CN103489117A - Method and system for information releasing - Google Patents
Method and system for information releasing Download PDFInfo
- Publication number
- CN103489117A CN103489117A CN201210192864.9A CN201210192864A CN103489117A CN 103489117 A CN103489117 A CN 103489117A CN 201210192864 A CN201210192864 A CN 201210192864A CN 103489117 A CN103489117 A CN 103489117A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- user behavior
- time
- feature
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A method for information releasing is characterized by comprising the following steps that user behavior characteristics and information characteristics corresponding to the user behavior characteristics of a user are recorded; weights of different user behavior characteristics are obtained; time of the user behavior characteristics is obtained, time weights are determined according to time, the closer the time of user behaviors is, the higher the time weights are, and the farther the time is, the lower the time weights are; the weighted value of the same-kind user behavior characteristics of the same user at different periods of time is determined according to the weights of the different user behavior characteristics and the time weights; according to information characteristics of multi-preset-information to be released, corresponding relations of information characteristics of the user behavior characteristics and the weighted values of the user behavior characteristics, the probability value of the clicked preset information containing the information characteristics is calculated; the preset information is pushed to the user according to the probability value. The invention further provides a corresponding information releasing system. The probability value figured out through the method embodies current interestingness of the user, and thus more accurate information releasing is achieved.
Description
Technical field
The present invention relates to field of computer technology, particularly relate to information distribution method and the system of internet.
Background technology
Along with the fast development of internet, netizen's quantity rapidly expands, and the web advertisement more and more is subject to liking of advertiser, and its injected volume has surpassed the conventional ads such as newspaper, TV.Current charging mode mainly contains CPM(by exposure charge), CPD(is by a day charge), CPC(is by clicking charge), CPA(is by the effect charge), CPS(is by the sales volume deduction) etc., for the medium and small advertiser of major part, the pattern that CPC, CPA etc. pay by effect is more and more welcome.Promote the clicking rate of advertisement, can not only promote advertiser's satisfaction, go back and can directly promote the advertising platform income.
Current advertisement putting rule has:
1) by advertisement and advertisement position specification coupling and content of pages coupling, decide advertisement putting.This method can solve the coupling of advertisement and advertisement position, but, to different user, display advertisement is identical, and personalized disappearance is limited to clicking rate lifting degree.
2) the directed coupling of the population-based characteristic row such as user's age, sex, region.The method has been introduced certain customers' feature, but this part feature is static nature substantially, and the long period is constant, also just causes the user to show for a long time same advertisement.And the population-based feature has certain deviation with click interest wish, low to the discrimination of advertisement.For example, not all women likes best and clicks the women's dress advertisement any time, and some constantly also may like game advertisement some women.
A lot of ad systems have been used gathering of above method, but lack the expansion to many time varying characteristics, make user profile lack to some extent, can not calculate more accurately the matching degree of user and advertisement.
Summary of the invention
Based on this, provide a kind of more accurate information distribution method and system.
A kind of information distribution method, comprise the steps:
The user behavior feature of counting user and corresponding information characteristics;
Obtain the weight of different user behavioural characteristic;
Obtain the time of described user behavior feature, determine time weighting according to the described time, the time of described user behavior is nearer, and described time weighting is larger, and the time is far away, and described time weighting is less;
According to weight and the described time weighting of described different user behavioural characteristic, determine the weighted value of user behavior feature of the same race of same user's different time;
The corresponding relation of the information characteristics of the presupposed information of throwing according to a plurality of wishs and the information characteristics of described user behavior feature, and the weighted value of each described user behavior feature, calculate the clicked probable value of each presupposed information that comprises described information characteristics;
According to described probable value, described presupposed information is pushed to described user.
In one of them embodiment, described user behavior feature comprises with lower at least one: browse, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, containing the microblogging of certain keyword, post or forward.
In one of them embodiment, the user behavior feature of described counting user and corresponding information characteristics comprise: obtain described user's user ID, according to described user ID, obtain and add up described user at the user behavior feature of heterogeneous networks platform and corresponding information characteristics.
In one of them embodiment, the user behavior feature of described counting user and corresponding information characteristics carry out in a preset time period, and different user behavior features adopts different preset time period to be added up.
In one of them embodiment, the available time of described preset time period length based on described user behavior, available time is longer, and preset time period is longer.
In one of them embodiment, the importance of this information that the weight of described user behavior feature shows based on user behavior to described user, importance is higher, and weight is larger.
In one of them embodiment, describedly according to described probable value, described presupposed information is pushed to described user and comprises: front at least one presupposed information that probable value is the highest is pushed to described user.
