北京沃东天骏信息技术有限公司 | Information display method and device |
| CN112435065A (en) * | 2020-11-27 | 2021-03-02 | 杭州推啊网络科技有限公司 | Mobile internet non-standard position interactive advertisement delivery method and system |
| CN112581195A (en) * | 2021-02-25 | 2021-03-30 | 武汉卓尔数字传媒科技有限公司 | Advertisement pushing method and device and electronic equipment |
| CN112767024A (en) * | 2021-01-15 | 2021-05-07 | 北京搜狗科技发展有限公司 | Method and related device for generating advertisement creativity |
| CN113129070A (en) * | 2021-04-28 | 2021-07-16 | 北京奇艺世纪科技有限公司 | Message delivery method, device, server and storage medium |
| CN113298510A (en) * | 2018-07-10 | 2021-08-24 | 马上消费金融股份有限公司 | Deduction instruction initiating method and device |
| CN113487368A (en) * | 2021-07-29 | 2021-10-08 | 宿迁市盛邦信息科技有限公司 | Scientific and technological information push service system based on big data |
| CN114254181A (en) * | 2020-09-21 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Resource recommendation method and device, computer equipment and storage medium |
| CN114820060A (en) * | 2022-04-26 | 2022-07-29 | 北京有竹居网络技术有限公司 | Advertisement recommendation method, device, equipment and medium |
| CN117495459A (en) * | 2024-01-02 | 2024-02-02 | 蓝色火焰科技成都有限公司 | Man-machine interaction advertisement method, device, equipment and storage medium based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567902A (en) * | 2012-02-10 | 2012-07-11 | 亿赞普(北京)科技有限公司 | Network advertisement dynamic release method and system thereof |
| CN104008109A (en) * | 2013-02-26 | 2014-08-27 | 南京邮电大学 | User interest based Web information push service system |
| CN105139237A (en) * | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN105160548A (en) * | 2015-08-20 | 2015-12-16 | 北京奇虎科技有限公司 | Method and apparatus for predicting advertisement click-through rate |
| CN105812844A (en) * | 2014-12-29 | 2016-07-27 | 深圳市Tcl高新技术开发有限公司 | User advertisement push method and system of TV |
| CN106997549A (en) * | 2017-02-14 | 2017-08-01 | 火烈鸟网络(广州)股份有限公司 | The method for pushing and system of a kind of advertising message |
-
2017
- 2017-08-25 CN CN201710744931.6A patent/CN107590689B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567902A (en) * | 2012-02-10 | 2012-07-11 | 亿赞普(北京)科技有限公司 | Network advertisement dynamic release method and system thereof |
| CN104008109A (en) * | 2013-02-26 | 2014-08-27 | 南京邮电大学 | User interest based Web information push service system |
| CN105812844A (en) * | 2014-12-29 | 2016-07-27 | 深圳市Tcl高新技术开发有限公司 | User advertisement push method and system of TV |
| CN105160548A (en) * | 2015-08-20 | 2015-12-16 | 北京奇虎科技有限公司 | Method and apparatus for predicting advertisement click-through rate |
| CN105139237A (en) * | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN106997549A (en) * | 2017-02-14 | 2017-08-01 | 火烈鸟网络(广州)股份有限公司 | The method for pushing and system of a kind of advertising message |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416610A (en) * | 2018-01-19 | 2018-08-17 | 阿里巴巴集团控股有限公司 | Frequency control method is launched in user's history feedback information forming method and advertisement |
| CN108416610B (en) * | 2018-01-19 | 2022-03-01 | 创新先进技术有限公司 | User history feedback information forming method and advertisement putting frequency control method |
| CN113298510B (en) * | 2018-07-10 | 2022-06-17 | 马上消费金融股份有限公司 | Deduction instruction initiating method and device |
| CN113298510A (en) * | 2018-07-10 | 2021-08-24 | 马上消费金融股份有限公司 | Deduction instruction initiating method and device |
| CN110796465A (en) * | 2018-08-03 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Resource display equipment determining method, advertisement display screen determining method and device |
| CN111626805B (en) * | 2019-02-28 | 2023-11-03 | 北京沃东天骏信息技术有限公司 | Information display method and device |
| CN111626805A (en) * | 2019-02-28 | 2020-09-04 | 北京沃东天骏信息技术有限公司 | Information display method and device |
| CN110059254A (en) * | 2019-04-24 | 2019-07-26 | 秒针信息技术有限公司 | A kind of message push method and device |
| CN110381377B (en) * | 2019-07-23 | 2021-07-27 | 秒针信息技术有限公司 | Detection method and device for information playing, electronic equipment and storage medium |
| CN110381377A (en) * | 2019-07-23 | 2019-10-25 | 秒针信息技术有限公司 | A kind of detection method, device, electronic equipment and storage medium that information plays |
| CN110555736A (en) * | 2019-09-05 | 2019-12-10 | 广东聚宝屋传媒有限公司 | control method and device for advertising based on published demand information |
| CN110555736B (en) * | 2019-09-05 | 2022-06-03 | 广东聚宝屋传媒有限公司 | Control method and device for advertising based on published demand information |
