CN103258020A - Recommending system and method combining SNS and search engine technology - Google Patents
Recommending system and method combining SNS and search engine technology Download PDFInfo
- Publication number
- CN103258020A CN103258020A CN2013101595857A CN201310159585A CN103258020A CN 103258020 A CN103258020 A CN 103258020A CN 2013101595857 A CN2013101595857 A CN 2013101595857A CN 201310159585 A CN201310159585 A CN 201310159585A CN 103258020 A CN103258020 A CN 103258020A
- Authority
- CN
- China
- Prior art keywords
- user
- sns
- good friend
- product
- 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 recommending system and method combining an SNS and a search engine technology. The recommending system and method combining the SNS and the search engine technology introduces user search behaviors and SNS friend information so that the user search behaviors and the SNS friend information are used as references to obtain recommending results from an angle of a user himself and an angle of a friend of the user. The recommending system comprises a friend information obtaining module, a recommending result generation module based on the SNS friend intimacy, a search behavior information obtaining module, a recommending result generation module based on the search behavior information and a result integrating module. The recommending method comprises a first step of obtaining friend information, a second step of obtaining the recommending results based on the SNS friend intimacy, a third step of obtaining the search behavior information, a fourth step of obtaining the recommending results based on the search behaviors, and a fifth step of integrating the recommending results. According to the recommending system and method combining the SNS and the search engine technology, the characteristics of sharing and exchanging of the SNS are applied, on the one hand, the transmission efficiency of products in an e-commerce platform is improved, on the other hand, complementary to the technology which is based on the search behaviors is formed, and therefore the accuracy, the reliability and the comprehensiveness of the recommending results are improved.
Description
Technical field
The invention belongs to the recommended technology field that internet data excavates, particularly a kind of in conjunction with SNS(full name Social Networking Services, i.e. social network services) and commending system and the method for search engine technique.
Background technology
Along with the develop rapidly of cybertimes, information development speed is exceedingly fast, and in magnanimity information, people can not find own needed information like a cork.The certain needs of people have been satisfied in the appearance of information retrieval technique, but owing to its versatility, still can not satisfy user's query requests of different background, different purpose and different times.In e-commerce field, it is more common that the user can not find the phenomenon of the product that is fit to oneself.Because the quantity of product is very many, each product is described very well by businessman, simultaneously again by some interests means so that the product of oneself is easier is searched out, businessman also may employ the people that the purchase volume of the product of oneself is improved, even provide a plurality of favorable comments, exaggerated the quality of product.This dishonest behavior becomes a drawback of ecommerce, so that the user is difficult to find the product that is fit to oneself.
In order to allow the user can find more easily the product that is fit to oneself, the commending system of research user-product model has just produced.Commending system refers to be based upon on the information and the deep basis of understanding of behavior to each user, is the suitable Related product of user's active push.Therefore just become a discussion focus of current era about the research of commending system, a series of recommended technology and algorithm are found out.Wherein collaborative filtering recommending is the most successful personalized recommendation technology, but people also recognize the deficiency of this algorithm gradually, and shortcoming mainly contains sparse property, extensibility, cold start-up problem and the many interest questions of user.Even relevant scholar's research solution, but still can not really effectively deal with problems.Main cause is to exist insoluble deficiency based on the commending system of a recommended models, is difficult to effectively provide the demand that satisfies the user.
SNS, i.e. social networking service, the social networks that is current popular is a kind of service of platform.When people use this service, usually need the real personal information of input, the real good friend's foundation with oneself on network contacts, and shares mutually, exchanges mutually.Therefore have authenticity and propagated characteristics in conjunction with SNS, can be conducive to the global optimization that commending system improves recommendation results accuracy and system architecture.
Summary of the invention
The present invention seeks to solve too unilateral, the single recommendation results tabulation of recommendation results that single recommended models now generates and can not meet consumers' demand and have and mix recommended models to the selection problem too blindly of model, solve simultaneously have now the reference of recommend method institute based on the not high problem of the existing confidence level of full internet data.