A kind of information jettison system, it comprises: feature acquisition module, Weight Acquisition module, time weighting acquisition module, assignment module, probability calculation module and information pushing module,
Described feature acquisition module is for user behavior feature and the corresponding information characteristics of counting user;
Described Weight Acquisition module is for obtaining the weight of different user behavioural characteristic;
Described time weighting acquisition module is for time of obtaining described user behavior feature, determines time weighting according to the described time, and the time of described user behavior is nearer, and described time weighting is larger, and the time is far away, and described time weighting is less;
Described assignment module is for according to weight and the described time weighting of described different user behavioural characteristic, determines the weighted value of user behavior feature of the same race of same user's different time;
The corresponding relation of the information characteristics of the presupposed information that described probability calculation module is thrown in for a plurality of wishs according to default and the information characteristics of described user behavior feature, and the weighted value of each described user behavior feature, calculate each and comprise the clicked probable value of described information characteristics presupposed information;
Described information pushing module is for being pushed to described user according to described probable value by default presupposed information.
In one of them embodiment, described user behavior feature comprise browse, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, containing the microblogging of certain keyword post or forward at least one.
In one of them embodiment, described feature acquisition module is used for first obtaining described user's user ID, then obtains and add up described user at the user behavior feature of heterogeneous networks platform and corresponding information characteristics according to described user ID.
In one of them embodiment, the user behavior feature of described feature acquisition module counting user and corresponding information characteristics carry out in a preset time period, and different user behavior features adopts different preset time period to be added up.
In one of them embodiment, the available time of described preset time period length based on described user behavior, available time is longer, and preset time period is longer.
In one of them embodiment, the importance of this information that the different weights of described default different user behavioural characteristic show based on user behavior to described user, importance is higher, and weight is larger.
In one of them embodiment, describedly according to described probable value, described presupposed information is pushed to described user and comprises: extract the highest front at least one presupposed information of probable value according to described probable value and be pushed to described user.
Above-mentioned information distribution method and system, by different user behavior features, different weights is set, and the generation time of same user behavior feature is successively arranged to different weighted values, the probable value of calculating more can embody the current interest-degree of user, thereby realizes that information is thrown in more accurately.
The accompanying drawing explanation
The flow chart of steps of the information distribution method that Fig. 1 is an embodiment;
The functional block diagram of the information jettison system that Fig. 2 is an embodiment;
Fig. 3 describes from macroscopic perspective the prediction flow process Organization Chart of clicking probability;
Fig. 4 is the integration process flow diagram that the feature shown in Fig. 3 gathers user behavior feature in layer.
Specific embodiment
The purpose of this programme is: calculate one or several presupposed informations of user interest Du Genggao (clicking probability larger) a plurality of presupposed informations of throwing in from wish, and show the user.Realize this function, feature that can reference comprises:
1, information characteristics, such as classification, price, title etc.;
2, information is thrown in window feature, such as the classification of size, the affiliated page etc.;
3, user's static nature, such as age, region, sex, educational background etc.;
4, the user behavior feature, such as browsing, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, post or forwarding etc. containing the microblogging of certain keyword.
First three kind feature can be directly used in a plurality of presupposed informations that wish is thrown in and be filtered, and obtains candidate's presupposed information.The user behavior feature, click the probability size of each presupposed information for the presupposed information user of calculated candidate.
As shown in Figure 1, the flow chart of steps of its information distribution method that is an embodiment, comprise the steps:
Step S101, the user behavior feature of counting user and corresponding information characteristics.
Described user behavior feature comprises at least one in " browse, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, containing the microblogging of certain keyword, post or forward ".In the present embodiment, with the information characteristics corresponding for behavioural characteristic, be preferably the feature of commodity, for example " commodity classification ", as " shoes ", " skirt ", " mobile phone " etc., can be also the classification specific to certain brand, for example " Samsung mobile phone ".User behavior feature combining information feature can be enumerated example as browsed shoes, the collection skirt, and mobile phone etc. places an order.
In other embodiment, the user behavior feature of described counting user and corresponding information characteristics carry out in a preset time period, and different user behavior features, adopt different preset time period to be added up.The available time of described preset time period length based on described user behavior, available time is longer, and preset time period is longer.In one embodiment, preset time period length is followed the principle that " browse, collect, place an order, strike a bargain " reduces successively.As: " browsing " information of nearly 15 days of counting user, " collection " information of nearly 10 days, " placing an order " information of nearly 5 days, and " conclusion of the business " information of nearly 2 days.
