CN105956888A - Advertisement personalized display method - Google Patents
Advertisement personalized display method Download PDFInfo
- Publication number
- CN105956888A CN105956888A CN201610373899.0A CN201610373899A CN105956888A CN 105956888 A CN105956888 A CN 105956888A CN 201610373899 A CN201610373899 A CN 201610373899A CN 105956888 A CN105956888 A CN 105956888A
- Authority
- CN
- China
- Prior art keywords
- intention
- user
- information
- advertisement
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
Abstract
The invention proposes an advertisement personalized display method, and the method comprises the following steps: obtaining the configuration information of advertisement visited by each user; building a database and an advertisement filtering rule; building a candidate idea set; filtering the candidate idea set, and obtaining an optimal advertisement idea; and carrying out redirection jump of a network. The method provided by the invention builds a click rate pre-estimation model according to big data, analyzes the aesthetic preference, shopping preference and game style preference of a user, and displays a material content which is the easiest for advertisement transfer in a mode of idea filtering and network redirection jump during advertisement display at each time, so as to attract the user to click the advertisement and to complete the purchase and registration, thereby meeting the personalized demands of the user. The method directly improves the input-output ratio of an advertiser.
Description
Technical field
The present invention relates to technical field of advertisement, particularly to a kind of ad personalization methods of exhibiting.
Background technology
The method of industry universal is that advertiser makes an ad material at present, carries out advertisement putting.Due to different user
Hobby point difference, and user watches an advertising creative for a long time and can cause aestheticly tired, therefore the poorest strong man of effect
Meaning.
Existing advertiser uses the mode the most manually changing material to promote effect of advertising, but can not solve user
Property demand, can not persistently solve aestheticly tired problem, it is impossible to fundamentally solve problem above.
Such as the patent of invention of Chinese patent CN 102473266 A, this invention provides one by customizing for target device
Optimize advertisement, can receive as not being bundled into predefined set of advertisements from any entity of advertizer or generation advertisement
The dynamic creative of the multiple creative element closed so that user obtains the Consumer's Experience optimized, but, this optimization method
Users ' individualized requirement can not be solved.
Summary of the invention
The purpose of the present invention is intended at least solve one of described technological deficiency.
To this end, it is an object of the invention to propose a kind of ad personalization methods of exhibiting meeting users ' individualized requirement.
To achieve these goals, the present invention provides a kind of ad personalization methods of exhibiting, comprises the steps:
A kind of ad personalization methods of exhibiting, it is characterised in that comprise the steps:
Step S1, obtains the advertisement configuration information that each user is accessed;
Step S2, creates data base and advertisement filter rule;
Step S201, is synchronized to server by control server, by server by the advertisement configuration information of above-mentioned acquisition
Set up intention index and advertisement filter rule, set up concordance list and store;
Step S202, is collected advertising display data, advertising display daily record by server, and by log transmission to cloud computing
Platform stores;
Step S203, cloud computing platform pass through log information, analyze customer attribute information, to each user process right
The label answered also stores to line in data base, and set up the user property storehouse corresponding with each user, webpage attribute library,
Behavioral characteristics storehouse;
Step S204, according to advertising display data, ad click data, UAD, webpage attribute data,
Create clicking rate prediction model, and according to the training pattern in clicking rate prediction model, the request to features multiple on line,
Carry out clicking rate prediction, and training result is stored to intention order module;
Step S3, sets up candidate's intention set;
Step S301, when user accesses, the request analysis device in server, by resolving network request parameter, identifies
The advertisement parameters of the user accessed, sets up analytic parameter search index table;
Step S302, the above-mentioned user property storehouse of intention search index in server, webpage attribute library, obtain and visited
The user asked and webpage attribute information, and according to above-mentioned analytic parameter search index table, retrieve this candidate applicable wide
Accuse intention, set up candidate's intention set;
Step S4, filters candidate's intention set, obtains optimal advertising intention;
Step S401, the intention filtering module in server limits according to precedence information, the frequency of candidate locations intention
Information, filters candidate's intention set;
Step S402, the intention order module in server uses above-mentioned clicking rate prediction model to be that each candidate's intention is pre-
Estimate clicking rate, and obtain clicking rate and estimate the highest ad creative Information, show optimal advertising intention as this;
Step S5, network redirection redirects;
Step S501, server is according to above-mentioned obtained optimal advertising intention, it is thus achieved that the network storage ground of advertising creative
Location, makes the target device of accessed user jump to the network storage ground of optimal advertising intention by network redirection mode
Location.
