CN103116589A - Method and device of sending recommendation information - Google Patents
Method and device of sending recommendation information Download PDFInfo
- Publication number
- CN103116589A CN103116589A CN2011103658211A CN201110365821A CN103116589A CN 103116589 A CN103116589 A CN 103116589A CN 2011103658211 A CN2011103658211 A CN 2011103658211A CN 201110365821 A CN201110365821 A CN 201110365821A CN 103116589 A CN103116589 A CN 103116589A
- Authority
- CN
- China
- Prior art keywords
- user
- content
- recommendation information
- similarity
- information
- 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
Images
Abstract
The invention discloses a method and a device of sending recommendation information. The method of sending the recommendation information includes the following steps of establishing a user attribute assembly, wherein the user attribute assembly comprises an assemble based on content and an assemble based on user relationships, ascertaining the recommendation information to be sent according to the user attribute assemble, and sending the recommendation information. The invention further discloses the device of sending the recommendation information. The device comprises a data allocation module, a data sending module and a data control module. The method and the device of sending the recommendation information can help users to screen information about the users from massive content, improve the precision of the recommendation information and reduce recommendation of irrelevant information.
Description
Technical field
The present invention relates to Internet technical field, specifically, relate to a kind of method and device that sends recommendation information.
Background technology
At present, owing to developing rapidly of internet and instant messaging technology, Internet user's quantity also increases thereupon gradually.In order to satisfy users ' individualized requirement, microblogging, blog, such communities such as QQ space provide the individual center page for the user, the user can according to the demands such as interest, hobby, custom of self, deliver the Extraordinaries operations such as daily record, upload pictures, simultaneously, also the multidate information of each good friend in the customer relationship chain can be recommended the user, so that the understanding good friend's that the user can be convenient recent condition.
Usually in existing scheme, the multidate information that produces for each good friend in the customer relationship chain in the page of individual center, can be pushed to the user according to time sequencing, but the user can not guarantee in time to login the individual center page interested multidate information is checked, since dynamic content can be along with the propelling of time roll screen, therefore, the user probably misses the multidate information that oneself is paid close attention to.
Also having a kind of existing scheme is to adopt the scope based on the customer relationship chain to push, and specifically the chain information that concerns of each good friend in the pass tethers of login user is recommended login user, the customer relationship chain of self so that the user can expand.But this information recommendation mode, because the complicacy of customer relationship chain, and be unfavorable for that login user finds like-minded friend, therefore, also be unfavorable for the further expansion of community relations chain.
Summary of the invention
The embodiment of the invention provides a kind of method and device that sends recommendation information, can improve the precision of recommendation information, reduces the propelling movement of uncorrelated content.
One aspect of the present invention provides a kind of method that sends recommendation information, comprising:
Set up user property set, described user property set comprises content-based set and based on the set of customer relationship;
According to the definite recommendation information that will send of described user property set;
Send described recommendation information.
Further, the described user property of setting up is gathered, and comprising:
Set up described content-based set according to user behavior information; Described user behavior information comprise individual subscriber attribute, user deliver in the content of daily record and the log content that the user browsed any one or multiple;
Set up described set based on customer relationship according to customer relationship information; Described customer relationship information comprise the user good friend ID and with the mutual frequency information of good friend.
Further, described according to the definite recommendation information that will send of described user property set, comprising:
Determine the content similarity of each document model in described content-based set and the database;
Determine the user's similarity based on the set of customer relationship of each document author in the set of described customer relationship and the database;
According to described content similarity and user's similarity, from described database, determine described recommendation information;
Wherein, according to described content similarity and user's similarity, from described database, determine described recommendation information, comprising:
Described content similarity and described user's similarity are carried out linear superposition;
According to described linear superposition value the content in the database is sorted, determine described recommendation information according to clooating sequence.
Further, described method also comprises:
From described database, determine described user's subscribed content data according to the tabulation of user's subscribed content;
In described user's subscribed content data and premium content data, determine initial recommendation information, in order to be integrated into definite recommendation information that will send in the described initial recommendation information according to described user property.
Further, the described recommendation information of described transmission comprises:
Adopt the directly mode of the described recommendation information of transmission, perhaps, the mode according to the clooating sequence of described recommendation information sends sends described recommendation information.