Because the behavior that browsing is a kind of longer-term, consciousness property is not strong, need a lot of days even monthly cycles to accumulate to reflect user's Long-term Interest.And place an order, be the behavior that a kind of property realized is strong, impulsion property is high, if the time has been grown, the user has completed conclusion of the business, may can be not interested in this type of information again recently.The statistics of so according to the different time cycle, the different user behavioural characteristic being carried out, can express the current interest of user more accurately.
In the present embodiment, the user behavior feature of described counting user and corresponding information characteristics comprise: obtain described user's user ID, according to described user ID, obtain and add up described user at the user behavior feature of heterogeneous networks platform and corresponding information characteristics.As by the action message of user on each platform of having connected such as cookie or alliance websites, so just can accomplish more transfer learning, the performance by the user on other platforms, reflect the possible interest of user on this platform.The user behavior feature of different platform can arrange different weights.
The life cycle of information recommendation is often very short, and the advertisement of take is example as wanting impression information, and it on average only has several days, and some advertisements even only have 1,2 day.Rely on like this advertisement self to throw in history and predict the click probability, because its behavior property is few, cover customer volume low, accuracy rate is limited.The behavioural characteristic that experiment showed, the user usually has stronger relevance with ad click, then we just the user characteristics of other platforms of consideration introducing carry out the click wish of predictive user to advertisement.For example, the user has just collected a women's dress on electric business's platform, represents that it is interesting to women's dress, and, when this user browses portal website's platform, this user is thrown in to the advertisement that women's dress is relevant, and it clicks wish will be stronger.This related platform is more, and the user characteristics that we can catch will be more, and predictive user will be more accurate to the click wish of which advertisement.
Step S102, obtain the weight of different user behavioural characteristic.
The importance of this information that the weight of described user behavior feature shows based on user behavior to described user, importance is higher, and weight is larger.As " browsing " once, count 5 minutes, " collection " once counted 10 minutes, " placing an order " once counts 50 minutes, " conclusion of the business " once counted 80 minutes.In the present embodiment, the weighted value of " browse, collect, place an order, strike a bargain " from low to high.
Step S103, the time of obtaining described user behavior feature, determine time weighting according to the described time, the time of described user behavior is nearer, and described time weighting is larger, and the time is far away, and described time weighting is less.
Because nearer browsing more can reflect the hobby that the user is nearest, should give and higher weight, and behavior far away should be given and lower weight.Take " placing an order " as example, the conclusion of the business of first day is counted 50 minutes at every turn recently, and the conclusion of the business of nearest second day is counted 40 minutes at every turn, and the nearest conclusion of the business of the 3rd day is scored 30 minutes at every turn ...Be that assignment decayed from the near to the remote according to the time, can realize by the time attenuation function.
Step S104, according to weight and the described time weighting of described different user behavioural characteristic, determine the weighted value of user behavior feature of the same race of same user's different time.
Step S105, the corresponding relation of the information characteristics of the presupposed information of throwing according to a plurality of wishs and the information characteristics of described user behavior feature, and the weighted value of each described user behavior feature, calculate each and comprise the clicked probable value of described information characteristics presupposed information.
In one embodiment, step S105 also can utilize classification or regression model in conjunction with user's static nature (age, sex etc.), information characteristics (classification, price etc.), calculates the click probability of user to each presupposed information.
Step S106, be pushed to described user according to described probable value by described presupposed information.
Describedly according to described probable value, described presupposed information is pushed to described user and comprises: front at least one presupposed information that probable value is the highest is pushed to described user.
Above-mentioned information distribution method arranges different weights by different user behavior features, and the generation time of same user behavior feature is successively arranged to different weighted values, the probable value of calculating more can embody the current interest-degree of user, thereby realizes that information is thrown in more accurately.
In other embodiment, described information distribution method can also comprise: by information characteristics, information is thrown in window feature, and at least one step that a plurality of presupposed informations are screened in user's static nature.
As shown in Figure 2, the functional block diagram of the information jettison system 20 that it is an embodiment comprises: feature acquisition module 202, Weight Acquisition module 203, time weighting acquisition module 204, assignment module 205, probability calculation module 206 and information pushing module 207.
Time weighting acquisition module 204 is for obtaining the time of described user behavior feature, determines time weighting according to the described time, and the time of described user behavior is nearer, and described time weighting is larger, and the time is far away, and described time weighting is less.
The corresponding relation of the information characteristics of the presupposed information that probability calculation module 206 is thrown in for a plurality of wishs according to default and the information characteristics of described user behavior feature, and the weighted value of each described user behavior feature, calculate each and comprise the clicked probable value of described information characteristics presupposed information.