Preferably, in step sl, server is to obtain each user by network request parameter or data-interface to browse or point
The advertisement configuration information hit, described advertisement configuration information comprises all of action message, sequence information, creative information, media
Information, ad spot information.
Preferably, in step s 2, advertising display daily record is in units of the set time, to user's processed user behavior label,
Set up the data base of multiple label, calling interface.
Preferably, in step s 2, described log content at least includes: Log Types, user uniquely identify, regional information,
Info web, advertising display creative information, popularization plan information.
Preferably, in step s 2, the foundation of described clicking rate prediction model at least includes: creative information, user property are believed
Breath, webpage attribute information, website domain name or mobile phone application unique mark, time, area, operating system.
Preferably, in step s3, described intention filtering module is carried out for the intention thrown in gone out for intention indexed search
Filter.
Preferably, in step s 4, the response during network redirection is HTML (Hypertext Markup Language) redirects.
The ad personalization methods of exhibiting of the present invention, sets up clicking rate prediction model according to big data, analyzes the aesthetic of user
Hobby, shopping preferences, the preference of type of play style, filtered by intention and network redirection redirects mode, often
During secondary advertising display, show the material content being easiest to advertising conversion for user, to attract user to click on advertisement,
Complete the behaviors such as purchase, registration, meet the demand of user individual.Directly promote the input-output ratio of advertiser.
Aspect and advantage that the present invention adds will part be given in the following description, and part will become bright from the following description
Aobvious, or recognized by the practice of the present invention.
Accompanying drawing explanation
Above-mentioned and/or the additional aspect of the present invention and advantage will be apparent from from combining the accompanying drawings below description to embodiment
With easy to understand, wherein:
Fig. 1 is the flow chart of the present invention;
Fig. 2 is the structure chart of the present invention.
Detailed description of the invention
Embodiments of the invention are described below in detail, and the example of described embodiment is shown in the drawings, the most identical
Or similar label represents same or similar element or has the element of same or like function.Retouch below with reference to accompanying drawing
The embodiment stated is exemplary, it is intended to is used for explaining the present invention, and is not considered as limiting the invention.
The present invention provides a kind of ad personalization methods of exhibiting, with reference to accompanying drawing 1-2, comprises the steps:
Step S1, obtains the advertisement configuration information that each user is accessed.
Wherein, server is to obtain, by network request parameter or data-interface, the advertisement configuration letter that each user browses or clicks on
Breath, advertisement configuration information comprises all of action message, sequence information, creative information, media information, ad spot information.
Step S2, creates data base and advertisement filter rule.
Step S201, is synchronized to server by control server, by server by the advertisement configuration information of above-mentioned acquisition
Set up intention index and advertisement filter rule, set up concordance list and store.
Control server (Control Center): be used for comprising the functions such as intention index construct, update notification.In
Control server stores information in non-relational database cluster, then calls the more new interface of control server.
Step S202, is collected advertising display data, advertising display daily record by server, and by log transmission to cloud computing
Platform stores.
Advertising display daily record is in units of the set time, to user's processed user behavior label, sets up multiple label
Data base, calling interface.Log content includes: Log Types, user uniquely identify, regional information, browser,
Operation system information, access info web, advertising display creative information, popularization plan information, logging time etc..
User behaviors log storage (Session Log), in units of day, does data clear in distributed storage (HDFS)
Wash, user behavior merger, the structured storage such as point row.As by same user behavior merger, clean and repeat daily record, draw
The behaviors such as subnetting page browsing behavior, search behavior, advertisement exposure daily record, ad click behavior, conversion behavior.
Statistical server (Count Server), as log recording, log statistic analysis.Wherein, log recording
Concomitantly exposure monitoring, the requests such as monitoring, arrival monitoring, conversion monitoring of clicking on are recorded as magnetic by prescribed form for height
Dish daily record;Log statistic analysis is timing statistical log record, and updates advertisement base.
Step S203, cloud computing platform pass through log information, analyze customer attribute information, to each user process right
The label answered also stores to line in data base, and set up the user property storehouse corresponding with each user, webpage attribute library,
Behavioral characteristics storehouse, advertisement base.
User property storehouse (User Attribute): uniquely identify the key assignments of corresponding label for storing each user
To (Key-Value Pair), it is stored in non-relational database (Redis) cluster.Wherein user property includes
The information such as hobby, consumption demand, intention preference, sex, age, area.
Structured tag storehouse (Structural Label Base): be used for storing tree structure label, plane dimension scale
The data base of multiple label, the calling interfaces such as label.Use distribution type file storage data base (MongoDB) or relation
Data base (Mysql) stores.For saving webpage attribute library (Page Attribute), user property storehouse (User
Attribute), the storage efficiency of distributed storage (HDFS), the computational efficiency of server (server), permissible
Each label and weight is represented with the form of 8 byte long integers.
Page properties storehouse (Page Attribute): be used for storing the key assignments of each web page address (URL) corresponding label
To (Key-Value Pair), it is stored in non-relational database (Redis) cluster.Wherein, webpage attribute bag
Include hobby, consumption demand.
The page labels (Near-line Page Fetcher): be used for receiving creative server (Creative Server)
Asynchronous Request (required parameter is the URL that need to analyze), capture response web page address (URL) according to queue, and analyze
Page text, labels for web page address (URL), is stored in page properties storehouse (Page Attribute).
Behavioral characteristics storehouse (COEC, i.e. Click Over Expected Click): for record according to click logs and
The COEC feature that migration model (Bais Model) generates, is stored in non-relational database (Redis) cluster.
Advertisement base (AD Base), comprises all of action message, sequence information, creative information, media information, wide
Accuse position information, be stored in distribution type file storage data base (MongoDB) or relational database (Mysql);Separately
Outward, comprise the data such as data statistic analysis, data cube, be stored in distribution type file storage data base (MongoDB)
In.
Additionally, use the mode of audient's orientation to the corresponding label of each user processing.
Audient orients (Audience Targeting): for the set time, add in distributed storage (HDFS)
Work user behavior label.Including: interest tags, demand label, Commercial goods labels, game label, region label, people
Mouth attribute tags, implicit tag (PLSI, LDA), keyword label etc..
Step S204, according to advertising display data, ad click data, UAD, webpage attribute data,
Create clicking rate prediction model, and according to the training pattern in clicking rate prediction model, the request to features multiple on line,
Carry out clicking rate prediction, and training result is stored to intention order module;
Wherein, the foundation of clicking rate prediction model at least includes: creative information, customer attribute information, webpage attribute are believed
Breath, website domain name or mobile phone application unique mark, time, area, operating system.
Prediction module (CTR Model) on clicking rate prediction model line: comprise advertising message, user profile, webpage letter
The Logic Regression Models of breath, migration model (Bais Model), behavioral characteristics.Use the training of clicking rate prediction model
The model parameter of module (CTR Modeling) module training, to ad creative Information, user profile, webpage on line
The request of information characteristics carries out clicking rate prediction.
Clicking rate prediction model training module (Click Modeling): comprise forecast model training, migration model instruction
The modules such as the generation of white silk, behavioral characteristics and write, data syn-chronization.Wherein, it was predicted that model training, click on according to user
The feature that advertising decisions is relevant is trained (target data: advertisement exposure daily record, advertising display daily record;Characteristic:
User characteristics, page feature, characteristic of advertisement, behavioral characteristics);Migration model is trained, and clicks on advertisement according to user
The unrelated feature of decision-making is trained (target data: advertisement exposure daily record, advertising display daily record;Characteristic: wide
Accuse position, position, advertisement position size, advertisement putting delay, date and time, browser);Behavioral characteristics, according to spy
Levy all hits under composite set/all deviants summation, calculate the behavioral characteristics value of this feature combination, and deposit
Store up to non-relational database (Redis) cluster.Wherein, each behavioral characteristics value is using as forecast model
Feature.
Step S3, sets up candidate's intention set.
Step S301, when user accesses, the request analysis device in server, by resolving network request parameter, identifies
The advertisement parameters of the user accessed, sets up analytic parameter search index table.
Request analysis device (Request Parser): for resolving movable ID corresponding to interface, exposure I D, request header
Etc. information.
Step S302, the above-mentioned user property storehouse of intention search index in server, webpage attribute library, obtain and visited
The user asked and webpage attribute information, and according to above-mentioned analytic parameter search index table, retrieve this candidate applicable wide
Accuse intention, set up candidate's intention set.Use concordance list query candidate advertisement can improve recall precision, solve tradition
Advertising display in, the problem that the computational efficiency that causes due to advertising creative quantity low more.
Intention index (Creative Index): defined herein as inverted index, non-DNF indexes.Mainly to region,
Time, domain name, web page tag, user tag, advertisement position size, adline, weather, be indexed operation.
Step S4, filters candidate's intention set, obtains optimal advertising intention;
Step S401, the intention filtering module in server limits according to precedence information, the frequency of candidate locations intention
Information, filters candidate's intention set;
Wherein, intention filters and filters for the intention thrown in gone out for intention indexed search.
Intention filters (Creative Filter): filters, for intention, the intention thrown in retrieved and filters.Cross
Filter condition includes: the information such as frequency restriction, priority, playing sequence filter.If there is not available wound after Guo Lving
Meaning, then use acquiescence intention.
Step S402, the intention order module in server uses above-mentioned clicking rate prediction model to be that each candidate's intention is pre-
Estimate clicking rate, and obtain clicking rate and estimate the highest ad creative Information, show optimal advertising intention as this.
Intention order module (Creative Ranking): be used for calling clicking rate prediction model (CTR Model),
Estimate the clicking rate of each advertising creative, return the ad creative Information that clicking rate is the highest.
Above-mentioned steps is used for selecting advertising creative, promotes ad click effect, substantially can promote the effect of 20%-40%
Really, different advertisement position effects are different.
Step S5, network redirection redirects;
Step S501, server is according to above-mentioned obtained optimal advertising intention, it is thus achieved that the network storage ground of advertising creative
Location, makes the target device of accessed user jump to the network storage ground of optimal advertising intention by network redirection mode
Location.Using network redirection can support more equipment, the system of ad distribution business is easier to support.
Wherein, network redirection (Audience Targeting) is that the response in HTML (Hypertext Markup Language) redirects.
Redirect service (Jump Server) to be used for according to different advertising display ID (Impression Id) from non-pass
It is the destination address that in type data-base cluster, reading need to redirect, returns and redirect response, and record click logs.
Also include counter practise fraud (Anti-Spam), analyze exposure daily record, click logs, conversion daily record, by multiple spy
Levy, rule combination, it is judged that each media, the cheating situation of advertisement position.
The ad personalization methods of exhibiting of the present invention, sets up clicking rate prediction model according to big data, analyzes the aesthetic of user
Hobby, shopping preferences, the preference of type of play style, filtered by intention and network redirection redirects mode, often
During secondary advertising display, show the material content being easiest to advertising conversion for user, to attract user to click on advertisement,
Complete the behaviors such as purchase, registration, meet the demand of user individual.Directly promote the input-output ratio of advertiser.
Although above it has been shown and described that embodiments of the invention, it is to be understood that above-described embodiment is exemplary,
Being not considered as limiting the invention, those of ordinary skill in the art is without departing from the principle of the present invention and the situation of objective
Under above-described embodiment can be changed within the scope of the invention, revise, replace and modification.The scope of the present invention is by institute
Attached claim is extremely equal to restriction.
Claims (7)
1. an ad personalization methods of exhibiting, it is characterised in that comprise the steps:
Step S1, obtains the advertisement configuration information that each user is accessed;
Step S2, creates data base and advertisement filter rule;
Step S201, is synchronized to server by control server, by server by the advertisement configuration information of above-mentioned acquisition
Set up intention index and advertisement filter rule, set up concordance list and store;
Step S202, is collected advertising display data, advertising display daily record by server, and by log transmission to cloud computing
Platform stores;
Step S203, cloud computing platform pass through log information, analyze customer attribute information, to each user process right
The label answered also stores to line in data base, and set up the user property storehouse corresponding with each user, webpage attribute library,
Behavioral characteristics storehouse;
Step S204, according to advertising display data, ad click data, UAD, webpage attribute data,
Create clicking rate prediction model, and according to the training pattern in clicking rate prediction model, the request to features multiple on line,
Carry out clicking rate prediction, and training result is stored to intention order module;
Step S3, sets up candidate's intention set;
Step S301, when user accesses, the request analysis device in server, by resolving network request parameter, identifies
The advertisement parameters of the user accessed, sets up analytic parameter search index table;
Step S302, the above-mentioned user property storehouse of intention search index in server, webpage attribute library, obtain and visited
The user asked and webpage attribute information, and according to above-mentioned analytic parameter search index table, retrieve this candidate applicable wide
Accuse intention, set up candidate's intention set;
Step S4, filters candidate's intention set, obtains optimal advertising intention;
Step S401, the intention filtering module in server limits according to precedence information, the frequency of candidate locations intention
Information, filters candidate's intention set;
Step S402, the intention order module in server uses above-mentioned clicking rate prediction model to be that each candidate's intention is pre-
Estimate clicking rate, and obtain clicking rate and estimate the highest ad creative Information, show optimal advertising intention as this;
Step S5, network redirection redirects;
Step S501, server is according to above-mentioned obtained optimal advertising intention, it is thus achieved that the network storage ground of advertising creative
Location, makes the target device of accessed user jump to the network storage ground of optimal advertising intention by network redirection mode
Location.
2. a kind of ad personalization methods of exhibiting as claimed in claim 1, it is characterised in that: in step sl, service
Device is to obtain, by network request parameter or data-interface, the advertisement configuration information that each user browses or clicks on, and described advertisement is joined
Confidence breath comprises all of action message, sequence information, creative information, media information, ad spot information.
3. a kind of ad personalization methods of exhibiting as claimed in claim 1, it is characterised in that: in step s 2, advertisement
Show that daily record is in units of the set time, to user's processed user behavior label, set up the data base of multiple label, call
Interface.
4. a kind of ad personalization methods of exhibiting as claimed in claim 1, it is characterised in that: in step s 2, described
Log content at least includes: Log Types, user uniquely identify, regional information, info web, advertising display creative information,
Popularization plan information.
5. a kind of ad personalization methods of exhibiting as claimed in claim 1, it is characterised in that: in step s 2, described
Clicking rate prediction model according at least including: creative information, customer attribute information, webpage attribute information, website domain name or
Mobile phone application unique mark, time, area, operating system.
6. a kind of ad personalization methods of exhibiting as claimed in claim 1, it is characterised in that: the most described wound
Meaning filtering module filters for the intention thrown in gone out for intention indexed search.
7. a kind of ad personalization methods of exhibiting as claimed in claim 1, it is characterised in that: in step s 4, network
Redirect and redirect for the response in HTML (Hypertext Markup Language).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610373899.0A CN105956888A (en) | 2016-05-31 | 2016-05-31 | Advertisement personalized display method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610373899.0A CN105956888A (en) | 2016-05-31 | 2016-05-31 | Advertisement personalized display method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105956888A true CN105956888A (en) | 2016-09-21 |
Family
ID=56907294
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610373899.0A Pending CN105956888A (en) | 2016-05-31 | 2016-05-31 | Advertisement personalized display method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105956888A (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106504686A (en) * | 2016-12-30 | 2017-03-15 | 山东依鲁光电科技有限公司 | LED intelligent marketing advertisement service systems |
CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
CN107295095A (en) * | 2017-07-13 | 2017-10-24 | 百度在线网络技术(北京)有限公司 | The method and apparatus for pushing and showing advertisement |
CN107993097A (en) * | 2017-05-16 | 2018-05-04 | 广州舜飞信息科技有限公司 | A kind of marketing method for transformation of BiddingX platforms |
CN108230024A (en) * | 2017-12-29 | 2018-06-29 | 北京皮尔布莱尼软件有限公司 | Automotive engine system is launched based on the advertisement that clue is collected |
CN108256892A (en) * | 2016-12-29 | 2018-07-06 | 北京奇虎科技有限公司 | Method, apparatus, server and the system of advertising display are carried out in Webpage |
CN108256886A (en) * | 2016-12-29 | 2018-07-06 | 北京奇虎科技有限公司 | Advertisement placement method and device |
CN108335122A (en) * | 2017-01-19 | 2018-07-27 | 安徽优数科技有限公司 | A kind of concrete operation method of order creation |
CN108764950A (en) * | 2018-03-14 | 2018-11-06 | 北京奇虎科技有限公司 | Game recommdation method, apparatus and computer readable storage medium |
CN108932659A (en) * | 2018-07-24 | 2018-12-04 | 合肥爱玩动漫有限公司 | A kind of game mall system and method being associated with real goods |
CN108959324A (en) * | 2017-05-26 | 2018-12-07 | 腾讯科技(深圳)有限公司 | Predictor method, device and the storage medium of multimedia show resource quantity in stock |
CN108959393A (en) * | 2018-05-31 | 2018-12-07 | 北京五八信息技术有限公司 | Dynamic picture processing method, device and storage medium |
CN109461011A (en) * | 2017-09-05 | 2019-03-12 | 腾讯科技(深圳)有限公司 | Machine learning method, apparatus and system |
CN109460513A (en) * | 2018-10-31 | 2019-03-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating clicking rate prediction model |