The objective of the invention is to be achieved through the following technical solutions:
A kind of commending system in conjunction with SNS and search engine technique comprises:
Obtain the friend information module, be used for obtaining mutual information data with the most intimate front 150 good friends of user from corresponding SNS platform, mainly comprise contacting number of times and contacting the time of user and certain good friend, also need in addition to obtain the application records that this good friend browsed, the application records that has, the application records commented on and the application records information of having recommended;
Recommendation results generation module based on SNS good friend cohesion, be used for calculating the cohesion between targeted customer and certain good friend and calculating this user to the classification value of certain product according to the user good friend interactive information that described obtaining information module obtains, then good friend's cohesion and the classification value information according to gained calculates the recommendation preferred value that the user good friend pays close attention to certain product again, and a Products Show will recommending preferred value to sort to obtain in conjunction with SNS is tabulated at last temporary this tabulation;
Obtain the search behavior information module, be used for the search behavior information database from the user, obtain targeted customer and other users' behavioural information and generate the user---the product two dimension is browsed matrix;
Recommendation results generation module based on search behavior information, be used for according to obtaining the matrix of browsing that the search behavior information module obtains, calculate and the immediate similar users group of user behavior, and calculate certain product according to this customer group and in this similar users group, have a number, thereby at last sort from big to small and obtain a Products Show tabulation in conjunction with search engine technique according to having number, and temporary;
Integrate module as a result, be used for will by the described tabulation that generates based on the recommendation results generation module of SNS good friend cohesion and the described row that generate based on the recommendation results generation module of search behavior information not each, distinguish simultaneously output display.
Described recommendation results generation module implementation procedure based on SNS good friend cohesion is as follows:
(1) calculate user and good friend's cohesion with following formula:
L wherein
iRepresentative of consumer i and good friend's cohesion, C
iExpression good friend i and targeted customer contact number of times, t
iExpression good friend i and targeted customer's the time that contacts, T represent all good friends and with T.T. that contacts of targeted customer.
(2) come the classification value of counting yield with following formula:
S
i=X
1+2X
2+4X
3+8X
4
S wherein
iThe classification value of representative products i, X
1, X
2, X
3, X
4Be fundamental function, expression is as follows respectively:
(3) certain good friend who calculates the user with following formula pays close attention to the recommendation preferred value of certain product:
K wherein
IjThe recommendation preferred value of the product j that representative of consumer good friend i pays close attention to.
(4) with K
IjArrange from big to small, can draw the product of paying close attention to most between the user good friend, thereby can draw a recommendation list in conjunction with SNS.
Described recommendation results generation module implementation procedure based on search behavior information is as follows:
(1) the following formula of use calculates the similarity between user and the user:
P wherein
IjExpression user i and user j browse similarity, u
iThe browsing document of expression user i also shows with vector form.
(2) according to P
IjValue, arrange from big to small, draw the immediate customer group of the behavior of browsing with user i.
(3) use formula calculating to browse the product that maximum people browse in the similar customer group of behavior:
A wherein
iRepresent to browse in the immediate customer group number of product i, X
jWhether expression product i belongs to the fundamental function of user j, as follows:
(4) according to A
iValue, arrange from big to small, draw a recommendation list in conjunction with search engine technique.
A kind of recommend method in conjunction with SNS and search engine technique that utilizes above-mentioned commending system comprises:
By obtain the mutual information data with the most intimate front 150 good friends of user from corresponding SNS platform, mainly comprise contacting number of times and contacting the time of user and certain good friend, also need in addition to obtain the application records that this good friend browsed, the application records that has, the application records commented on and the application records information of having recommended;
According to described mutual information data (the interchange number of times between the user, exchange time, mutual access frequency), calculate the cohesion between targeted customer and certain good friend and calculate this user to the classification value of certain product, then according to cohesion result and the classification value information of gained, certain good friend who calculates the user pays close attention to the recommendation preferred value of certain product and according to recommending preferred value all recommendation results that sort from big to small, draws a tabulation and temporary in conjunction with SNS;
From database, the search behavior information that reads all users is namely browsed the historical record data of product, and data-switching is become a user---and the two dimension of product is browsed in the data structure of matrix;
According to the described matrix of browsing, calculate the behavior similarity between this user and other users, and the screening of sorting draws the immediate similar users group of the behavior of browsing with the targeted customer according to similarity.From described similar users group, calculate having number and accordingly product being sorted the recommendation list of all results that will sort from big to small at last and temporary gained of certain product at last;
At last by respectively output display that the described living and described recommendation results based on the search behavior Information generation of recommendation results tabulation that generates based on SNS good friend cohesion is tabulated simultaneously.