In one embodiment, described default presupposed information and corresponding information characteristics thereof are stored in a memory module.
In one embodiment, describedly according to described probable value, described presupposed information is pushed to described user and comprises: extract front at least one presupposed information that probable value is the highest according to described probable value and be pushed to described user from described memory module.
In one embodiment, feature acquisition module 202, for obtaining described user's user ID, obtains and adds up described user at the user behavior feature of heterogeneous networks platform and corresponding information characteristics according to described user ID.
Described user behavior feature comprises at least one in " browse, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, containing the microblogging of certain keyword, post or forward ".
The user behavior feature of described feature acquisition module 202 counting users and corresponding information characteristics carry out in a preset time period, and different user behavior features, adopt different preset time period to be added up.The available time of described preset time period length based on described user behavior, available time is longer, and preset time period is longer.
The importance of this information that the different weights of described default different user behavioural characteristic show based on user behavior to described user, importance is higher, and weight is larger.In one embodiment, the weight of " browse, collect, place an order, strike a bargain " from low to high.
Described Preset Time decay principle is that the time is nearer, and weight is larger, and the time is far away, and weight is less.
Above-mentioned information jettison system 20 arranges different weights by different user behavior features, and the generation time of same user behavior feature is successively arranged to different weighted values, the probable value of calculating more can embody the current interest-degree of user, thereby realizes that information is thrown in more accurately.
In other embodiment, described information jettison system can also comprise the screening module, and for by information characteristics, information is thrown in window feature, and at least one in user's static nature screened a plurality of presupposed informations.Information pushing module 207 is selected presupposed information for the presupposed information from screening, and is pushed to described user.
The advertisement of take is example as wanting impression information, refers to Fig. 3, and it is to describe from macroscopic perspective the prediction flow process Organization Chart of clicking probability, and it comprises:
Feature gathers layer
This layer data comprises following characteristics:
Characteristic of advertisement: the classification that comprises advertisement, title, unit price, and the information such as advertiser.
Advertisement position feature: comprise advertisement position specification, affiliated page classification, can throw the information such as advertising listing
User's static nature: comprise the relatively stable fixed informations such as age of user, sex, region, occupation.
User behavior feature: mainly refer to that the behavior of user on each platform gathers.This feature extensibility is strong, from resource, can be the independent characteristic of each platform resource, can be also the feature that gathers of a plurality of resource datas; From the time, have by the hour, by sky, monthly wait the tabulate statistics feature of each granularity.General time span is longer, and data are more stable, and the time is nearer, and data are more timely, and this layer of needs have been taken into account ageing and accuracys data.
The prediction logic layer
It gathers the feature of layer by a kind of machine learning method of supporting the large-scale data amount based on feature, the click probability of predictive user each candidate's advertisement on different advertisement positions, output top N advertising listing.Comprised advertisement in this top N list and clicked probability, during input, can throw according to clicking the probability carousel.
The advertisement putting layer
For accepting external user, ad spot information, by the advertisement position resource, user's directed information, do elementary filtration, calculates candidate's advertising listing, is transferred to the prediction logic layer.And receive the top N advertising listing that the prediction logic layer returns, according to regular broadcast advertisement.
Refer to Fig. 4, it is the integration flow process that the feature shown in Fig. 3 gathers user behavior feature in layer, and main modular is as follows:
The platform resource layer
Store the source data of each platform self, but each platform is parallel expansion, data source is more usually, and the user that can represent and the match information of advertisement are more, and the click probability calculated is more accurate.
Platform time varying characteristic layer
The feature screened from the platform resource layer, for the advertisement launching platform characteristics, to the screening filtering of some noise data, do the operations such as data screening, cleaning, conversion, statistical summaries to raw data.
Each platform features is analyzed, for different features, adopted different time granularity statistical summaries.For example, unique user at least needs N days granularities just meaningful to the clicking rate of certain advertisement, and the different sexes user can arrive a minute granularity to the clicking rate of different advertisements.Again for example, due to platform to women's dress to browse click volume large, to women's dress, as long as the combined data of 1 day, and more day data could the stably expressed user interests possibly to camera.
Multi-platform feature clustering layer
Comprehensive a plurality of platform resource feature, calculate the feature that level is higher.The data of browsing, clicking such as gathering the platforms such as a plurality of websites, electric business, different time granularity, gather the shot and long term interest of this user to women's dress.Because each platform data amount is limited, the embodiment user interest that the behavior of each user on single platform can not be complete, and gather multi-platform data, can more comprehensive reflection user interest.