CN109598543A (en) * | 2018-11-21 | 2019-04-09 | 优估(上海)信息科技有限公司 | A kind of method and system obtaining result from a variety of dimension conditions |
CN110516162A (en) * | 2019-09-02 | 2019-11-29 | 上海喜马拉雅科技有限公司 | A kind of information recommendation method, device, equipment and storage medium |
CN111177620A (en) * | 2019-12-20 | 2020-05-19 | 上海淇玥信息技术有限公司 | Page display method and device based on time dimension and electronic equipment |
CN111242654A (en) * | 2018-11-28 | 2020-06-05 | 北京沃东天骏信息技术有限公司 | Method and system for generating advertisement picture |
CN111401972A (en) * | 2020-04-13 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Data processing and advertisement scoring method, device and equipment |
CN112699296A (en) * | 2019-10-23 | 2021-04-23 | 百度在线网络技术(北京)有限公司 | Creative content generation method, device, equipment and medium for delivering information |
CN112823369A (en) * | 2018-10-09 | 2021-05-18 | 电子湾有限公司 | Generation of personalized banner images using machine learning |
CN113392340A (en) * | 2020-03-11 | 2021-09-14 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and computer readable medium for generating display content |
CN113793179A (en) * | 2021-09-13 | 2021-12-14 | 深圳市卓越鸿业信息技术有限公司 | Advertisement optimization analysis system based on big data and machine learning |
CN113822688A (en) * | 2020-06-23 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Advertisement conversion rate estimation method and device, storage medium and electronic equipment |
CN115471283A (en) * | 2022-11-07 | 2022-12-13 | 深圳市易售科技有限公司 | Advertisement batch delivery method, device, equipment and storage medium |
CN116029770A (en) * | 2022-12-26 | 2023-04-28 | 中国科学技术大学 | Intelligent pushing method, system, equipment and storage medium for advertising creative |
CN116167804A (en) * | 2023-04-19 | 2023-05-26 | 江西时刻互动科技股份有限公司 | Advertisement putting method and device, computer readable storage medium and electronic equipment |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020010757A1 (en) * | 1999-12-03 | 2002-01-24 | Joel Granik | Method and apparatus for replacement of on-line advertisements |
CN1339752A (en) * | 2000-07-28 | 2002-03-13 | 精工爱普生株式会社 | Personal newspaper with personal content and layout edition based on network |
WO2003054736A1 (en) * | 2001-12-17 | 2003-07-03 | France Telecom | Adapting presentation of downloaded documents to terminal reading modes |
CN101802860A (en) * | 2007-07-09 | 2010-08-11 | 维蒂公开股份有限公司 | Mobile device marketing and advertising platforms, methods, and systems |
CN102334118A (en) * | 2010-11-29 | 2012-01-25 | 华为技术有限公司 | Promoting method and system for personalized advertisement based on interested learning of user |
CN102346899A (en) * | 2011-10-08 | 2012-02-08 | 亿赞普(北京)科技有限公司 | Method and device for predicting advertisement click rate based on user behaviors |
CN102591983A (en) * | 2012-01-10 | 2012-07-18 | 凤凰在线(北京)信息技术有限公司 | Advertisement filter system and advertisement filter 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 |
CN103200262A (en) * | 2013-04-02 | 2013-07-10 | 亿赞普(北京)科技有限公司 | Method, device and system for advertisement scheduling based on mobile network |
CN103310003A (en) * | 2013-06-28 | 2013-09-18 | 华东师范大学 | Method and system for predicting click rate of new advertisement based on click log |
CN103345512A (en) * | 2013-07-06 | 2013-10-09 | 北京品友互动信息技术有限公司 | Online advertising click-through rate forecasting method and device based on user attribute |
-
2016
- 2016-05-31 CN CN201610373899.0A patent/CN105956888A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020010757A1 (en) * | 1999-12-03 | 2002-01-24 | Joel Granik | Method and apparatus for replacement of on-line advertisements |
CN1339752A (en) * | 2000-07-28 | 2002-03-13 | 精工爱普生株式会社 | Personal newspaper with personal content and layout edition based on network |
WO2003054736A1 (en) * | 2001-12-17 | 2003-07-03 | France Telecom | Adapting presentation of downloaded documents to terminal reading modes |
CN101802860A (en) * | 2007-07-09 | 2010-08-11 | 维蒂公开股份有限公司 | Mobile device marketing and advertising platforms, methods, and systems |