The present invention provides a kind of device that sends recommendation information on the other hand, comprising:
The data configuration module is used for setting up the user property set, and described user property set comprises content-based set and based on the set of customer relationship;
The Data Control module is used for the definite recommendation information that will send of user property set of setting up according to described data configuration module;
Data transmission blocks is used for sending the described recommendation information that described Data Control module is determined.
Preferably, described data configuration module specifically is used for:
Set up described content-based set according to user behavior information; Described user behavior information comprise individual subscriber attribute, user deliver in the content of daily record and the log content that the user browsed any one or multiple;
Set up described set based on customer relationship according to customer relationship information; Described customer relationship information comprise the user good friend ID and with the mutual frequency information of good friend.
Preferably, described Data Control module further comprises:
Content similarity determining unit is used for determining described content-based set and the content similarity of each document model of database;
User's similarity determining unit be used for to be determined the user's similarity based on the set of customer relationship of the set of described customer relationship and each document author of database;
The recommendation information determining unit is used for according to described content similarity and user's similarity, determines described recommendation information from described database;
Wherein, described recommendation information determining unit specifically is used for:
Described content similarity and described user's similarity are carried out linear superposition; According to described linear superposition value the content in the database is sorted, determine described recommendation information according to clooating sequence.
Preferably, described device also comprises:
The data screening module is used for according to the subscribed content data of user's subscribed content tabulation from the definite described user of described database; In described user's subscribed content data and premium content data, determine initial recommendation information, so that described Data Control module is integrated into definite recommendation information that will send in the described initial recommendation information according to described user property.
Preferably, described data transmission blocks specifically is used for:
Adopt the directly mode of the described recommendation information of transmission, perhaps, the mode according to the clooating sequence of described recommendation information sends sends described recommendation information.
As seen from the above technical solution provided by the invention, the embodiment of the invention is by setting up user property set, and described user property set comprises content-based set and based on the set of customer relationship; And according to the definite recommendation information that will push of described user property set, and send described recommendation information.The realization of technical solution of the present invention, can in huge volumes of content, filter out information relevant with the user and that like, reduce the propelling movement of uncorrelated content, thus the propelling movement precision of the information of raising, simultaneously also can increase the user to the attention rate of recommendation information, be conducive to the expansion of customer relationship chain.
Description of drawings
In order to be illustrated more clearly in the technical scheme of the embodiment of the invention, the accompanying drawing of required use was done to introduce simply during the below will describe embodiment, apparently, accompanying drawing in the following describes only is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite of not paying creative work, can also obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is a kind of method flow diagram that sends recommendation information of the embodiment of the invention;
Fig. 2 is a kind of apparatus structure synoptic diagram that sends recommendation information of the embodiment of the invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on embodiments of the invention, those of ordinary skills belong to protection scope of the present invention not making the every other embodiment that obtains under the creative work prerequisite.
The embodiment of the invention provides a kind of method and device that sends recommendation information, by setting up content-based set and the set of customer relationship, can in storing the database of mass data, filter out and interested information relevant with the user, not only improved the precision of recommendation information, can also increase the user to the click volume of recommendation information and the interactive frequency between the user, thereby be convenient to further expand the community relations chain.
Below in conjunction with accompanying drawing the embodiment of the invention is described in further detail.
As shown in Figure 1, the embodiment of the invention proposes a kind of method that sends recommendation information, and technical scheme can comprise:
101, set up user property set, described user property set comprises content-based set and based on the set of customer relationship;
102, according to the definite recommendation information that will send of described user property set;
103, send described recommendation information.
As seen, the method for the transmission recommendation information that the invention described above embodiment proposes mainly comprises two processes setting up the user property set and gather definite recommendation information according to user property.The below is elaborated to these two processes.
In an optional embodiment of the present invention, before step 101, described method can also comprise step 100 (not shown in figure 1):
From database, determine described user's subscribed content data according to the tabulation of user's subscribed content;
In described user's subscribed content data and premium content data, determine initial recommendation information, in order to be integrated into definite recommendation information that will send in the initial recommendation information according to user property.
Specifically, from database, determine user's subscribed content data according to the tabulation of user's subscribed content, this process can adopt existing method to realize, for example: at present user's subscribed content is exactly the content that the user of user QQ good friend or microblogging follow relation produces, after the user reaches the standard grade, according to the customer relationship chain, the mode that employing pulls the other side's content is obtained the content-data that described user subscribes to, because this obtain manner can adopt prior art to realize, the present invention does not do at this and gives unnecessary details.
Further, in the embodiment of the invention user's subscribed content data can comprise in the contents such as the good friend issues in the customer relationship chain daily record, article, photo, video any one or multiple.
Specifically, with in the mass data of storing in the database, the data that following feature specifically arranged are as the premium content data in the embodiment of the invention:
(1) title of document contains semantic information, and length for heading is unsuitable too short, and the content of text in the document is longer, and information content is abundant;
(2) possesses certain content of text and contain picture or the page of content of multimedia, and the described page has that any one or a few is greater than predetermined value in pageview, comment amount, reprinting amount, the amount of sharing, and wherein said predetermined value will rule of thumb be worth to set.
In sum, adopting the purpose of step 100 is at microblogging, blog, preliminary screening goes out and user-dependent data in the mass data of the community data library storage that QQ space etc. are such, with these data as preliminary recommendation information, in order to dwindle the screening scope of recommendation information, reduce data processing amount, improve the treatment effeciency of data.
In an optional embodiment of the present invention, the process of step 101 specifically comprises:
Set up described content-based set according to user behavior information; Described user behavior information comprise individual subscriber attribute, user deliver in the content of daily record and the log content that the user browsed any one or multiple;
Set up described set based on customer relationship according to customer relationship information; Described customer relationship information comprise the user good friend ID and with the mutual frequency information of good friend.
Concrete, described content-based set can be specially the properties collection based on keyword; Wherein, the properties collection of setting up based on keyword can adopt existing scheme to realize, such as: for the premium content data that filter out in the database operation such as classify, label, under corresponding to again under the keyword; Perhaps, for containing keyword in the high-quality internal data, in affiliated classification, retrieve, can obtain content-based set.Because this process belongs to existing scheme, the embodiment of the invention is not done at this and is given unnecessary details.
Concrete, the individual subscriber attribute comprises what the user filled in the embodiment of the invention in individual community, as: the information such as interest, hobby, speciality, occupation, do not limit the concrete scope of individual subscriber attribute in the present embodiment, the information that can embody user self hobby all can be used as the individual subscriber attribute.
Concrete, when setting up content-based set, it is also conceivable that online user's (logining the user of the individual center page) to the click situation of recommendation information, gets off the content that the user pays close attention to keyword record, thereby determine the scope of the recommendation information that the user pays close attention to.
In embodiments of the present invention, recommendation information can be the feeds content, and the feeds content refers to content-aggregatedly be pushed to the content that he reads with what the user may need.
Concrete, in the aggregation process of embodiment of the invention foundation based on customer relationship, the mutual frequency information of described user and good friend can comprise that user to user closes the access frequency in good friend space in the tethers, and with the frequency of good friend's chat, in order to can determine good friend's scope that the user pays close attention to.
In an optional embodiment of the present invention, step 102 specifically can comprise:
Determine the content similarity of each document model in described content-based set and the database;
Determine the user's similarity based on the set of customer relationship of each document author in the set of described customer relationship and the database;
According to described content similarity and user's similarity, from described database, determine the recommendation information that will send.
Specifically, document model described in the embodiment of the invention is the vector space module, therefore the method for building up that the method for building up of described document model can reference vector spatial model (VSM:Vector Space Model), specifically the processing of content of text is reduced to vector operation in the vector space, and express semantic similarity with the similarity on the space, have visual and understandable characteristics.
Further, be represented as the vector of document space when document, just can measure similarity between document by the similarity between the compute vector, therefore determine each document model content similarity in content-based set and the database in the embodiment of the invention, can adopt cosine distance similarity metric form the most frequently used in the text-processing to realize;
In addition, determine in the embodiment of the invention that the mode of described content similarity can also adopt other existing schemes to realize, as: Euclidean distance etc.
Specifically, when adopting the cosine range-range mode to calculate described content similarity in the embodiment of the invention, described content similarity can be expressed as:
Rank1=sim(C(people),C(feed))
Wherein, C (people) is the content-based set of user, and C (feed) is the content-based set of document.
Determine described user's similarity, also can adopt the existing modes such as cosine distance to realize, equally take cosine apart from account form as example, described user's similarity can be expressed as:
Rank2=sim(U(people),U(feed_author))
Wherein, U (people) be the user based on the set of customer relationship, U (feed_author) is that the author of feeds content is based on the set of customer relationship.
In an optional embodiment of the present invention, described method can also comprise:
Described content similarity and described user's similarity are carried out linear superposition;
According to described linear superposition value the content in the database is sorted, determine the recommendation information that will send according to clooating sequence.
Specifically, in the embodiment of the invention, described content similarity and user's similarity are carried out linear superposition, obtain the ranking value of feeds content, described linear superposition result can represent in the following way:
Rank=a*Rank1+(1-a)*Rank2,0<a<1;
Wherein, a represents weight coefficient, is used for adjusting user's similarity and the shared weight of content similarity, specifically can adjust according to actual needs, generally can be set to 0.5;
Rank1 denoting contents similarity, Rank2 represents user's similarity.
Concrete, specifically can according to the linear superposition that obtains Rank value as a result, determine to user's recommendation information of logining the individual center page according to order from big to small in the embodiment of the invention.
In an optional embodiment of the present invention, the method that sends described recommendation information comprises:
Adopt the directly mode of the described recommendation information of transmission, perhaps, the mode according to the clooating sequence of described recommendation information sends sends described recommendation information.
Can be found out by the invention described above embodiment, the technical scheme that the embodiment of the invention proposes, by setting up content-based set for the user and based on the set of customer relationship, in the process of determining recommendation information, can take into account simultaneously the behavioural information of customer relationship chain information and communities of users, can improve the propelling movement degree of accuracy of feeds content, break tradition based on customer relationship chain or the way of recommendation that pushes according to the time, reduced the recommendation of uncorrelated content.
As shown in Figure 2, the embodiment of the invention also provides a kind of device that sends recommendation information, and technical scheme comprises:
Data transmission blocks 23 is used for sending the described recommendation information that described Data Control module is determined.
In an optional embodiment of the present invention, described device can also comprise:
Specifically, described data screening module determines that according to the tabulation of user's subscribed content the existing method of can adopting of user's subscribed content realizes from database; User's subscribed content data can comprise in the contents such as the good friend issues in the customer relationship chain daily record, article, photo, video any one or multiple.
In an optional embodiment of the present invention, described data configuration module 21 specifically is used for:
Set up described content-based set according to user behavior information; Described user behavior information comprise individual subscriber attribute, user deliver in the content of daily record and the log content that the user browsed any one or multiple;
Set up described set based on customer relationship according to customer relationship information; Described customer relationship information comprise the user good friend ID and with the mutual frequency information of good friend.
Concrete, described content-based set can be specially the properties collection based on keyword, and foundation can adopt existing scheme to realize based on the detailed process of the properties collection of keyword.
Concrete, the individual subscriber attribute information can comprise what the user filled in the embodiment of the invention in individual community, as: the information such as interest, hobby, speciality, occupation.
Concrete, when setting up content-based set, it is also conceivable that the online user to the click situation of f recommendation information, the getting off with keyword record of the content that the user is paid close attention to, thus determine the scope of the feeds content that the user pays close attention to.
Concrete, the embodiment of the invention is set up based in the customer relationship aggregation process, the mutual frequency information of described user and good friend can comprise that user to user closes the access frequency in good friend space in the tethers, and with the frequency of good friend's chat, in order to can determine the friend information that the user pays close attention to.
In an optional embodiment of the present invention, described Data Control module 22 further comprises:
Content similarity determining unit 221 is used for determining described content-based set and the content similarity of each document model of database;
User's similarity determining unit 222 be used for to be determined the user's similarity based on the set of customer relationship of the set of described customer relationship and each document author of database;
Recommendation information determining unit 223 is used for according to described content similarity and user's similarity, determines the recommendation information that will send from described database;
Wherein, described recommendation information determining unit 223 specifically is used for:
Described content similarity and described user's similarity are carried out linear superposition; According to described linear superposition value the content in the database is sorted, determine recommendation information according to clooating sequence.
Concrete, determine described content similarity and described user's similarity in the embodiment of the invention, can adopt the existing mode such as cosine distance to realize;
Specifically, in the embodiment of the invention, the described content similarity and the user's similarity that adopt the cosine distance algorithm to calculate can be carried out linear superposition, obtain the ranking value of content among the feeds.
In addition, data transmission blocks in the embodiment of the invention can adopt the mode of the described recommendation information of direct transmission, and perhaps, the mode according to the clooating sequence of described recommendation information sends sends described recommendation information.
Need to prove, the embodiment of the invention is based on the device embodiment that embodiment of the method shown in Figure 1 obtains, comprised the technical characterictic identical with Fig. 1 embodiment, wherein, in the embodiment of the invention among each functional module and Fig. 1 embodiment each step have corresponding relation, therefore, the concrete technical scheme that relates in the embodiment of the invention can be referring to the associated description among above-mentioned Fig. 1 embodiment, does not do at this and gives unnecessary details.
In sum, a kind of method and device that sends recommendation information of the embodiment of the invention, by setting up content-based set for the user and based on the set of customer relationship, in determining to recommend the process of user profile, can take into account simultaneously the behavioural information of customer relationship chain information and communities of users, can in the feeds of magnanimity information, determine the recommendation information relevant with user interest, improved the propelling movement degree of accuracy of feeds information, solved in the prior art and can not satisfy the demand of logining individual center page user according to the customer relationship chain or according to the information recommendation mode that the time pushes.
The above; only for the better embodiment of the present invention, but protection scope of the present invention is not limited to this, anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; the variation that can expect easily or replacement all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (11)
1. a method that sends recommendation information is characterized in that, comprising:
Set up user property set, described user property set comprises content-based set and based on the set of customer relationship;
According to the definite recommendation information that will send of described user property set;
Send described recommendation information.
2. described method according to claim 1 is characterized in that, describedly sets up the user property set, comprising:
Set up described content-based set according to user behavior information; Described user behavior information comprise individual subscriber attribute, user deliver in the content of daily record and the log content that the user browsed any one or multiple;
Set up described set based on customer relationship according to customer relationship information; Described customer relationship information comprise the user good friend lD and with the mutual frequency information of good friend.
3. method according to claim 2 is characterized in that, and is described according to the definite recommendation information that will send of described user property set, comprising:
Determine the content similarity of each document model in described content-based set and the database;
Determine the user's similarity based on the set of customer relationship of each document author in described set based on customer relationship and the database;
According to described content similarity and user's similarity, from described database, determine described recommendation information;
Wherein, according to described content similarity and user's similarity, from described database, determine described recommendation information, comprising:
Described content similarity and described user's similarity are carried out linear superposition;
According to described linear superposition value the content in the database is sorted, determine described recommendation information according to clooating sequence.
4. method according to claim 1 is characterized in that, described method also comprises:
From described database, determine described user's subscribed content data according to the tabulation of user's subscribed content;
In described user's subscribed content data and premium content data, determine initial recommendation information, in order to be integrated into definite recommendation information that will send in the described initial recommendation information according to described user property.
5. arbitrary described method in 4 according to claim 1 is characterized in that the described recommendation information of described transmission comprises:
Adopt the directly mode of the described recommendation information of transmission, perhaps, the mode according to the clooating sequence of described recommendation information sends sends described recommendation information.
6. a device that sends recommendation information is characterized in that, comprising:
The data configuration module is used for setting up the user property set, and described user property set comprises content-based set and based on the set of customer relationship;
The Data Control module is used for the definite recommendation information that will send of user property set of setting up according to described data configuration module;
Data transmission blocks is used for sending the described recommendation information that described Data Control module is determined.
7. device according to claim 6 is characterized in that, described data configuration module specifically is used for:
Set up described content-based set according to user behavior information; Described user behavior information comprise individual subscriber attribute, user deliver in the content of daily record and the log content that the user browsed any one or multiple;
Set up described set based on customer relationship according to customer relationship information; Described customer relationship information comprise the user good friend ID and with the mutual frequency information of good friend.
8. device according to claim 7 is characterized in that, described Data Control module further comprises:
Content similarity determining unit is used for determining described content-based set and the content similarity of each document model of database;
User's similarity determining unit be used for to be determined the user's similarity based on the set of customer relationship of the set of described customer relationship and each document author of database;
The recommendation information determining unit is used for according to described content similarity and user's similarity, determines described recommendation information from described database.
9. device according to claim 8 is characterized in that, described recommendation information determining unit specifically is used for:
Described content similarity and described user's similarity are carried out linear superposition; According to described linear superposition value the content in the database is sorted, determine described recommendation information according to clooating sequence.
10. device according to claim 6 is characterized in that, described device also comprises:
The data screening module is used for according to the subscribed content data of user's subscribed content tabulation from the definite described user of described database; In described user's subscribed content data and premium content data, determine initial recommendation information, so that described Data Control module is integrated into definite recommendation information that will send in the described initial recommendation information according to described user property.
11. arbitrary described device in 10 according to claim 6 is characterized in that described data transmission blocks specifically is used for:
Adopt the directly mode of the described recommendation information of transmission, perhaps, the mode according to the clooating sequence of described recommendation information sends sends described recommendation information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011103658211A CN103116589A (en) | 2011-11-17 | 2011-11-17 | Method and device of sending recommendation information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011103658211A CN103116589A (en) | 2011-11-17 | 2011-11-17 | Method and device of sending recommendation information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103116589A true CN103116589A (en) | 2013-05-22 |
Family
ID=48414966
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011103658211A Pending CN103116589A (en) | 2011-11-17 | 2011-11-17 | Method and device of sending recommendation information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103116589A (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104216903A (en) * | 2013-05-30 | 2014-12-17 | 北京千橡网景科技发展有限公司 | Method and device for evaluating attention between users |
CN104516915A (en) * | 2013-09-30 | 2015-04-15 | 腾讯科技(北京)有限公司 | Media data publishing method and device based on tweet timeline |
CN104636371A (en) * | 2013-11-11 | 2015-05-20 | 华为技术有限公司 | Information recommendation method and device |
WO2015078251A1 (en) * | 2013-11-27 | 2015-06-04 | Tencent Technology (Shenzhen) Company Limited | Methods and systems for aggregating user generated content |
CN104869439A (en) * | 2015-05-14 | 2015-08-26 | 无锡天脉聚源传媒科技有限公司 | Video push method and device |
WO2015135475A1 (en) * | 2014-03-12 | 2015-09-17 | Tencent Technology (Shenzhen) Company Limited | Multimedia file push method and apparatus |
CN105447170A (en) * | 2015-12-07 | 2016-03-30 | 联想(北京)有限公司 | Information processing method and electronic device |
CN105718525A (en) * | 2016-01-15 | 2016-06-29 | 北京橙鑫数据科技有限公司 | Exhibition recommendation method and exhibition recommendation device |
CN105718545A (en) * | 2016-01-18 | 2016-06-29 | 合一网络技术(北京)有限公司 | Recommendation method and device of multimedia resources |
CN105787055A (en) * | 2016-02-26 | 2016-07-20 | 合网络技术(北京)有限公司 | Information recommendation method and device |
CN105933308A (en) * | 2016-04-20 | 2016-09-07 | 北京章鱼智数科技有限公司 | Mobile intelligent device stream large data real-time processing method |
CN106097110A (en) * | 2016-06-15 | 2016-11-09 | 西安邮电大学 | A kind of dictionary construction method based on community network and word matched recommend method |
CN106294846A (en) * | 2016-08-19 | 2017-01-04 | 维沃移动通信有限公司 | A kind of recommendation method of information and mobile terminal |
WO2017028791A1 (en) * | 2015-08-18 | 2017-02-23 | 中兴通讯股份有限公司 | Public number recommendation method and system |
CN107147724A (en) * | 2017-05-23 | 2017-09-08 | 深圳市金立通信设备有限公司 | A kind of information push method, server and computer-readable recording medium |
CN107196999A (en) * | 2017-05-03 | 2017-09-22 | 网易传媒科技(北京)有限公司 | Method and apparatus for issuing information flow propelling data |
CN107395743A (en) * | 2017-08-16 | 2017-11-24 | 维沃移动通信有限公司 | A kind of information processing method and mobile terminal |
WO2018023658A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for pushing advertisement according to followed public account, and push system |
WO2018023656A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for adjusting advertisement push according to usage conditions of other users, and push system |
WO2018023657A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for adjusting wechat public account-based advertisement push technique, and push system |
CN107959617A (en) * | 2017-11-27 | 2018-04-24 | 广西塔锡科技有限公司 | A kind of domestic customers terminal interaction method and service system |
CN109446432A (en) * | 2018-12-17 | 2019-03-08 | 微梦创科网络科技(中国)有限公司 | A kind of information recommendation method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101105795A (en) * | 2006-10-27 | 2008-01-16 | 北京搜神网络技术有限责任公司 | Network behavior based personalized recommendation method and system |
CN101321190A (en) * | 2008-07-04 | 2008-12-10 | 清华大学 | Recommend method and recommend system of heterogeneous network |
CN101446959A (en) * | 2008-12-30 | 2009-06-03 | 深圳市迅雷网络技术有限公司 | Internet-based news recommendation method and system thereof |
CN101763351A (en) * | 2008-12-23 | 2010-06-30 | 未序网络科技(上海)有限公司 | Data fusion based video program recommendation method |
CN102141986A (en) * | 2010-01-28 | 2011-08-03 | 北京邮电大学 | Individualized information providing method and system based on user behaviors |
-
2011
- 2011-11-17 CN CN2011103658211A patent/CN103116589A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101105795A (en) * | 2006-10-27 | 2008-01-16 | 北京搜神网络技术有限责任公司 | Network behavior based personalized recommendation method and system |
CN101321190A (en) * | 2008-07-04 | 2008-12-10 | 清华大学 | Recommend method and recommend system of heterogeneous network |
CN101763351A (en) * | 2008-12-23 | 2010-06-30 | 未序网络科技(上海)有限公司 | Data fusion based video program recommendation method |
CN101446959A (en) * | 2008-12-30 | 2009-06-03 | 深圳市迅雷网络技术有限公司 | Internet-based news recommendation method and system thereof |
CN102141986A (en) * | 2010-01-28 | 2011-08-03 | 北京邮电大学 | Individualized information providing method and system based on user behaviors |
Non-Patent Citations (1)
Title |
---|
程光曦: "SNS中用户生成内容和行为数据的分析与应用", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104216903A (en) * | 2013-05-30 | 2014-12-17 | 北京千橡网景科技发展有限公司 | Method and device for evaluating attention between users |
CN104516915B (en) * | 2013-09-30 | 2018-03-23 | 腾讯科技(北京)有限公司 | A kind of media data dissemination method and device based on microblogging timeline |
CN104516915A (en) * | 2013-09-30 | 2015-04-15 | 腾讯科技(北京)有限公司 | Media data publishing method and device based on tweet timeline |
CN104636371A (en) * | 2013-11-11 | 2015-05-20 | 华为技术有限公司 | Information recommendation method and device |
CN104636371B (en) * | 2013-11-11 | 2018-05-18 | 华为技术有限公司 | Information recommendation method and equipment |
WO2015078251A1 (en) * | 2013-11-27 | 2015-06-04 | Tencent Technology (Shenzhen) Company Limited | Methods and systems for aggregating user generated content |
US10122673B2 (en) | 2013-11-27 | 2018-11-06 | Tencent Technology (Shenzhen) Company Limited | Methods and systems for aggregating user generated content |
WO2015135475A1 (en) * | 2014-03-12 | 2015-09-17 | Tencent Technology (Shenzhen) Company Limited | Multimedia file push method and apparatus |
US9571597B2 (en) | 2014-03-12 | 2017-02-14 | Tencent Technology (Shenzhen) Company Limited | Multimedia file push method and apparatus |
CN104869439A (en) * | 2015-05-14 | 2015-08-26 | 无锡天脉聚源传媒科技有限公司 | Video push method and device |
CN104869439B (en) * | 2015-05-14 | 2018-03-09 | 无锡天脉聚源传媒科技有限公司 | A kind of video pushing method and device |
WO2017028791A1 (en) * | 2015-08-18 | 2017-02-23 | 中兴通讯股份有限公司 | Public number recommendation method and system |
CN105447170A (en) * | 2015-12-07 | 2016-03-30 | 联想(北京)有限公司 | Information processing method and electronic device |
CN105447170B (en) * | 2015-12-07 | 2019-10-29 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
CN105718525A (en) * | 2016-01-15 | 2016-06-29 | 北京橙鑫数据科技有限公司 | Exhibition recommendation method and exhibition recommendation device |
CN105718545A (en) * | 2016-01-18 | 2016-06-29 | 合一网络技术(北京)有限公司 | Recommendation method and device of multimedia resources |
CN105787055A (en) * | 2016-02-26 | 2016-07-20 | 合网络技术(北京)有限公司 | Information recommendation method and device |
CN105933308A (en) * | 2016-04-20 | 2016-09-07 | 北京章鱼智数科技有限公司 | Mobile intelligent device stream large data real-time processing method |
CN106097110A (en) * | 2016-06-15 | 2016-11-09 | 西安邮电大学 | A kind of dictionary construction method based on community network and word matched recommend method |
CN106097110B (en) * | 2016-06-15 | 2020-02-11 | 西安邮电大学 | Word bank construction method and word matching recommendation method based on social network |
WO2018023658A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for pushing advertisement according to followed public account, and push system |
WO2018023657A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for adjusting wechat public account-based advertisement push technique, and push system |
WO2018023656A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for adjusting advertisement push according to usage conditions of other users, and push system |
CN106294846A (en) * | 2016-08-19 | 2017-01-04 | 维沃移动通信有限公司 | A kind of recommendation method of information and mobile terminal |
CN107196999A (en) * | 2017-05-03 | 2017-09-22 | 网易传媒科技(北京)有限公司 | Method and apparatus for issuing information flow propelling data |
CN107196999B (en) * | 2017-05-03 | 2020-01-24 | 网易传媒科技(北京)有限公司 | Method and equipment for transmitting information flow push data |
CN107147724A (en) * | 2017-05-23 | 2017-09-08 | 深圳市金立通信设备有限公司 | A kind of information push method, server and computer-readable recording medium |
CN107395743B (en) * | 2017-08-16 | 2019-07-26 | 维沃移动通信有限公司 | A kind of information processing method and mobile terminal |
CN107395743A (en) * | 2017-08-16 | 2017-11-24 | 维沃移动通信有限公司 | A kind of information processing method and mobile terminal |
CN107959617A (en) * | 2017-11-27 | 2018-04-24 | 广西塔锡科技有限公司 | A kind of domestic customers terminal interaction method and service system |
CN107959617B (en) * | 2017-11-27 | 2021-04-30 | 广西塔锡科技有限公司 | Home client terminal interaction method and service system |
CN109446432A (en) * | 2018-12-17 | 2019-03-08 | 微梦创科网络科技(中国)有限公司 | A kind of information recommendation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103116589A (en) | Method and device of sending recommendation information | |
US10805252B2 (en) | Prioritizing messages within a message network | |
US11727048B2 (en) | Methods, systems, and media for presenting recommended content based on social cues | |
CN104969224B (en) | Improved user experience for unacknowledged and new users | |
US9979994B2 (en) | Contextual based information aggregation system | |
US9361373B1 (en) | Content aggregation and presentation | |
US10810499B2 (en) | Method and apparatus for recommending social media information | |
US11805165B2 (en) | Computerized system and method for an interactive online learning experience | |
US8589434B2 (en) | Recommendations based on topic clusters | |
US8996629B1 (en) | Generating a stream of content for a channel | |
US9721019B2 (en) | Systems and methods for providing personalized recommendations for electronic content | |
CN103106208B (en) | A kind of streaming medium content in mobile Internet recommends method and system | |
WO2014134940A1 (en) | Method and server of group recommendation | |
US10387915B2 (en) | Digital magazine recommendations by topic | |
KR20180053673A (en) | Clustering of viewing time for video search | |
KR20220145424A (en) | Predicting topics of potential relevance based on retrieved/created digital media files | |
US20140229487A1 (en) | System and method for user preference augmentation through social network inner-circle knowledge discovery | |
US10990620B2 (en) | Aiding composition of themed articles about popular and novel topics and offering users a navigable experience of associated content | |
WO2008073594A1 (en) | A content recommendation system and a method of operation therefor | |
KR102164409B1 (en) | Crowdsourcing user-provided identifiers and associating them with brand identities | |
US20180114279A1 (en) | Automatic Newsletter Creation | |
JP5846033B2 (en) | Information processing device, terminal device, information processing method, display method, information processing program, and display program | |
US20180165368A1 (en) | Demographic Based Collaborative Filtering for New Users | |
US11086905B1 (en) | Method and system for presenting stories |
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 |
Application publication date: 20130522 |
|
RJ01 | Rejection of invention patent application after publication |