Time decay function layer
Interval according to selected time change, do the time attenuation transform in this interval.Such as a user clicked certain advertisement before 1 minute, its importance degree will, higher than the click before 10 minutes, because the time more closely more can be reflected user's up-to-date interest, just need to recommend more relevant advertisement.We use the multiple life cycle function such as logistic selective, and the time is nearer, and weight is larger, and the time is far away, and weight is less, thereby reach with becoming in window for the moment the purpose of time decay.
The user behavior characteristic layer
This layer gathers the submodule of layer as feature, become cluster data while becoming many that behavioral data and a plurality of platform gather while having gathered each platform oneself many, and every kind of data have all comprised many latitudes feature that the different periods expand.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (14)
1. an information distribution method, is characterized in that, comprises the steps:
The user behavior feature of counting user and corresponding information characteristics;
Obtain the weight of different user behavioural characteristic;
Obtain the time of described user behavior feature, determine time weighting according to the described time, the time of described user behavior is nearer, and described time weighting is larger, and the time is far away, and described time weighting is less;
According to weight and the described time weighting of described different user behavioural characteristic, determine the weighted value of user behavior feature of the same race of same user's different time;
The corresponding relation of the information characteristics of the presupposed information of throwing according to a plurality of wishs and the information characteristics of described user behavior feature, and the weighted value of each described user behavior feature, calculate the clicked probable value of each presupposed information that comprises described information characteristics;
According to described probable value, described presupposed information is pushed to described user.
2. information distribution method according to claim 1, it is characterized in that, described user behavior feature comprises with lower at least one: browse, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, containing the microblogging of certain keyword, post or forward.
3. information distribution method according to claim 1, it is characterized in that, the user behavior feature of described counting user and corresponding information characteristics comprise: obtain described user's user ID, according to described user ID, obtain and add up described user at the user behavior feature of heterogeneous networks platform and corresponding information characteristics.
4. information distribution method according to claim 1, it is characterized in that, the user behavior feature of described counting user and corresponding information characteristics carry out in a preset time period, and different user behavior features adopts different preset time period to be added up.
5. information distribution method according to claim 4, is characterized in that, the available time of described preset time period length based on described user behavior, and available time is longer, and preset time period is longer.
6. information distribution method according to claim 1, is characterized in that, the importance of this information that the weight of described user behavior feature shows based on user behavior to described user, and importance is higher, and weight is larger.
7. information distribution method according to claim 1, is characterized in that, describedly according to described probable value, described presupposed information is pushed to described user and comprises: front at least one presupposed information that probable value is the highest is pushed to described user.
8. an information jettison system, is characterized in that, it comprises: feature acquisition module, Weight Acquisition module, time weighting acquisition module, assignment module, probability calculation module and information pushing module,
Described feature acquisition module is for user behavior feature and the corresponding information characteristics of counting user;
Described Weight Acquisition module is for obtaining the weight of different user behavioural characteristic;
Described time weighting acquisition module is for time of obtaining described user behavior feature, determines time weighting according to the described time, and the time of described user behavior is nearer, and described time weighting is larger, and the time is far away, and described time weighting is less;
Described assignment module is for according to weight and the described time weighting of described different user behavioural characteristic, determines the weighted value of user behavior feature of the same race of same user's different time;
The corresponding relation of the information characteristics of the presupposed information that described probability calculation module is thrown in for a plurality of wishs according to default and the information characteristics of described user behavior feature, and the weighted value of each described user behavior feature, calculate each and comprise the clicked probable value of described information characteristics presupposed information;
Described information pushing module is for being pushed to described user according to described probable value by default presupposed information.
9. information jettison system according to claim 8, it is characterized in that, described user behavior feature comprise browse, collect, place an order, the download of the registration of the login of conclusion of the business, APP information, game, game, game, containing the microblogging of certain keyword post or forward at least one.
10. information jettison system according to claim 8, it is characterized in that, described feature acquisition module is used for first obtaining described user's user ID, then obtains and add up described user at the user behavior feature of heterogeneous networks platform and corresponding information characteristics according to described user ID.
11. information jettison system according to claim 8, it is characterized in that, the user behavior feature of described feature acquisition module counting user and corresponding information characteristics carry out in a preset time period, and different user behavior features adopts different preset time period to be added up.
12. information jettison system according to claim 11, is characterized in that, the available time of described preset time period length based on described user behavior, and available time is longer, and preset time period is longer.