Compared with prior art, the present invention has following technique effect and advantage:
The method and system's one side are from good friend's angle of user, combine the advantage of SNS, not only obtain the higher data of confidence level as the foundation of recommendation results from this user's SNS good friend network of personal connections, and so that the user plays an active part in the commending system more, be more other the more valuable data of commending system collection.Consider from user's self angle on the other hand, introduce and excavate user's interest based on the technology of search engine, thereby recommend new product or even the product of unexpected winner to the user.In addition owing to recognizing that single recommendation list can not satisfy user's demand effectively, so native system and method be in connection with the recommendation results of SNS and in conjunction with the recommendation results of search engine technique respectively with two tabulations output displays simultaneously, like this so that two kinds of recommendation results form complementation, not only to a certain degree solving owing to the cold start-up problem with reference to user behavior information, and obtaining again more to meet more comprehensively the recommendation results of user's needs.
Description of drawings
Fig. 1 is the system construction drawing in conjunction with the commending system of SNS and search engine technique;
Fig. 2 is employed user among the embodiment---the two dimension of product is browsed the matrix schematic diagram.
Fig. 3 is the schematic flow sheet in conjunction with the recommend method of SNS and search engine technique.
Fig. 4 is the implementation procedure schematic diagram based on the recommendation results generation module of SNS good friend cohesion in conjunction with the commending system of SNS and search engine technique.
Fig. 5 is the implementation procedure schematic diagram based on the recommendation results generation module of search behavior information in conjunction with the commending system of SNS and search engine technique.
Embodiment
For the ease of understanding technical method of the present invention, come to be elaborated to of the present invention below in conjunction with drawings and Examples.What will illustrate simultaneously a bit is that these embodiment are not intended to limit the present invention.
Example one:
A kind of commending system in conjunction with SNS and search engine technique of the present invention, as shown in Figure 1, by obtain the friend information module, based on the recommendation results generation module of SNS good friend cohesion, obtain the search behavior information module, based on the recommendation results generation module of search behavior information, integrate module consists of as a result.
Obtain the friend information module, be used for obtaining mutual information data with the most intimate front 150 good friends of user from corresponding SNS platform; For example one side is take the Sina of largest domestic microblogging as example, we can offer the api interface that the developer uses by Sina's microblogging and obtain the jason data structure that comprises the various information of user, we then only need to use wherein user's friend information list, and for example targeted customer and good friend's contacts number of times and contact the time.We also need from the database of user system of the present invention on the other hand, obtain the application records that user's good friend browsed, the application records that has, the application records commented on and the application records information of having recommended; Then all these information are input in the recommendation results generation module based on SNS good friend cohesion as parameter.
Recommendation results generation module based on SNS good friend cohesion, be used for calculating the cohesion between targeted customer and certain good friend and calculating this user to the classification value of certain product according to the user good friend interactive information with the parametric form input that described obtaining information module obtains, then good friend's cohesion and the classification value information according to gained calculates the recommendation preferred value that the user good friend pays close attention to certain product again, and will recommend preferred value to sort from big to small to obtain a Products Show tabulation in conjunction with SNS, be input to as a result in the integrate module as parameter at last; For example certain good friend of user is more intimate, and this good friend is that browsed higher to user's weight with product that had so, just more might recommend the user.
Obtaining the search behavior information module, be used for obtaining from the customer data base of system of the present invention user's search behavior information, mainly is the product historical record that the user browsed.Thereby generating the user---the product two dimension is browsed matrix and is input in the recommendation results generation module based on search behavior information with parametric form, this two dimension is browsed matrix and be please refer to of Fig. 2 with reference to example, numeral 1 certain user of expression in the table has browsed certain project, and numeral 0 certain user of expression do not browse certain project.
Recommendation results generation module based on search behavior information, be used for basis and obtain the matrix of browsing with the parametric form input that the search behavior information module obtains, calculate and the immediate similar users group of user behavior, and calculate certain product according to this customer group and in this similar users group, have a number, thereby at last sort from big to small and obtain one in conjunction with the Products Show tabulation of search engine technique according to having number, be input to as a result in the integrate module as parameter at last; For example his each product of browsing of certain user is very similar with the product that the user browsed, and he and user's similarity weight is just larger so, thereby more might elect as among the similar users group.
Integrate module as a result, since obtain the friend information module and based on the recommendation results generation module of SNS good friend cohesion with obtain the search behavior information module and be executed in parallel based on the recommendation results generation module of search behavior information, so can obtain fast the tabulation and the described tabulation that generates based on the recommendation results generation module of search behavior information that are generated by described recommendation results generation module based on SNS good friend cohesion, at last simultaneously respectively output.For example for cellphone subscriber's end, can divide two hurdles to show recommendation results.And for webpage, can divide two zonule output recommendation results.
Example two:
A kind of recommend method in conjunction with SNS and search engine technique of the present invention, shown in the process flow diagram of Fig. 3 the method, whole performing step is as follows:
1. at first by obtain the mutual information data between user and good friend from corresponding SNS platform, mainly comprise contacting number of times and contacting the time of user and certain good friend, also need in addition to obtain the application records that this good friend browsed, the application records that has, the application records commented on and the application records information of having recommended;
2. secondly as shown in Figure 4, by the mutual information data of obtaining according to previous step, contact number of times C with reference to good friend i and targeted customer on the one hand
i, good friend i and targeted customer's the time that contacts t
iWith all good friends with utilize formula with targeted customer's the T.T. T that contacts
Calculate user i and good friend's cohesion L
i, also need on the other hand the application records X that browsed with reference to the good friend
1, the application records X that has
2, the application records X that has commented on
3With the application records X that has recommended
4Fundamental function utilizes formula S
i=X
1+ 2X
2+ 4X
3+ 8X
4Calculate the classification value S of product i
i, then utilize cohesion L
iWith classification value S
iAnd utilize formula
Calculate the recommendation preferred value K of the product j of user good friend i concern
Ij, at last according to K
IjAll products that sort from big to small, thus recommendation results tabulation based on SNS good friend cohesion generated, and it is temporary.
3. then from system database, reading the product historical record data that all users' search behavior information was namely browsed, and data-switching become a user---the two dimension of product is browsed the data structure of matrix;
4. then as shown in Figure 5, at first obtain browsing document u with the user i of vector form performance according to the matrix of browsing of previous step gained
iUtilize formula
What calculate user i and user j browses similarity P
IjThen arrange from big to small and select the forward a certain amount of user of rank wherein as the similar users group according to the similarity of browsing that calculates all users; Secondly draw the fundamental function X whether product i belongs to user j with reference to similar users group data
jAnd utilize formula
Calculate the number A that browsed product i among the similar users group
iLast A according to each product
iFrom big to small ordering draws in conjunction with a recommendation list of search engine technique and temporary.
5. a last recommendation list in conjunction with search engine technique that draws according to recommendation results tabulation and step 4 based on SNS good friend cohesion by step 2 gained, with their respectively while output display to the user.
Especially, in step 2, fundamental function X
1, X
2, X
3And X
4All only has 0 and 1 two value.0 expression does not have, and 1 expression has.
Especially, in step 4, fundamental function X
jOnly has 0 and 1 two value.0 expression was not browsed, and 1 expression was browsed.