CN102334118A (en) * | 2010-11-29 | 2012-01-25 | 华为技术有限公司 | Promoting method and system for personalized advertisement based on interested learning of user |
CN102346899A (en) * | 2011-10-08 | 2012-02-08 | 亿赞普(北京)科技有限公司 | Method and device for predicting advertisement click rate based on user behaviors |
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 |
CN102591983A (en) * | 2012-01-10 | 2012-07-18 | 凤凰在线(北京)信息技术有限公司 | Advertisement filter system and advertisement filter method |
CN103200262A (en) * | 2013-04-02 | 2013-07-10 | 亿赞普(北京)科技有限公司 | Method, device and system for advertisement scheduling based on mobile network |
CN103310003A (en) * | 2013-06-28 | 2013-09-18 | 华东师范大学 | Method and system for predicting click rate of new advertisement based on click log |
CN103345512A (en) * | 2013-07-06 | 2013-10-09 | 北京品友互动信息技术有限公司 | Online advertising click-through rate forecasting method and device based on user attribute |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108256892A (en) * | 2016-12-29 | 2018-07-06 | 北京奇虎科技有限公司 | Method, apparatus, server and the system of advertising display are carried out in Webpage |
CN108256886A (en) * | 2016-12-29 | 2018-07-06 | 北京奇虎科技有限公司 | Advertisement placement method and device |
CN106504686A (en) * | 2016-12-30 | 2017-03-15 | 山东依鲁光电科技有限公司 | LED intelligent marketing advertisement service systems |
CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
CN108335122A (en) * | 2017-01-19 | 2018-07-27 | 安徽优数科技有限公司 | A kind of concrete operation method of order creation |
CN107993097A (en) * | 2017-05-16 | 2018-05-04 | 广州舜飞信息科技有限公司 | A kind of marketing method for transformation of BiddingX platforms |
CN108959324A (en) * | 2017-05-26 | 2018-12-07 | 腾讯科技(深圳)有限公司 | Predictor method, device and the storage medium of multimedia show resource quantity in stock |
CN108959324B (en) * | 2017-05-26 | 2022-04-15 | 腾讯科技(深圳)有限公司 | Method and device for estimating multimedia display resource inventory and storage medium |
CN107295095A (en) * | 2017-07-13 | 2017-10-24 | 百度在线网络技术(北京)有限公司 | The method and apparatus for pushing and showing advertisement |
CN109461011A (en) * | 2017-09-05 | 2019-03-12 | 腾讯科技(深圳)有限公司 | Machine learning method, apparatus and system |
CN109461011B (en) * | 2017-09-05 | 2022-11-15 | 腾讯科技(深圳)有限公司 | Machine learning method, device and system |
CN108230024A (en) * | 2017-12-29 | 2018-06-29 | 北京皮尔布莱尼软件有限公司 | Automotive engine system is launched based on the advertisement that clue is collected |
CN108230024B (en) * | 2017-12-29 | 2020-12-01 | 北京皮尔布莱尼软件有限公司 | Advertisement putting engine system based on clue collection |
CN108764950A (en) * | 2018-03-14 | 2018-11-06 | 北京奇虎科技有限公司 | Game recommdation method, apparatus and computer readable storage medium |
CN108959393A (en) * | 2018-05-31 | 2018-12-07 | 北京五八信息技术有限公司 | Dynamic picture processing method, device and storage medium |
CN108932659A (en) * | 2018-07-24 | 2018-12-04 | 合肥爱玩动漫有限公司 | A kind of game mall system and method being associated with real goods |
CN112823369A (en) * | 2018-10-09 | 2021-05-18 | 电子湾有限公司 | Generation of personalized banner images using machine learning |
CN109460513A (en) * | 2018-10-31 | 2019-03-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating clicking rate prediction model |
CN109460513B (en) * | 2018-10-31 | 2021-01-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating click rate prediction model |
CN109598543A (en) * | 2018-11-21 | 2019-04-09 | 优估(上海)信息科技有限公司 | A kind of method and system obtaining result from a variety of dimension conditions |
CN111242654B (en) * | 2018-11-28 | 2021-04-30 | 北京沃东天骏信息技术有限公司 | Method and system for generating advertisement picture |
CN111242654A (en) * | 2018-11-28 | 2020-06-05 | 北京沃东天骏信息技术有限公司 | Method and system for generating advertisement picture |
CN110516162A (en) * | 2019-09-02 | 2019-11-29 | 上海喜马拉雅科技有限公司 | A kind of information recommendation method, device, equipment and storage medium |
CN110516162B (en) * | 2019-09-02 | 2023-03-28 | 上海喜马拉雅科技有限公司 | Information recommendation method, device, equipment and storage medium |
CN112699296A (en) * | 2019-10-23 | 2021-04-23 | 百度在线网络技术(北京)有限公司 | Creative content generation method, device, equipment and medium for delivering information |
CN112699296B (en) * | 2019-10-23 | 2023-10-24 | 百度在线网络技术(北京)有限公司 | Creative content generation method, device, equipment and medium for putting information |