13. information jettison system according to claim 8, is characterized in that, the importance of this information that the different weights of described default different user behavioural characteristic show based on user behavior to described user, and importance is higher, and weight is larger.
14. information jettison system according to claim 8, it is characterized in that, describedly according to described probable value, described presupposed information is pushed to described user and comprises: extract the highest front at least one presupposed information of probable value according to described probable value and be pushed to described user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210192864.9A CN103489117B (en) | 2012-06-12 | 2012-06-12 | Method and system for information releasing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210192864.9A CN103489117B (en) | 2012-06-12 | 2012-06-12 | Method and system for information releasing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103489117A true CN103489117A (en) | 2014-01-01 |
| CN103489117B CN103489117B (en) | 2015-07-01 |
Family
ID=49829319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210192864.9A Active CN103489117B (en) | 2012-06-12 | 2012-06-12 | Method and system for information releasing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103489117B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537502A (en) * | 2015-01-15 | 2015-04-22 | 北京嘀嘀无限科技发展有限公司 | Method and device for processing orders |
| CN105096152A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Commodity popularity-based operation execution method and device |
| CN105677895A (en) * | 2016-02-03 | 2016-06-15 | 北京千米时代科技有限公司 | Device and method for acquiring mobile internet user behavior characteristic attribute |
| CN105843864A (en) * | 2016-03-17 | 2016-08-10 | 合网络技术（北京）有限公司 | Message pushing method and device |
| CN105898420A (en) * | 2015-01-09 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Video recommendation method and device, and electronic equipment |
| WO2016131220A1 (en) * | 2015-02-16 | 2016-08-25 | Lee Ying Chiu Herbert | Characterized wireless signal mobile messaging method and system |
| WO2017035970A1 (en) * | 2015-08-31 | 2017-03-09 | 北京百度网讯科技有限公司 | Information pushing method and apparatus |
| WO2017075980A1 (en) * | 2015-11-06 | 2017-05-11 | 北京金山安全软件有限公司 | Information pushing method and apparatus |
| CN106875201A (en) * | 2015-12-11 | 2017-06-20 | 北京国双科技有限公司 | The acquisition methods and device of the visible factor of advertisement |
| CN106886915A (en) * | 2017-01-17 | 2017-06-23 | 华南理工大学 | A kind of ad click predictor method based on time decay sampling |
| CN107315548A (en) * | 2016-04-26 | 2017-11-03 | 富士施乐株式会社 | Sending destination change device, print system and sending destination variation |
| CN107590691A (en) * | 2017-09-06 | 2018-01-16 | 晶赞广告（上海）有限公司 | A kind of information issuing method and device, storage medium, terminal |
| CN107656918A (en) * | 2017-05-10 | 2018-02-02 | 平安科技（深圳）有限公司 | Obtain the method and device of targeted customer |
| CN107851262A (en) * | 2015-07-09 | 2018-03-27 | 华为技术有限公司 | A kind of advertisement value determines method and device |
| CN108197288A (en) * | 2018-01-16 | 2018-06-22 | 平安好房（上海）电子商务有限公司 | According to source of houses method for pushing, device, equipment and the medium of user characteristics preference |
| CN108255856A (en) * | 2016-12-29 | 2018-07-06 | 阿里巴巴集团控股有限公司 | A kind of information object dissemination method and device |
| CN108256971A (en) * | 2018-01-16 | 2018-07-06 | 平安好房（上海）电子商务有限公司 | User's source of houses portrait update method, device, equipment and storage medium |
| WO2018148894A1 (en) * | 2017-02-16 | 2018-08-23 | 深圳大学 | Time-dependent reputation evaluation algorithm based on scoring network |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN109189812A (en) * | 2018-08-14 | 2019-01-11 | 中国平安人寿保险股份有限公司 | A kind of index querying method, computer readable storage medium and server |
| CN109214842A (en) * | 2017-06-30 | 2019-01-15 | 北京金山安全软件有限公司 | Information popularization method, device and equipment |
| CN109801107A (en) * | 2019-01-17 | 2019-05-24 | 有米科技股份有限公司 | A kind of advertisement liveness predictor method, device, server and storage medium |
| CN109840782A (en) * | 2017-11-24 | 2019-06-04 | 腾讯科技（深圳）有限公司 | Clicking rate prediction technique, device, server and storage medium |