Claims (6)
1. commending system in conjunction with SNS and search engine technique is characterized in that comprising with lower module:
Obtain the friend information module, be used for obtaining mutual information data with the most intimate front 150 good friends of user from corresponding SNS platform;
Recommendation results generation module based on SNS good friend cohesion, be used for calculating the cohesion between targeted customer and arbitrary good friend and calculating this user to the classification value of certain product according to the user good friend mutual information data that described obtaining information module obtains, then this good friend who calculates again the user according to good friend's cohesion and the classification value information of gained pays close attention to the recommendation preferred value of certain product, and the Products Show that will recommend preferred value to sort from big to small to obtain in conjunction with SNS is tabulated at last temporary this tabulation;
Obtain the search behavior information module, be used for the search behavior information database from the user, obtain targeted customer and targeted customer good friend's behavioural information and generate the user---the product two dimension is browsed matrix;
Recommendation results generation module based on search behavior information, be used for browsing matrix according to obtaining the product two dimension that the search behavior information module obtains, draw and the immediate similar users group of user behavior, and calculate arbitrary product wherein according to this similar users group and in this similar users group, have a number, thereby at last sort from big to small and obtain one in conjunction with the Products Show tabulation of search engine technique according to having number, and temporary;
Integrate module as a result, for the Products Show tabulation in conjunction with search engine technique that will be generated by Products Show tabulation and the described recommendation results generation module based on search behavior information in conjunction with SNS that described recommendation results generation module based on SNS good friend cohesion generates, distinguish simultaneously output display.
2. a kind of commending system in conjunction with SNS and search engine technique according to claim 1, it is characterized in that: describedly obtain the interactive information that the friend information module obtains and comprise contacting number of times and contacting the time of user and arbitrary good friend, also need in addition to obtain the application records that this good friend browsed, the application records that has, the application records commented on and the application records information of having recommended.
3. a kind of commending system in conjunction with SNS and search engine technique according to claim 1 is characterized in that: the described foundation of obtaining with the most intimate front 150 good friends of user is that guest sieve Dunbar proposes " 150 law ".
4. a kind of commending system in conjunction with SNS and search engine technique according to claim 1 is characterized in that: the implementation procedure of described recommendation results generation module based on SNS good friend cohesion is as follows:
(1) calculate user and good friend's cohesion with following formula:
L wherein
iRepresentative of consumer i and good friend's cohesion, C
iExpression good friend i and targeted customer contact number of times, t
iExpression good friend i and targeted customer's the time that contacts, T represents all good friends and targeted customer's the T.T. that contacts, and i is used for distinguishing different users and good friend herein;
(2) come the classification value of counting yield with following formula:
S
i=X
1+2X
2+4X
3+8X
4
S wherein
iThe classification value of representative products i, i is used for distinguishing different products, X herein
1, X
2, X
3, X
4Be fundamental function, expression is as follows respectively:
(3) certain the good friend i that calculates the user with following formula pays close attention to the recommendation preferred value of certain product j:
K wherein
IjThe recommendation preferred value of the product j that representative of consumer good friend i pays close attention to;
(4) with K
IjArrange from big to small, namely draw the product of paying close attention to most between the user good friend, thereby draw a recommendation list in conjunction with SNS.