| CN110992096A (en) * | 2019-12-03 | 2020-04-10 | 秒针信息技术有限公司 | Prediction model training method and device and media identification prediction method and device |
| CN110992096B (en) * | 2019-12-03 | 2023-08-29 | 秒针信息技术有限公司 | Prediction model training method and device and media identification prediction method and device |
| CN111144937B (en) * | 2019-12-20 | 2024-05-14 | 北京达佳互联信息技术有限公司 | Advertisement material determining method, device, equipment and storage medium |
| CN111144937A (en) * | 2019-12-20 | 2020-05-12 | 北京达佳互联信息技术有限公司 | Advertisement material determination method, device, equipment and storage medium |
| CN114254181A (en) * | 2020-09-21 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Resource recommendation method and device, computer equipment and storage medium |
| CN112435065B (en) * | 2020-11-27 | 2024-03-01 | 杭州推啊网络科技有限公司 | Mobile internet non-standard position interactive advertisement putting method and system |
| CN112435065A (en) * | 2020-11-27 | 2021-03-02 | 杭州推啊网络科技有限公司 | Mobile internet non-standard position interactive advertisement delivery method and system |
| CN112767024A (en) * | 2021-01-15 | 2021-05-07 | 北京搜狗科技发展有限公司 | Method and related device for generating advertisement creativity |
| CN112767024B (en) * | 2021-01-15 | 2024-02-20 | 北京搜狗科技发展有限公司 | Advertisement creative generation method and related device |
| CN112581195A (en) * | 2021-02-25 | 2021-03-30 | 武汉卓尔数字传媒科技有限公司 | Advertisement pushing method and device and electronic equipment |
| CN113129070B (en) * | 2021-04-28 | 2023-09-01 | 北京奇艺世纪科技有限公司 | Message delivery method, device, server and storage medium |
| CN113129070A (en) * | 2021-04-28 | 2021-07-16 | 北京奇艺世纪科技有限公司 | Message delivery method, device, server and storage medium |
| CN113487368A (en) * | 2021-07-29 | 2021-10-08 | 宿迁市盛邦信息科技有限公司 | Scientific and technological information push service system based on big data |
| CN114820060A (en) * | 2022-04-26 | 2022-07-29 | 北京有竹居网络技术有限公司 | Advertisement recommendation method, device, equipment and medium |
| CN117495459A (en) * | 2024-01-02 | 2024-02-02 | 蓝色火焰科技成都有限公司 | Man-machine interaction advertisement method, device, equipment and storage medium based on big data |
| CN117495459B (en) * | 2024-01-02 | 2024-03-19 | 蓝色火焰科技成都有限公司 | Man-machine interaction advertisement method, device, equipment and storage medium based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107590689B (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590689A (en) | A kind of ad data recommends method and system | |
| KR101790312B1 (en) | Apparatus and Method for matching management | |
| CN105227975B (en) | Advertisement placement method and device | |
| JP6427417B2 (en) | Multidimensional ad bidding | |
| JP5414693B2 (en) | Video quality measurement | |
| JP4910000B2 (en) | Listing advertisement sending device and method | |
| US20100138852A1 (en) | System and method for the presentation of interactive advertising quizzes | |
| CN105100886B (en) | Distribution control method and device, the server and system of network media information | |
| EP2835979A1 (en) | Attribute setting method and device | |
| US20090037967A1 (en) | Video upload system | |
| TW201520936A (en) | User engagement-based contextually-dependent automated pricing for non-guaranteed delivery | |
| US10282758B1 (en) | Pricing control in a real-time network-based bidding environment | |
| CN105868685A (en) | Advertisement recommendation method and device based on face recognition | |
| WO2014105622A2 (en) | Selecting an advertisement for a traffic source | |
| KR20070111350A (en) | Context related advertisement/information exposure method and their recommendation service system to enhance relativity | |
| US11507604B1 (en) | Automated persona feature selection | |
| CN106204121A (en) | Advertisement placement method based on browser and system | |
| CN108744523A (en) | Game recommdation method, apparatus and computer readable storage medium | |
| CN109729433A (en) | A kind of video playing appraisal procedure and device | |
| CN109003149A (en) | A kind of barrage advertisement placement method and device | |
| WO2014138779A1 (en) | Sponsorship system | |
| CN110020108A (en) | Network resource recommended method, device, computer equipment and storage medium | |
| CN108229990A (en) | A kind of advertisement title generation method, device and equipment | |
| US10945033B2 (en) | System and method to generate a customized, parameter-based video | |
| US20150256900A1 (en) | Dynamic content creation for interactive video overlays |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |