CN103428169A - Method and system for recommending users in SNS community - Google Patents
Method and system for recommending users in SNS community Download PDFInfo
- Publication number
- CN103428169A CN103428169A CN2012101538741A CN201210153874A CN103428169A CN 103428169 A CN103428169 A CN 103428169A CN 2012101538741 A CN2012101538741 A CN 2012101538741A CN 201210153874 A CN201210153874 A CN 201210153874A CN 103428169 A CN103428169 A CN 103428169A
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- information
- good friend
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000008878 coupling Effects 0.000 claims description 34
- 238000010168 coupling process Methods 0.000 claims description 34
- 238000005859 coupling reaction Methods 0.000 claims description 34
- 238000012216 screening Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000001143 conditioned effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to a method and system for recommending users in an SNS community. The method comprises the steps that a client-side acquires update information of users and uploads the update information to a server in real time; the server calculates in an on-line mode to obtain the information of to-be-recommended users according to the update information; the client-side obtains the information of the to-be-recommended users from the server and displays the information of the to-be-recommended users to users. According to the method and system for recommending users in the SNS community, after the update information of users is obtained, the information of the to-be-recommended users is instantly obtained through calculation and is displayed to the users, so that only users relevant to the update information need calculating, and not all users need calculating for one time in an off-line mode. Consequently, time is saved, and the calculation burden of the server is reduced.
Description
Technical field
The present invention relates to network technology, particularly relate to the method and system of recommending the user in a kind of SNS community.
Background technology
SNS(Social Networking Services, social network services) be the internet, applications service that a kind of people of help set up social network.The SNS community is based on the theoretical and Web Community's system of building of SNS.In the SNS community, the user is by getting to know a lot of other strange users, and using it as friend.The SNS community by variety of way to user's recommending friends.
In the SNS community, according to the user concern chain information, data, interactive information in community etc., to the user recommend potential can knowable people, help the user development good friend to close tethers.Traditional recommendation can knowable people obtains after user profile by server the mode that adopts calculated off-line, because information is numerous, amount of calculation is huge, the time cycle that once needs cost longer is calculated in every renewal, and need by this time cycle, calculate once each user, so, spend a large amount of time, and increased the computational burden of computer, inconvenient user understands potential information that can knowable people after upgrading in time, has reduced user's experience.
Summary of the invention
Based on this, be necessary to provide a kind of and can save time and can alleviate the method for in the SNS community of computational burden of server, recommending the user.
Recommend user's method in a kind of SNS community, comprise the following steps:
Client is obtained user's lastest imformation, and described lastest imformation real-time report is arrived to server;
Described server calculates user's to be recommended information online according to described lastest imformation;
Described client pulls described user's to be recommended information from described server, and gives described user by described user's to be recommended information display.
In embodiment, described lastest imformation comprises that user's personal attribute information and/or user's good friend concern chain information therein.
Therein in embodiment, calculate online the user's to be recommended step of information according to described lastest imformation at described server after, also comprise step:
Described server obtains user to be recommended and user's the degree of correlation, and user's to be recommended priority is set according to the described degree of correlation.
In embodiment, described client pulls described user's to be recommended information from described server therein, and comprises described user's to be recommended information display to described user's step:
Described client pulls described user's to be recommended information from high to low according to user's to be recommended priority from described server, and according to priority give described user by the user's to be recommended of correspondence information display from high to low.
In embodiment, the step that described server calculates user's to be recommended information online according to described lastest imformation comprises therein:
Described server sets in advance user's the coupling weights of personal attribute information and the coupling weights that the good friend concerns chain information;
Described server concerns that by each user's of non-good friend user personal attribute information and good friend chain information and user's personal attribute information and good friend concern that chain information compares respectively, determines each user's of non-good friend user weights according to comparison result and corresponding coupling weights;
Weights in non-good friend user are greater than to the user of threshold value to described server or the large user of weights of default number is defined as user to be recommended.
In addition, also being necessary to provide a kind of can save time and can alleviate the system of in the SNS community of computational burden of server, recommending the user.
Recommend user's system in a kind of SNS community, comprise client and server,
Described client comprises: capture module, for obtaining user's lastest imformation;
Reporting module, for arriving server by described lastest imformation real-time report;
Described server comprises:
Processing module, for calculating online user's to be recommended information according to described lastest imformation;
Described client also comprises:
Pull module, for pull described user's to be recommended information from described server;
Display module, give described user for the information display by described user to be recommended.
In embodiment, described lastest imformation comprises that user's personal attribute information and/or user's good friend concern chain information therein.
In embodiment, described server also comprises therein:
Degree of correlation acquisition module, for obtaining user to be recommended and user's the degree of correlation;
Module is set, for each user's priority is set according to described lastest imformation.
In embodiment, the described module that pulls is also for pulling from high to low described user's to be recommended information according to user's to be recommended priority from server therein; Described display module is also for giving described user by the user's to be recommended of correspondence information display from high to low according to priority.
In embodiment, described processing module comprises therein:
Initialization unit, for the coupling weights of the personal attribute information that sets in advance the user and the coupling weights that the good friend concerns chain information;
Comparing unit, concern that for the personal attribute information that each user's of non-good friend user personal attribute information and good friend concerned to chain information and user and good friend chain information compares respectively, according to comparison result and mate accordingly the weights that weights are determined each user of non-good friend user;
The screening unit, be defined as user to be recommended for the user that non-good friend user's weights is greater than to threshold value or the large user of weights of default number.
Recommend user's method and system in above-mentioned SNS community, after getting user's lastest imformation, calculate immediately user's to be recommended information, and it is showed to the user, because only needing to calculate the user relevant to this lastest imformation, do not need each is used per family and calculates once by offline mode, saved the time, and alleviated the computational burden of server.
The accompanying drawing explanation
Fig. 1 recommends the flow chart of user's method in the SNS community in an embodiment;
Fig. 2 calculates the particular flow sheet of user's to be recommended information online according to this lastest imformation in an embodiment;
Fig. 3 recommends the internal structure schematic diagram of user's system in the SNS community in an embodiment;
Fig. 4 is the internal structure schematic diagram of processing module in Fig. 3 in an embodiment;
Fig. 5 recommends the internal structure schematic diagram of user's system in the SNS community in another embodiment.
Embodiment
Below in conjunction with specific embodiment and accompanying drawing to recommending the technical scheme of user's method and system to be described in detail in the SNS community, so that it is clearer.
As shown in Figure 1, in one embodiment, recommend user's method in a kind of SNS community, comprise the following steps:
Step S110, client is obtained user's lastest imformation, and this lastest imformation real-time report is arrived to server.
Concrete, in the SNS community, user's lastest imformation can comprise that user's personal attribute information and/or user's good friend concern chain information.Wherein, user's personal attribute information can comprise sex, age, constellation, blood group, previous graduate college, specialty, graduation time, native place, location, the industry of being engaged in, the hobby etc. learned.User's good friend concerns that chain information comprises newly-increased good friend's relation and/or good friend's relation of releasing, and as the user A B that Adds User is the good friend, user A removes with good friend's relation of user C etc.
Once client gets user's lastest imformation, immediately it is reported to server, is processed by server.
Step S120, server calculates user's to be recommended information online according to this lastest imformation.
Concrete, after server gets user's lastest imformation, calculate online immediately the user's to be recommended who recommends to this user information.User's to be recommended information refers to the user's that may become the good friend who determines in non-good friend user information.For example, user A Adds User B for after the good friend, because of user B and user C good friend each other, user C may become the good friend by user A,, using user C as the user to be recommended who recommends user A, the information of user C can comprise a human head picture, name, sex, acquaintanceship degree etc., but is not limited to this.
After line computation refers to that server receives the user's that client reports lastest imformation, calculate immediately this user's user's to be recommended information according to lastest imformation.Now, server is not processed the user who there is no lastest imformation, has so alleviated the burden of server.And calculated off-line refers to that server regularly all calculates its user profile to be recommended to all users, the data volume of processing is huge, expends time in longer.
In one embodiment, recommend user's method in above-mentioned SNS community, after step S120, also comprise step: server obtains user to be recommended and user's the degree of correlation, and user's to be recommended priority is set according to the degree of correlation.Server can be set the coupling weights to user's personal attribute information, user's to be recommended personal attribute information and user's personal attribute information are mated, calculate user's to be recommended coupling weights, the degree of correlation using it as this user to be recommended and user, then set user's to be recommended priority according to the degree of correlation, the degree of correlation is higher, and corresponding user's to be recommended priority is higher.User's to be recommended priority refers to that priority level or client that server is pushed to the user by user to be recommended pull the priority level of user to be recommended to the user, i.e. sequencing.
In the present embodiment, as shown in Figure 2, server calculates user's to be recommended information online step according to this lastest imformation can comprise:
Step S210, server sets in advance user's the coupling weights of personal attribute information and the coupling weights that the good friend concerns chain information.
Concrete, as the native place coupling weights that the user is set are 10, user's location coupling weights are 5, the good friend concerns that the coupling weights of chain information are 15 etc.Wherein, the good friend concerns that the coupling of chain information refers between the user and has total good friend, and its coupling weights can arrange different value according to total good friend's quantity, and quantity is more, and the coupling weights are larger.
In addition, also comprise step after step S210: server obtains non-good friend user from Relation Element, and the non-good friend user who obtains is carried out to the duplicate removal processing.
Concrete, Relation Element can comprise cell phone address book, instant messaging account number address list etc., for example from cell phone address book according to pre-conditioned choose 50 user A can knowable people, and choose front 50 user A according to common good friend's number from instant messaging account number address list can knowable people, the remaining non-good friend user as user A after these 100 can knowable people's duplicate removal be processed.So can reduce back compares and determine to recommend user's amount of calculation.
Step S220, server concerns that by each user's of non-good friend user personal attribute information and good friend chain information and user's personal attribute information and good friend concern that chain information compares respectively, determines each user's of non-good friend user weights according to comparison result and corresponding coupling weights.
Concrete, as the personal attribute information by user C and user A, to compare, the native place coupling weights that obtain user C are 10, to mate weights be 5 in location, and the good friend is concerned to chain information compares, and obtaining mating weights is 15, and the weights of user C are 30.
Step S230, weights in non-good friend user are greater than to the user of threshold value to server or the large user of weights of default number is defined as user to be recommended.
Concrete, as threshold value can be set to 20, weights are greater than 20 user as user to be recommended.Perhaps, the weights of each user in non-good friend user are sorted from big to small, the user of weights sequence front 10 is as recommending the user.
Step S130, client pulls user's to be recommended information from server, and gives this user by user's to be recommended information display.
Concrete, client pulls the user's to be recommended who obtains according to lastest imformation information from server, by user's to be recommended information display to the user, as information such as user's to be recommended head portrait, name, location, acquaintanceship degree.
In one embodiment, after according to the degree of correlation, user's to be recommended priority being set, step S130 specifically comprises step: client pulls user's to be recommended information from high to low according to user's to be recommended priority from server, and according to priority gives described user by the user's to be recommended of correspondence information display from high to low.For example, user B to be recommended and the C of user A, calculate the degree of correlation of the degree of correlation of user B to be recommended higher than user C to be recommended, and the priority of user B to be recommended, higher than the priority of user C to be recommended, while pulling, first pulls the information of user B to be recommended.Then height according to priority, preferential by the information display of user B to be recommended to user A, then by the information display of user C to be recommended to user A, information display that also can user B to be recommended is in the front of user C to be recommended.
In one embodiment, recommend user's method in above-mentioned SNS community, also comprise step: storage user's lastest imformation and user's to be recommended information.
As shown in Figure 3, in one embodiment, recommend user's system in a kind of SNS community, comprise client 10 and server 20.Client 10 comprises capture module 110, reporting module 120, pulls module 130 and display module 140.Server 20 comprises processing module 210.Wherein:
In one embodiment, as shown in Figure 4, processing module 210 comprises initialization unit 212, comparing unit 214 and screening unit 216.Wherein:
Concrete, as the native place coupling weights that the user is set are 10, user's location coupling weights are 5, the good friend concerns that the coupling weights of chain information are 15 etc.Wherein, the good friend concerns that the coupling of chain information refers between the user and has total good friend, and its coupling weights can arrange different value according to total good friend's quantity, and quantity is more, and the coupling weights are larger.
The personal attribute information that comparing unit 214 concerns chain information and user for personal attribute information and the good friend of each user by non-good friend user and good friend concern that chain information compares respectively, determine each user's of non-good friend user weights according to comparison result and corresponding coupling weights.
Concrete, as the personal attribute information by user C and user A, to compare, the native place coupling weights that obtain user C are 10, to mate weights be 5 in location, and the good friend is concerned to chain information compares, and obtaining mating weights is 15, and the weights of user C are 30.
Concrete, as threshold value can be set to 20, weights are greater than 20 user as user to be recommended.Perhaps, the weights of each user in non-good friend user are sorted from big to small, the user of weights sequence front 10 is as recommending the user.
In addition, processing module 210 also comprises collecting unit, for obtain non-good friend user from Relation Element, and the non-good friend user who obtains is carried out to the duplicate removal processing.
Concrete, Relation Element can comprise cell phone address book, instant messaging account number address list etc., for example from cell phone address book according to pre-conditioned choose 50 user A can knowable people, and choose front 50 user A according to common good friend's number from instant messaging account number address list can knowable people, the remaining non-good friend user as user A after these 100 can knowable people's duplicate removal be processed.So can reduce back compares and determine to recommend user's amount of calculation.
As shown in Figure 5, in one embodiment, recommend user's system in above-mentioned SNS community, server 20, except comprising processing module 210, also comprises degree of correlation acquisition module 220, module 230 and memory module 240 is set.Wherein:
Degree of correlation acquisition module 220 is for obtaining user to be recommended and user's the degree of correlation.Degree of correlation acquisition module 220 can be set the coupling weights to user's personal attribute information, user's to be recommended personal attribute information and user's personal attribute information are mated, calculate user's to be recommended coupling weights, the degree of correlation using it as this user to be recommended and user.
Recommend user's method and system in above-mentioned SNS community, after getting user's lastest imformation, calculate immediately user's to be recommended information, and it is showed to the user, because only needing to calculate the user relevant to this lastest imformation, do not need each with calculating once by offline mode per family, saved the time, and alleviated the computational burden of server, facilitated the user to obtain in time the associated chain of renewal simultaneously, according to this pass tethers, obtained the chances of setting up good friend's relation more.
In addition, pull from high to low user's to be recommended information according to user's to be recommended priority, convenient user to be recommended that will be high with user's degree of correlation recommends the user, facilitates user's expansion relation chain.
The above embodiment has only expressed several execution mode 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 range of patent of the present invention should be as the criterion with claims.
Claims (10)
1. recommend user's method in a SNS community, comprise the following steps:
Client is obtained user's lastest imformation, and described lastest imformation real-time report is arrived to server;
Described server calculates user's to be recommended information online according to described lastest imformation;
Described client pulls described user's to be recommended information from described server, and gives described user by described user's to be recommended information display.
2. recommend user's method in SNS according to claim 1 community, it is characterized in that, described lastest imformation comprises that user's personal attribute information and/or user's good friend concern chain information.
3. recommend user's method in SNS according to claim 1 community, it is characterized in that, calculate online the user's to be recommended step of information according to described lastest imformation at described server after, also comprise step:
Described server obtains user to be recommended and user's the degree of correlation, and user's to be recommended priority is set according to the described degree of correlation.
4. recommend user's method in SNS according to claim 3 community, it is characterized in that, described client pulls described user's to be recommended information from described server, and is specially described user's to be recommended information display to described user's step:
Described client pulls described user's to be recommended information from high to low according to user's to be recommended priority from described server, and according to priority give described user by the user's to be recommended of correspondence information display from high to low.
5. recommend user's method in SNS according to claim 1 community, it is characterized in that, the step that described server calculates user's to be recommended information online according to described lastest imformation comprises:
Described server sets in advance user's the coupling weights of personal attribute information and the coupling weights that the good friend concerns chain information;
Described server concerns that by each user's of non-good friend user personal attribute information and good friend chain information and user's personal attribute information and good friend concern that chain information compares respectively, determines each user's of non-good friend user weights according to comparison result and corresponding coupling weights;
Weights in non-good friend user are greater than to the user of threshold value to described server or the large user of weights of default number is defined as user to be recommended.
6. recommend user's system in a SNS community, it is characterized in that, comprise client and server, described client comprises:
Capture module, for obtaining user's lastest imformation;
Reporting module, for arriving server by described lastest imformation real-time report;
Described server comprises:
Processing module, for calculating online user's to be recommended information according to described lastest imformation;
Described client also comprises:
Pull module, for pull described user's to be recommended information from described server;
Display module, give described user for the information display by described user to be recommended.
7. recommend user's system in SNS according to claim 6 community, it is characterized in that, described lastest imformation comprises that user's personal attribute information and/or user's good friend concern chain information.
8. recommend user's system in SNS according to claim 6 community, it is characterized in that, described server also comprises:
Degree of correlation acquisition module, for obtaining user to be recommended and user's the degree of correlation;
Module is set, for described user's to be recommended priority is set according to the described degree of correlation.
9. recommend user's system in SNS according to claim 8 community, it is characterized in that, the described module that pulls is also for pulling from high to low described user's to be recommended information according to user's to be recommended priority from server; Described display module is also for giving described user by the user's to be recommended of correspondence information display from high to low according to priority.
10. recommend user's system in SNS according to claim 6 community, it is characterized in that, described processing module comprises:
Initialization unit, for the coupling weights of the personal attribute information that sets in advance the user and the coupling weights that the good friend concerns chain information;
Comparing unit, concern that for the personal attribute information that each user's of non-good friend user personal attribute information and good friend concerned to chain information and user and good friend chain information compares respectively, according to comparison result and mate accordingly the weights that weights are determined each user of non-good friend user;
The screening unit, be defined as user to be recommended for the user that non-good friend user's weights is greater than to threshold value or the large user of weights of default number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101538741A CN103428169A (en) | 2012-05-17 | 2012-05-17 | Method and system for recommending users in SNS community |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101538741A CN103428169A (en) | 2012-05-17 | 2012-05-17 | Method and system for recommending users in SNS community |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103428169A true CN103428169A (en) | 2013-12-04 |
Family
ID=49652350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101538741A Pending CN103428169A (en) | 2012-05-17 | 2012-05-17 | Method and system for recommending users in SNS community |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103428169A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104618555A (en) * | 2014-12-29 | 2015-05-13 | 北京奇虎科技有限公司 | A method, device and system for labeling user information |
| CN105653833A (en) * | 2014-11-12 | 2016-06-08 | 腾讯科技（深圳）有限公司 | Method and device for recommending game community |
| CN105975538A (en) * | 2016-04-29 | 2016-09-28 | 乐视控股（北京）有限公司 | Content recommendation method and device |
| WO2016165414A1 (en) * | 2015-08-28 | 2016-10-20 | 中兴通讯股份有限公司 | Method and device for push information |
| CN107861967A (en) * | 2017-09-02 | 2018-03-30 | 长沙军鸽软件有限公司 | A kind of methods, devices and systems of intelligent Matching good friend |
| CN108022142A (en) * | 2016-11-03 | 2018-05-11 | 阿里巴巴集团控股有限公司 | The definite method, apparatus and electronic equipment of a kind of shopping guide user |
| CN108038789A (en) * | 2017-11-01 | 2018-05-15 | 平安科技（深圳）有限公司 | Item recommendation method, electronic equipment and computer-readable recording medium |
| CN112307355A (en) * | 2019-10-09 | 2021-02-02 | 吴仁超 | Recommendation method for user privacy protection based on big data |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040254881A1 (en) * | 1998-12-08 | 2004-12-16 | Srihari Kumar | Interactive transaction center interface |
| US20070150300A1 (en) * | 2005-12-27 | 2007-06-28 | Ntt Docomo, Inc. | Service recommendation system and service recommendation method |
| CN101044504A (en) * | 2004-10-19 | 2007-09-26 | 雅虎公司 | System and method for location based social networking |
| CN101079898A (en) * | 2007-06-06 | 2007-11-28 | 腾讯科技（深圳）有限公司 | A friend recommendation system and method in SNS network |
| CN101540739A (en) * | 2009-04-14 | 2009-09-23 | 腾讯科技（深圳）有限公司 | User recommendation method and user recommendation system |
| CN101645926A (en) * | 2009-09-01 | 2010-02-10 | 北京邮电大学 | Mobile SNS communication system based on address book of mobile phone and operating method thereof |
| CN101770459A (en) * | 2008-12-31 | 2010-07-07 | 华为技术有限公司 | Method and device for commending friends |
| CN101827123A (en) * | 2010-03-29 | 2010-09-08 | 北京掌中宽途科技有限公司 | Method and system for realizing mobile widget engine with SNS function |
| CN101986674A (en) * | 2010-09-17 | 2011-03-16 | 中兴通讯股份有限公司 | Method and device for inviting friends in social networking sites through mobile communication terminal |
| CN102075573A (en) * | 2011-01-07 | 2011-05-25 | 北京邮电大学 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
| CN102130934A (en) * | 2010-01-20 | 2011-07-20 | 腾讯数码（天津）有限公司 | Method and system for recommending friends in social network site (SNS) community |
| CN102347963A (en) * | 2010-07-30 | 2012-02-08 | 阿里巴巴集团控股有限公司 | Method and device of recommending friends |
| US20120117144A1 (en) * | 2010-11-09 | 2012-05-10 | Sony Corporation | System and method for creating a viewing social network |
-
2012
- 2012-05-17 CN CN2012101538741A patent/CN103428169A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040254881A1 (en) * | 1998-12-08 | 2004-12-16 | Srihari Kumar | Interactive transaction center interface |
| CN101044504A (en) * | 2004-10-19 | 2007-09-26 | 雅虎公司 | System and method for location based social networking |
| US20070150300A1 (en) * | 2005-12-27 | 2007-06-28 | Ntt Docomo, Inc. | Service recommendation system and service recommendation method |
| CN101079898A (en) * | 2007-06-06 | 2007-11-28 | 腾讯科技（深圳）有限公司 | A friend recommendation system and method in SNS network |
| CN101770459A (en) * | 2008-12-31 | 2010-07-07 | 华为技术有限公司 | Method and device for commending friends |
| CN101540739A (en) * | 2009-04-14 | 2009-09-23 | 腾讯科技（深圳）有限公司 | User recommendation method and user recommendation system |
| CN101645926A (en) * | 2009-09-01 | 2010-02-10 | 北京邮电大学 | Mobile SNS communication system based on address book of mobile phone and operating method thereof |
| CN102130934A (en) * | 2010-01-20 | 2011-07-20 | 腾讯数码（天津）有限公司 | Method and system for recommending friends in social network site (SNS) community |
| CN101827123A (en) * | 2010-03-29 | 2010-09-08 | 北京掌中宽途科技有限公司 | Method and system for realizing mobile widget engine with SNS function |
| CN102347963A (en) * | 2010-07-30 | 2012-02-08 | 阿里巴巴集团控股有限公司 | Method and device of recommending friends |
| CN101986674A (en) * | 2010-09-17 | 2011-03-16 | 中兴通讯股份有限公司 | Method and device for inviting friends in social networking sites through mobile communication terminal |
| US20120117144A1 (en) * | 2010-11-09 | 2012-05-10 | Sony Corporation | System and method for creating a viewing social network |
| CN102075573A (en) * | 2011-01-07 | 2011-05-25 | 北京邮电大学 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653833A (en) * | 2014-11-12 | 2016-06-08 | 腾讯科技（深圳）有限公司 | Method and device for recommending game community |
| CN104618555A (en) * | 2014-12-29 | 2015-05-13 | 北京奇虎科技有限公司 | A method, device and system for labeling user information |
| WO2016165414A1 (en) * | 2015-08-28 | 2016-10-20 | 中兴通讯股份有限公司 | Method and device for push information |
| CN105975538A (en) * | 2016-04-29 | 2016-09-28 | 乐视控股（北京）有限公司 | Content recommendation method and device |
| CN108022142A (en) * | 2016-11-03 | 2018-05-11 | 阿里巴巴集团控股有限公司 | The definite method, apparatus and electronic equipment of a kind of shopping guide user |
| CN107861967A (en) * | 2017-09-02 | 2018-03-30 | 长沙军鸽软件有限公司 | A kind of methods, devices and systems of intelligent Matching good friend |
| CN108038789A (en) * | 2017-11-01 | 2018-05-15 | 平安科技（深圳）有限公司 | Item recommendation method, electronic equipment and computer-readable recording medium |
| WO2019085333A1 (en) * | 2017-11-01 | 2019-05-09 | 平安科技（深圳）有限公司 | Project recommendation method, electronic device and computer readable storage medium |
| CN112307355A (en) * | 2019-10-09 | 2021-02-02 | 吴仁超 | Recommendation method for user privacy protection based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103428169A (en) | Method and system for recommending users in SNS community | |
| US11416540B2 (en) | Methods, systems, and media for presenting recommended content based on social cues | |
| CN103678647B (en) | A kind of method and system for realizing information recommendation | |
| CN102629945B (en) | Method for user information acquisition and server as well as terminal | |
| US11276004B2 (en) | Method and apparatus for monitoring system | |
| US10331734B2 (en) | Method and apparatus for recommending network service | |
| US20140046939A1 (en) | User recommendation method and a user recommendation system using the same | |
| US10380129B2 (en) | Automated measurement of content quality | |
| WO2011041067A1 (en) | A method, apparatus and system for increasing website data transfer speed | |
| CN112100221B (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN102223393A (en) | Methods and systems for relationship characterization and utilization from a user's social networks | |
| CN103379158A (en) | Method and system for recommending friend information in social network | |
| CN104053023A (en) | Method and device for determining video similarity | |
| CN113656698B (en) | Training method and device for interest feature extraction model and electronic equipment | |
| CN105608121B (en) | Personalized recommendation method and device | |
| CN107277115A (en) | A kind of content delivery method and device | |
| CN104915359B (en) | Theme label recommended method and device | |
| CN104504138A (en) | Human-based information fusion method and device | |
| CN103561259A (en) | Network conference visual quality automatic evaluation method for application sharing services | |
| CN105721899A (en) | Video quality scoring method and system | |
| CN107809370A (en) | User recommends method and device | |
| KR20130116982A (en) | User interest inference method and system in sns using topics on social activities with neighbors | |
| CN107368499B (en) | Client label modeling and recommending method and device | |
| CN113869926B (en) | Advertisement identification method, advertisement identification device, electronic equipment and storage medium | |
| JP2021177284A (en) | Abnormality / change estimation method, program and device using multiple posting time series data |
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: 20131204 |
|
| RJ01 | Rejection of invention patent application after publication |