| CN111242689A (en) * | 2020-01-14 | 2020-06-05 | 喜大（上海）网络科技有限公司 | Advertisement putting method, device, server and storage medium |
| CN112150179A (en) * | 2019-06-28 | 2020-12-29 | 京东数字科技控股有限公司 | Information pushing method and device |
| CN112214306A (en) * | 2019-07-11 | 2021-01-12 | 北京字节跳动网络技术有限公司 | Content display weight value calculation method and device, electronic equipment and computer readable storage medium |
| CN112989212A (en) * | 2021-05-19 | 2021-06-18 | 腾讯科技（深圳）有限公司 | Media content recommendation method, device and equipment and computer storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101960444A (en) * | 2008-02-27 | 2011-01-26 | 雅虎公司 | Event communication platform for mobile device users |
| CN102236867A (en) * | 2011-08-15 | 2011-11-09 | 悠易互通（北京）广告有限公司 | Cloud computing-based audience behavioral analysis advertisement targeting system |
| CN102332006A (en) * | 2011-08-03 | 2012-01-25 | 百度在线网络技术（北京）有限公司 | Information push control method and device |
| 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 |
| CN102394798A (en) * | 2011-11-16 | 2012-03-28 | 北京交通大学 | Multi-feature based prediction method of propagation behavior of microblog information and system thereof |
-
2012
- 2012-06-12 CN CN201210192864.9A patent/CN103489117B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101960444A (en) * | 2008-02-27 | 2011-01-26 | 雅虎公司 | Event communication platform for mobile device users |
| CN102332006A (en) * | 2011-08-03 | 2012-01-25 | 百度在线网络技术（北京）有限公司 | Information push control method and device |
| CN102236867A (en) * | 2011-08-15 | 2011-11-09 | 悠易互通（北京）广告有限公司 | Cloud computing-based audience behavioral analysis advertisement targeting system |
| 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 |
| CN102394798A (en) * | 2011-11-16 | 2012-03-28 | 北京交通大学 | Multi-feature based prediction method of propagation behavior of microblog information and system thereof |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096152A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Commodity popularity-based operation execution method and device |
| CN105898420A (en) * | 2015-01-09 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Video recommendation method and device, and electronic equipment |
| CN105898420B (en) * | 2015-01-09 | 2019-04-12 | 阿里巴巴集团控股有限公司 | A kind of video recommendation method, device and electronic equipment |
| CN104537502A (en) * | 2015-01-15 | 2015-04-22 | 北京嘀嘀无限科技发展有限公司 | Method and device for processing orders |
| WO2016131220A1 (en) * | 2015-02-16 | 2016-08-25 | Lee Ying Chiu Herbert | Characterized wireless signal mobile messaging method and system |
| CN107851262A (en) * | 2015-07-09 | 2018-03-27 | 华为技术有限公司 | A kind of advertisement value determines method and device |
| WO2017035970A1 (en) * | 2015-08-31 | 2017-03-09 | 北京百度网讯科技有限公司 | Information pushing method and apparatus |
| WO2017075980A1 (en) * | 2015-11-06 | 2017-05-11 | 北京金山安全软件有限公司 | Information pushing method and apparatus |
| CN106875201A (en) * | 2015-12-11 | 2017-06-20 | 北京国双科技有限公司 | The acquisition methods and device of the visible factor of advertisement |
| CN105677895A (en) * | 2016-02-03 | 2016-06-15 | 北京千米时代科技有限公司 | Device and method for acquiring mobile internet user behavior characteristic attribute |
| CN105843864A (en) * | 2016-03-17 | 2016-08-10 | 合网络技术（北京）有限公司 | Message pushing method and device |
| CN107315548A (en) * | 2016-04-26 | 2017-11-03 | 富士施乐株式会社 | Sending destination change device, print system and sending destination variation |
| CN108255856A (en) * | 2016-12-29 | 2018-07-06 | 阿里巴巴集团控股有限公司 | A kind of information object dissemination method and device |
| CN106886915A (en) * | 2017-01-17 | 2017-06-23 | 华南理工大学 | A kind of ad click predictor method based on time decay sampling |
| CN106886915B (en) * | 2017-01-17 | 2020-07-28 | 华南理工大学 | Advertisement click estimation method based on time attenuation sampling |
| WO2018148894A1 (en) * | 2017-02-16 | 2018-08-23 | 深圳大学 | Time-dependent reputation evaluation algorithm based on scoring network |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN107656918A (en) * | 2017-05-10 | 2018-02-02 | 平安科技（深圳）有限公司 | Obtain the method and device of targeted customer |
| CN109214842B (en) * | 2017-06-30 | 2020-07-28 | 北京金山安全软件有限公司 | Information popularization method, device and equipment |
| CN109214842A (en) * | 2017-06-30 | 2019-01-15 | 北京金山安全软件有限公司 | Information popularization method, device and equipment |
| CN107590691A (en) * | 2017-09-06 | 2018-01-16 | 晶赞广告（上海）有限公司 | A kind of information issuing method and device, storage medium, terminal |