5. a kind of commending system in conjunction with SNS and search engine technique according to claim 1 is characterized in that: the implementation procedure based on the recommendation results generation module of search behavior information is as follows:
(1) the following formula of use calculates the similarity between user and the user:
P wherein
IjExpression user i and user j browse similarity, u
iThe browsing document of expression user i also shows with vector form;
(2) according to P
IjValue, arrange from big to small, draw the immediate customer group of the behavior of browsing with user i;
(3) use following formula to calculate and browse the product that maximum people browse in the similar customer group of behavior:
A wherein
iRepresent to browse in the immediate customer group number of product i, X
jWhether expression product i belongs to the fundamental function of user j:
6. recommend method that utilizes each described commending system of claim 1~5 is characterized in that may further comprise the steps:
By obtain the mutual information data with the most intimate front 150 good friends of user from corresponding SNS platform;
According to described mutual information data, calculate the cohesion between targeted customer and certain good friend and calculate this user to the classification value of certain product, then according to cohesion result and the classification value information of gained, certain good friend who calculates the user pays close attention to the recommendation preferred value of certain product and according to recommending preferred value all recommendation results that sort from big to small, draws a tabulation and temporary in conjunction with SNS; From database, the search behavior information that reads all users is namely browsed the historical record data of product, and data-switching is become a user---and the two dimension of product is browsed in the data structure of matrix;
According to the described matrix of browsing, calculate the behavior similarity between this user and other users, and the screening of sorting draws the immediate similar users group of the behavior of browsing with the targeted customer according to similarity; From described similar users group, calculate having number and accordingly product being sorted all results that sort from big to small and temporary this recommendation list in conjunction with search engine technique of certain product at last;
At last by respectively output display that the described living and described recommendation results based on the search behavior Information generation of recommendation results tabulation that generates based on SNS good friend cohesion is tabulated simultaneously.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013101595857A CN103258020A (en) | 2013-05-02 | 2013-05-02 | Recommending system and method combining SNS and search engine technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013101595857A CN103258020A (en) | 2013-05-02 | 2013-05-02 | Recommending system and method combining SNS and search engine technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103258020A true CN103258020A (en) | 2013-08-21 |
Family
ID=48961937
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013101595857A Pending CN103258020A (en) | 2013-05-02 | 2013-05-02 | Recommending system and method combining SNS and search engine technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103258020A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103475717A (en) * | 2013-09-11 | 2013-12-25 | 杭州东信北邮信息技术有限公司 | Method and system for recommending friends based on social network |
CN103605791A (en) * | 2013-12-04 | 2014-02-26 | 深圳中兴网信科技有限公司 | Information pushing system and information pushing method |
CN103823888A (en) * | 2014-03-07 | 2014-05-28 | 安徽融数信息科技有限责任公司 | Node-closeness-based social network site friend recommendation method |
CN104519057A (en) * | 2014-12-12 | 2015-04-15 | 小米科技有限责任公司 | Qualification awarding method, qualification acquiring device and qualification acquiring device |
CN104601435A (en) * | 2013-10-30 | 2015-05-06 | 北京千橡网景科技发展有限公司 | Method and device for recommending friends |
CN104699732A (en) * | 2013-12-05 | 2015-06-10 | 联想(新加坡)私人有限公司 | Method for forming user profile and information processing equipment |
CN104932920A (en) * | 2015-06-16 | 2015-09-23 | 广东欧珀移动通信有限公司 | Method and device for guiding browse paths of application program |
CN104933125A (en) * | 2015-06-10 | 2015-09-23 | 百度在线网络技术(北京)有限公司 | Recommendation method and device based on trust relationship |
CN105354259A (en) * | 2015-10-22 | 2016-02-24 | 百度在线网络技术(北京)有限公司 | Mobile search method and apparatus |
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 |
WO2016197758A1 (en) * | 2015-06-09 | 2016-12-15 | 腾讯科技(深圳)有限公司 | Information recommendation system, method and apparatus |
CN106780071A (en) * | 2016-12-28 | 2017-05-31 | 西安交通大学 | A kind of online community network Information Communication modeling method based on multi-mode mixed model |
CN107391556A (en) * | 2017-06-07 | 2017-11-24 | 百度在线网络技术(北京)有限公司 | Based on searching method, server and the computer-readable medium for recommending application |
CN107491462A (en) * | 2016-06-13 | 2017-12-19 | 腾讯科技(深圳)有限公司 | The method and system of search result is provided |
CN109344354A (en) * | 2018-09-20 | 2019-02-15 | 珠海分享赢天下科技有限公司 | A kind of social browsing device with content self-propagation function |
CN110197207A (en) * | 2019-05-13 | 2019-09-03 | 腾讯科技(深圳)有限公司 | To not sorting out the method and relevant apparatus that user group is sorted out |
CN111368202A (en) * | 2020-03-06 | 2020-07-03 | 咪咕文化科技有限公司 | Search recommendation method and device, electronic equipment and storage medium |
US10726465B2 (en) | 2016-03-24 | 2020-07-28 | International Business Machines Corporation | System, method and computer program product providing eye tracking based cognitive filtering and product recommendations |
CN112632359A (en) * | 2020-12-30 | 2021-04-09 | 北京锐安科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
CN116887001A (en) * | 2023-09-06 | 2023-10-13 | 四川中电启明星信息技术有限公司 | Short video pushing method and device integrating social attribute information and electronic equipment |
CN117009557A (en) * | 2023-08-08 | 2023-11-07 | 苏州瑞山传媒有限公司 | Multimedia system data processing method and processing device |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102915307A (en) * | 2011-08-02 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Device and method for recommending personalized information and information processing system |
-
2013
- 2013-05-02 CN CN2013101595857A patent/CN103258020A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102915307A (en) * | 2011-08-02 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Device and method for recommending personalized information and information processing system |
Non-Patent Citations (2)
Title |
---|
李智琦等: "基于数据挖掘的个性化推荐在SNS中的应用", 《电脑知识与技术》 * |
李聪等: "基于项目类别相似性的协同过滤推荐算法", 《合肥工业大学学报(自然科学版)》 * |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103475717A (en) * | 2013-09-11 | 2013-12-25 | 杭州东信北邮信息技术有限公司 | Method and system for recommending friends based on social network |
CN103475717B (en) * | 2013-09-11 | 2017-03-15 | 杭州东信北邮信息技术有限公司 | A kind of friend recommendation method and system based on social networks |
CN104601435A (en) * | 2013-10-30 | 2015-05-06 | 北京千橡网景科技发展有限公司 | Method and device for recommending friends |
CN103605791A (en) * | 2013-12-04 | 2014-02-26 | 深圳中兴网信科技有限公司 | Information pushing system and information pushing method |
CN103605791B (en) * | 2013-12-04 | 2017-08-25 | 深圳中兴网信科技有限公司 | Information transmission system and information-pushing method |
CN104699732A (en) * | 2013-12-05 | 2015-06-10 | 联想(新加坡)私人有限公司 | Method for forming user profile and information processing equipment |
CN104699732B (en) * | 2013-12-05 | 2019-09-06 | 联想(新加坡)私人有限公司 | Form the method and information processing equipment of user profiles |
CN103823888A (en) * | 2014-03-07 | 2014-05-28 | 安徽融数信息科技有限责任公司 | Node-closeness-based social network site friend recommendation method |
CN103823888B (en) * | 2014-03-07 | 2017-02-08 | 安徽融数信息科技有限责任公司 | Node-closeness-based social network site friend recommendation method |
CN104519057B (en) * | 2014-12-12 | 2018-06-19 | 小米科技有限责任公司 | Qualification giving method, qualification acquisition methods and device |
CN104519057A (en) * | 2014-12-12 | 2015-04-15 | 小米科技有限责任公司 | Qualification awarding method, qualification acquiring device and qualification acquiring device |
US10972395B2 (en) | 2014-12-12 | 2021-04-06 | Xiaomi Inc. | Method and device for granting and acquiring qualification |
US10411945B2 (en) | 2015-06-09 | 2019-09-10 | Tencent Technology (Shenzhen) Company Limited | Time-distributed and real-time processing in information recommendation system, method and apparatus |
WO2016197758A1 (en) * | 2015-06-09 | 2016-12-15 | 腾讯科技(深圳)有限公司 | Information recommendation system, method and apparatus |
CN104933125A (en) * | 2015-06-10 | 2015-09-23 | 百度在线网络技术(北京)有限公司 | Recommendation method and device based on trust relationship |
CN104933125B (en) * | 2015-06-10 | 2019-05-03 | 百度在线网络技术(北京)有限公司 | Recommended method and device based on trusting relationship |
CN104932920A (en) * | 2015-06-16 | 2015-09-23 | 广东欧珀移动通信有限公司 | Method and device for guiding browse paths of application program |
CN104932920B (en) * | 2015-06-16 | 2018-02-23 | 广东欧珀移动通信有限公司 | The browse path bootstrap technique and device of a kind of application program |
CN105354259A (en) * | 2015-10-22 | 2016-02-24 | 百度在线网络技术(北京)有限公司 | Mobile search method and apparatus |
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 |
US10726465B2 (en) | 2016-03-24 | 2020-07-28 | International Business Machines Corporation | System, method and computer program product providing eye tracking based cognitive filtering and product recommendations |
CN107491462A (en) * | 2016-06-13 | 2017-12-19 | 腾讯科技(深圳)有限公司 | The method and system of search result is provided |
CN107491462B (en) * | 2016-06-13 | 2020-09-11 | 腾讯科技(深圳)有限公司 | Method and system for providing search results |
CN106780071A (en) * | 2016-12-28 | 2017-05-31 | 西安交通大学 | A kind of online community network Information Communication modeling method based on multi-mode mixed model |
CN106780071B (en) * | 2016-12-28 | 2020-06-26 | 西安交通大学 | Online social network information propagation modeling method based on multi-mode hybrid model |
CN107391556B (en) * | 2017-06-07 | 2020-12-18 | 百度在线网络技术(北京)有限公司 | Search method based on recommended application, server and computer readable medium |
CN107391556A (en) * | 2017-06-07 | 2017-11-24 | 百度在线网络技术(北京)有限公司 | Based on searching method, server and the computer-readable medium for recommending application |
CN109344354A (en) * | 2018-09-20 | 2019-02-15 | 珠海分享赢天下科技有限公司 | A kind of social browsing device with content self-propagation function |
CN110197207A (en) * | 2019-05-13 | 2019-09-03 | 腾讯科技(深圳)有限公司 | To not sorting out the method and relevant apparatus that user group is sorted out |
CN111368202A (en) * | 2020-03-06 | 2020-07-03 | 咪咕文化科技有限公司 | Search recommendation method and device, electronic equipment and storage medium |
CN111368202B (en) * | 2020-03-06 | 2023-09-19 | 咪咕文化科技有限公司 | Search recommendation method and device, electronic equipment and storage medium |
CN112632359A (en) * | 2020-12-30 | 2021-04-09 | 北京锐安科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
CN112632359B (en) * | 2020-12-30 | 2023-11-07 | 北京锐安科技有限公司 | Information recommendation method, device, electronic equipment and storage medium |
CN117009557A (en) * | 2023-08-08 | 2023-11-07 | 苏州瑞山传媒有限公司 | Multimedia system data processing method and processing device |
CN116887001A (en) * | 2023-09-06 | 2023-10-13 | 四川中电启明星信息技术有限公司 | Short video pushing method and device integrating social attribute information and electronic equipment |
CN116887001B (en) * | 2023-09-06 | 2023-12-15 | 四川中电启明星信息技术有限公司 | Short video pushing method and device integrating social attribute information and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103258020A (en) | Recommending system and method combining SNS and search engine technology | |
US11632407B2 (en) | Supplementing user web-browsing | |
CN102880691B (en) | A kind of mixing commending system based on user's cohesion and method | |
Kim et al. | Impact of social influence in e-commerce decision making | |
Zhang et al. | Product information diffusion in a social network | |
CN101324948B (en) | A kind of method of information recommendation and device | |
US8676875B1 (en) | Social media measurement | |
CN106126582A (en) | Recommend method and device | |
US20120226678A1 (en) | Optimization of social media engagement | |
US20130086063A1 (en) | Deriving User Influences on Topics from Visual and Social Content | |
KR20160083017A (en) | Systems and methods for identifying influencers and their communities in a social data network | |
CN103778260A (en) | Individualized microblog information recommending system and method | |
CN105247507A (en) | Influence score of a brand | |
CN102063433A (en) | Method and device for recommending related items | |
CN106062743A (en) | Systems and methods for keyword suggestion | |
CN103946886A (en) | Structured objects and actions on a social networking system | |
CN103136303A (en) | Method and equipment of dividing user group in social network service website | |
CN103617289A (en) | Micro-blog recommendation method based on user characteristics and network relations | |
CN105023178B (en) | A kind of electronic commerce recommending method based on ontology | |
CN101957968A (en) | Online transaction service aggregation method based on Hadoop | |
CN110637317A (en) | Distributed node cluster for establishing digital contact points across multiple devices on a digital communications network | |
Pham et al. | Sentiment analysis and user similarity for social recommender system: An experimental study | |
KR101206863B1 (en) | Method and Apparatus for Producing User Reputation of Online Network | |
Guo et al. | An opinion feature extraction approach based on a multidimensional sentence analysis model | |
CN109615437A (en) | Sale obtains objective method for tracking and managing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130821 |