CN111177620B (en) * | 2019-12-20 | 2024-03-01 | 上海淇玥信息技术有限公司 | Page display method and device based on time dimension and electronic equipment |
CN111177620A (en) * | 2019-12-20 | 2020-05-19 | 上海淇玥信息技术有限公司 | Page display method and device based on time dimension and electronic equipment |
CN113392340A (en) * | 2020-03-11 | 2021-09-14 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and computer readable medium for generating display content |
CN111401972A (en) * | 2020-04-13 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Data processing and advertisement scoring method, device and equipment |
CN113822688A (en) * | 2020-06-23 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Advertisement conversion rate estimation method and device, storage medium and electronic equipment |
CN113793179A (en) * | 2021-09-13 | 2021-12-14 | 深圳市卓越鸿业信息技术有限公司 | Advertisement optimization analysis system based on big data and machine learning |
CN115471283A (en) * | 2022-11-07 | 2022-12-13 | 深圳市易售科技有限公司 | Advertisement batch delivery method, device, equipment and storage medium |
CN116029770A (en) * | 2022-12-26 | 2023-04-28 | 中国科学技术大学 | Intelligent pushing method, system, equipment and storage medium for advertising creative |
CN116029770B (en) * | 2022-12-26 | 2023-10-20 | 中国科学技术大学 | Intelligent pushing method, system, equipment and storage medium for advertising creative |
CN116167804A (en) * | 2023-04-19 | 2023-05-26 | 江西时刻互动科技股份有限公司 | Advertisement putting method and device, computer readable storage medium and electronic equipment |
CN116167804B (en) * | 2023-04-19 | 2023-07-21 | 江西时刻互动科技股份有限公司 | Advertisement putting method and device, computer readable storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105956888A (en) | Advertisement personalized display method | |
JP6067713B2 (en) | Understand the effectiveness of communications propagated through social networking systems | |
CN103946886B (en) | Structure objects and action on social networking system | |
CN106803190A (en) | A kind of ad personalization supplying system and method | |
US9626443B2 (en) | Searching and accessing application functionality | |
CN102647462B (en) | Application acquisition and sending method and device | |
CN102567897B (en) | For showing the method and system of promotional content to the user of communication equipment | |
CN107451861B (en) | Method for identifying user internet access characteristics under big data | |
CN108776907A (en) | Advertisement intelligent recommends method, server and storage medium | |
US20140188627A1 (en) | Method and system for creating user based summaries for content distribution | |
US20120078725A1 (en) | Method and system for contextual advertisement recommendation across multiple devices of content delivery | |
CN106408329A (en) | Advertisement visitor retrieving method and advertisement putting system | |
CN105959745A (en) | Advertising method and system | |
US20130211909A1 (en) | Server device and advertisment image distribution and program | |
CN102629273A (en) | Advertising information pushing method based on browser, device and browser system | |
JP2017522662A (en) | Automated click type selection for content performance optimization | |
CN101178737A (en) | Method and system for publishing information related to internet key character | |
CN102708174A (en) | Method and device for displaying rich media information in browser | |
CN108230025A (en) | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement | |
CN109963259A (en) | A kind of note transmission method and device | |
US20170046745A1 (en) | Method and system for providing relevant advertisements | |
JP4804372B2 (en) | Advertisement distribution order determination method, advertisement distribution system, advertisement distribution order determination apparatus, and computer program | |
CN101180668A (en) | Web advertisement system and web advertisement program | |
CN109598543A (en) | A kind of method and system obtaining result from a variety of dimension conditions | |
CN1996301A (en) | Method and system for distributing information directly associated with user |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160921 |