| CN107590691B (en) * | 2017-09-06 | 2021-01-15 | 晶赞广告（上海）有限公司 | Information publishing method and device, storage medium and terminal |
| CN109840782A (en) * | 2017-11-24 | 2019-06-04 | 腾讯科技（深圳）有限公司 | Clicking rate prediction technique, device, server and storage medium |
| CN108256971A (en) * | 2018-01-16 | 2018-07-06 | 平安好房（上海）电子商务有限公司 | User's source of houses portrait update method, device, equipment and storage medium |
| CN108197288B (en) * | 2018-01-16 | 2020-09-01 | 平安好房（上海）电子商务有限公司 | House source pushing method, device, equipment and medium according to user characteristic preference |
| CN108197288A (en) * | 2018-01-16 | 2018-06-22 | 平安好房（上海）电子商务有限公司 | According to source of houses method for pushing, device, equipment and the medium of user characteristics preference |
| CN109189812A (en) * | 2018-08-14 | 2019-01-11 | 中国平安人寿保险股份有限公司 | A kind of index querying method, computer readable storage medium and server |
| CN109801107A (en) * | 2019-01-17 | 2019-05-24 | 有米科技股份有限公司 | A kind of advertisement liveness predictor method, device, server and storage medium |
| CN112150179A (en) * | 2019-06-28 | 2020-12-29 | 京东数字科技控股有限公司 | Information pushing method and device |
| CN112150179B (en) * | 2019-06-28 | 2024-04-09 | 京东科技控股股份有限公司 | Information pushing method and device |
| CN112214306A (en) * | 2019-07-11 | 2021-01-12 | 北京字节跳动网络技术有限公司 | Content display weight value calculation method and device, electronic equipment and computer readable storage medium |
| CN111242689A (en) * | 2020-01-14 | 2020-06-05 | 喜大（上海）网络科技有限公司 | Advertisement putting method, device, server and storage medium |
| CN111242689B (en) * | 2020-01-14 | 2023-11-10 | 喜大（上海）网络科技有限公司 | Advertisement putting method, advertisement putting device, server and storage medium |
| CN112989212A (en) * | 2021-05-19 | 2021-06-18 | 腾讯科技（深圳）有限公司 | Media content recommendation method, device and equipment and computer storage medium |
| CN112989212B (en) * | 2021-05-19 | 2021-08-10 | 腾讯科技（深圳）有限公司 | Media content recommendation method, device and equipment and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103489117B (en) | 2015-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103489117B (en) | Method and system for information releasing | |
| KR102159274B1 (en) | Methods and systems for creating a data-driven attribution model for assigning attribution credit to a plurality of events | |
| CN113169886A (en) | Communication network optimization | |
| CN104065565B (en) | The method of PUSH message, server, client terminal device and system | |
| CN102811371B (en) | The method, system and device that intelligent television application program is recommended | |
| CN104063801A (en) | Mobile advertisement recommendation method based on cluster | |
| CN106412644A (en) | Accurate advertising method and system based on smart TV player | |
| CN102932206B (en) | The method and system of monitoring website access information | |
| CN105045916A (en) | Mobile game recommendation system and recommendation method thereof | |
| CN105898209A (en) | Video platform monitoring and analyzing system | |
| WO2012121935A2 (en) | Sending product information based on determined preference values | |
| CN101520878A (en) | Method, device and system for pushing advertisements to users | |
| CN106294830A (en) | The recommendation method and device of multimedia resource | |
| WO2014105622A2 (en) | Selecting an advertisement for a traffic source | |
| CN101375306A (en) | System and method for providing user-customized event | |
| CN105989074A (en) | Method and device for recommending cold start through mobile equipment information | |
| CN101802856A (en) | Measuring a location based advertising campaign | |
| CN102682005A (en) | Method and device for determining preference categories | |
| CN103686236A (en) | Method and system for recommending video resource | |
| CN103365902A (en) | Method and device for evaluating Internet News | |
| CN107229754B (en) | Information sorting method and device, electronic equipment and storage medium | |
| CN102541893A (en) | Keyword analysis method and keyword analysis device | |
| CN103186595A (en) | Method and system for recommending audios/videos | |
| CN106204121A (en) | Advertisement placement method based on browser and system | |
| CN103700004A (en) | Method and device for pushing microblog advertising service information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |