CN103138954A - Recommending method, recommending system and recommending server of referenced item - Google Patents
Recommending method, recommending system and recommending server of referenced item Download PDFInfo
- Publication number
- CN103138954A CN103138954A CN2011103976178A CN201110397617A CN103138954A CN 103138954 A CN103138954 A CN 103138954A CN 2011103976178 A CN2011103976178 A CN 2011103976178A CN 201110397617 A CN201110397617 A CN 201110397617A CN 103138954 A CN103138954 A CN 103138954A
- Authority
- CN
- China
- Prior art keywords
- strategy
- user
- recommendation
- list
- recommended
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a recommending method, a recommending system and a recommending server of a recommended item. When a recommending incident triggered by operation of a current user is confirmed, based on a recommending strategy of the current user on a to-be-recommended item and a receiving strategy of all target users in a friend list of the current user on the to-be-recommended item, a candidate target user list is generated. When the target user list which is confirmed and fed back by the current user based on the candidate target user list is received, the current to-be-recommended item is recommended to all the target users in the target user list. Regarding to the current user who sends the recommended item, recommendation of the recommended item to target users who are not likely to receive the item is reduced, recommending resources are saved, recommending flexibility of the current user is increased based on improvement of the success rate in reception of an item. Regarding to the target users who receive recommendation, items that are not attractive are prevented from being received, recommending resources are saved and the reception rate of the current to-be-recommended item is improved.
Description
Technical field
The present invention relates to the business support field, relate in particular to a kind of method for pushing, system and recommendation server of recommendation items.
Background technology
Along with the rise of ecommerce, social online media sites, recommended technology has been widely applied in the application of many hot topics such as Taobao, bean cotyledon, Google's news, Amazon, popular comment net.Traditional commending system mainly is divided into two classes: content-based recommendation system and collaborative filtering system.In the content-based recommendation system, the input data are treated to user profiles one by one, each user profiles generally is expressed as a characteristic vector, recommended candidate information is carried out similar processing, then carry out similarity with targeted customer's profile and calculate, the candidate information near user profiles is pushed to the user as recommendation items.In the collaborative filtering system, user behavior data is used to calculate between the user or the similarity between recommended candidate information, draws after recommendation results weighting further according to this similitude.
In a typical recommendation based on social networks, the user can send to the recommendation items of self liking other user in social networks and receive the recommendation items that is pushed by other users from other user, yet, complexity due to the social networks formation, the recommendation items that certain user's good friend may push him is also lost interest in, simultaneously, certain user also can receive a large amount of self and uninterested recommendation items, cause the waste of recommending resource, also reduced the success rate that recommendation items is adopted; And after the user received recommendation items there repeatedly from a good friend, the possibility of adopting recommendation items also can reduce gradually, made the success rate that whole recommendation items is adopted reduce.
Summary of the invention
The embodiment of the present invention provides a kind of method for pushing, system and recommendation server of recommendation items, causes the waste of recommending resource and the not high problem of success rate that recommendation items is adopted in order to solve existing method for pushing.
The method for pushing of a kind of recommendation items that the embodiment of the present invention provides comprises:
When the operation of determining the active user triggers the recommendation event, obtain described active user's buddy list according to described active user's sign;
To the reception strategy of each targeted customer in current to be recommended recommendation strategy and described buddy list to current to be recommended, produce the candidate target user list according to described active user;
Described candidate target user list is presented to described active user, receive the list of targeted subscribers that described active user determines and returns according to described candidate target user list;
The confirmation that sends according to described active user sends the instruction of recommending, and each targeted customer pushes described current to be recommended in the described list of targeted subscribers.
A kind of recommendation server that the embodiment of the present invention provides comprises:
Acquisition module is used for obtaining described active user's buddy list according to described active user's sign when the operation of determining the active user triggers the recommendation event;
Computing module is used for according to described active user the recommendation strategy of current to be recommended and each targeted customer of described buddy list reception strategy to current to be recommended is produced the candidate target user list;
Confirm module, be used for described candidate target user list is presented to described active user, receive the list of targeted subscribers that described active user determines and returns according to described candidate target user list;
Recommending module, the confirmation that is used for sending according to described active user sends the instruction of recommending, and each targeted customer pushes described current to be recommended in the described list of targeted subscribers.
The supplying system of a kind of recommendation items that the embodiment of the present invention provides comprises: recommendation server, service server and information promulgating platform server;
Described recommendation server is used for obtaining described active user's buddy list according to described active user's sign when the operation of determining the active user triggers the recommendation event; To the reception strategy of each targeted customer in current to be recommended recommendation strategy and described buddy list to current to be recommended, produce the candidate target user list according to described active user; Described candidate target user list is presented to described active user, receive the list of targeted subscribers that described active user determines and returns according to described candidate target user list; The confirmation that sends according to described active user sends the instruction of recommending, and each targeted customer pushes described current to be recommended in the described list of targeted subscribers;
Described service server is for friend information and recommendation items information that the user is provided;
Described information promulgating platform server is used for current to be recommended the receiving platform that is published to the targeted customer that described recommendation server is pushed.
The beneficial effect of the embodiment of the present invention comprises:
The method for pushing of a kind of recommendation items that the embodiment of the present invention provides, system and recommendation server, when the operation of determining the active user triggers the recommendation event, to the reception strategy of each targeted customer in current to be recommended recommendation strategy and active user's buddy list to current to be recommended, produce the candidate target user list according to the active user; Receive that the active user determines according to the candidate target user list and the list of targeted subscribers returned after, each targeted customer recommends current to be recommended in the list of targeted subscribers.the method for pushing of the recommendation items that the embodiment of the present invention provides is when the list of targeted subscribers that produces current to be recommended, comprehensive reference between active user and targeted customer the recommendation strategy and receive strategy, filter out and be fit to the targeted customer of current to be recommended, and finally confirm each targeted customer in list of targeted subscribers via the active user, for the active user who sends recommendation items, can reduce to adopting the low targeted customer of probability and push recommendation items, saved the recommendation resource, and on the basis of the success rate that the raising recommendation items is adopted, increased the flexibility that the active user pushes, for pushed targeted customer, avoided receiving a large amount of uninterested recommendation items, saved the recommendation resource, improved the probability of adopting to current to be recommended.
Description of drawings
The flow chart of the method for pushing of the recommendation items that Fig. 1 provides for the embodiment of the present invention;
The flow chart that obtains the recommendation strategy that Fig. 2 provides for the embodiment of the present invention;
The flow chart that obtains the reception strategy that Fig. 3 provides for the embodiment of the present invention;
The structural representation of the recommendation server that Fig. 4 provides for the embodiment of the present invention;
The Organization Chart of the supplying system of the recommendation items of the example that Fig. 5 provides for the embodiment of the present invention;
The structural representation of the recommendation server in the example that Fig. 6 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the embodiment of method for pushing, system and the recommendation server of the recommendation items that the embodiment of the present invention is provided is described in detail.
The method for pushing of a kind of recommendation items that the embodiment of the present invention provides, as shown in Figure 1, idiographic flow comprises the following steps:
S101, when the operation of determining the active user triggers the recommendation event, obtain active user's buddy list according to active user's sign;
S102, according to the active user to the reception strategy of each targeted customer in current to be recommended recommendation strategy and buddy list to current to be recommended, produce the candidate target user list;
S103, the candidate target user list is presented to the active user, receive the list of targeted subscribers that the active user determines and returns according to the candidate target user list;
S104, the confirmation that sends according to the active user send the instruction of recommending, and each targeted customer pushes current to be recommended in the list of targeted subscribers.
The below is described in detail the specific implementation of above steps.
In above-mentioned steps S101, the operation that the active user triggers the recommendation event can include but not limited to following several event: (1) active user completes the payment of online order; (2) active user completes the download to setting software; (3) active user completes set information is made comments; (4) active user selects the friend of Information Sharing to oneself.When completing above-mentioned event, the active user can trigger the recommendation event, system can obtain according to active user's sign active user's buddy list, in the specific implementation, system can import active user's buddy list from social networks, outside social website, instant message software or e-mail address are thin, do not limit the source of buddy list at this.
Preferably, in above-mentioned steps S102, the detailed process that produces the candidate target user list can comprise the following steps:
At first, according to the recommendation strategy of active user to current to be recommended, each targeted customer in buddy list is screened, obtain meeting the candidate target user list of recommending strategy;
Then, according to the reception strategy of each targeted customer in buddy list to current to be recommended, the targeted customer who meets in the candidate target user list of recommending strategy is screened, obtain meeting the candidate target user list that receives strategy.
The candidate target user list that obtains by above-mentioned twice screening had both met active user's recommendation strategy, the reception strategy that has met again the targeted customer, like this, for the active user who sends recommendation items, can avoid the active user that recommendation items is pushed to the there to the uninterested targeted customer of this recommendation items, saved the recommendation resource, for pushed targeted customer, a large amount of uninterested recommendation items have been avoided receiving, save the recommendation resource, improved the probability of adopting to current to be recommended.
Particularly, the recommendation strategy of the user in the said method that provides of the embodiment of the present invention and receive obtaining of strategy can be by following step realization:
For the recommendation strategy that obtains the user, as shown in Figure 2, can comprise the following steps:
S201, for each user who reaches the standard grade, obtain the user to each current recommendation strategy that arranges to be recommended;
S202, according to the reception strategy of each targeted customer in user's recommendation strategy and user's buddy list to current to be recommended, the targeted customer in the prediction buddy list adopts ratio to current item to be recommended; For example: how many good friends the recommendation of predictive user can be received by, and the possibility of being adopted by these good friends;
S203, will predict the outcome and present to the user;
S204, when receiving recommendation strategy that the user sends and confirm instruction, preserve the recommendation strategy that the user arranges;
S205, when receiving the recommendation policy update instruction that the user sends, preserve the recommendation strategy that the user upgrades.
Similarly, similar for the reception strategy that obtains the user and the above-mentioned user's of obtaining recommendation strategic process, as shown in Figure 3, can realize by following step:
S301, for each user who reaches the standard grade, obtain the user to each current reception strategy that arranges to be recommended;
S302, according to the recommendation strategy of each targeted customer in user's reception strategy and user's buddy list to current to be recommended, predict the recommended amount that this user can receive over a period to come;
S303, will predict the outcome and present to the user;
S304, when receiving reception strategy that the user sends and confirm instruction, preserve the reception strategy that the user arranges;
S305, when receiving the reception policy update instruction that the user sends, preserve the reception strategy that the user upgrades.
In the specific implementation, obtain the step S201 of user's recommendation strategy～S205 and obtain the step S301 of user's reception strategy～S305 and can carry out simultaneously also can carrying out respectively, not doing restriction at this.
Preferably, in the step S103 of the said method that the embodiment of the present invention provides, receive that the active user determines according to the candidate target user list and the list of targeted subscribers returned before, when getting the active user and revise it and recommend strategy, will upgrade the candidate target user list, and the candidate target user list after upgrading is presented to the active user.
Particularly, in the said method that the embodiment of the present invention provides, the recommendation strategy of use or reception strategy can be one of following strategy:
The combined strategy of black and white lists strategy, circle of influence strategy, preference strategy and circle of influence strategy and preference strategy; Wherein, the circle of influence strategy is for adopting to active user's recommendation the strategy that situation arranges to the recommendation number of times of each targeted customer in its buddy list and each targeted customer according to the active user.
The below is described in detail each strategy.
The black and white lists strategy: buddy list is divided into two lists, and all good friends in white list are as the targeted customer, and all good friends in blacklist are with disallowable.
The circle of influence strategy: the substrategy by three basic consists of, can connect by logical “and” or logical "or" between substrategy, to reach different filter effects, particularly, substrategy is: 1) active user sends new recommendation items to the good friend who adopted its recommendation items within the time interval; 2) active user sends to accumulative total within the time interval and recommends number of times to send new recommendation items less than the good friend of k; 3) active user sends new recommendation items to receiving recently its n recommendation items and having adopted one of them individual good friend.
For example: supposition only adopts 1) or 2) strategy, the time interval was set as for 1 week, the recommendation number of times upper limit k that accumulative total sends is set as 7, so, if in the week, user A not yet reaches 7 to the recommendation transmission times of good friend B, perhaps surpassed 7 but good friend B once adopted wherein a certain, good friend B will be as the targeted customer so, otherwise good friend B is removed from the targeted customer.
Utilize the circle of influence strategy, can avoid the active user that a large amount of items to be recommended is sent to the good friend there that those continue not pay close attention to its recommendation.Simultaneously, can also realize souning out the good friend to the degree of concern of its recommendation by sending on a small quantity.
The preference strategy: by a threshold value is set, will be to the preference of current to be recommended greater than the good friend of threshold value as the targeted customer, because the computational methods of preference belong to prior art, do not elaborate at this.
In specific embodiment, the arranging of threshold value can be carried out normalization according to certain principle with good friend's preference, and (for example linear normalization is to [0,1] interval), with the good friend for current average preference's degree to be recommended as threshold value, a concrete numerical value perhaps is set as required, the intimate filtration that for example, all can be shown preference to current item to be recommended take 0 as threshold value out.
Preferably, step S104 in the method that the embodiment of the present invention provides sends according to the confirmation that the active user sends the instruction of recommending, each targeted customer pushes current to be recommended in the list of targeted subscribers, in the specific implementation, add a unique sign in can connecting the access of current to be recommended that generates, the recommendation items that can identify user's click by this sign is that concrete which user sends, like this,, prepare against and provide reference to the subsequent user Provisioning Policy for the click of recommendation results and purchase conversion situation by recording user.
Based on same inventive concept, the embodiment of the present invention also provides the supplying system of a kind of recommendation server and recommendation items, because the principle that this server and system deal with problems is similar to the method for pushing of aforementioned a kind of recommendation items, therefore the enforcement of this server and system can referring to the enforcement of method, repeat part and repeat no more.
A kind of recommendation server that the embodiment of the present invention provides as shown in Figure 4, comprising:
Recommending module 404, the confirmation that is used for sending according to the active user sends the instruction of recommending, and each targeted customer pushes current to be recommended in the list of targeted subscribers.
Further, the above-mentioned server that the embodiment of the present invention provides as shown in Figure 4, can also comprise: strategy is preserved module 405, is used for for each user who reaches the standard grade, and obtains the user to each current to be recommended recommendation strategy that arranges and receives strategy; According to the reception strategy of each targeted customer in user's recommendation strategy and user's buddy list to current to be recommended, the targeted customer in the prediction buddy list adopts ratio to current item to be recommended; Or according to the recommendation strategy of each targeted customer in user's reception strategy and user's buddy list, the recommended amount that predictive user can be received over a period to come; To predict the outcome and present to the user; When receiving the recommendation strategy that the user sends or receive strategy when confirming instruction, preserve the recommendation strategy that the user arranges or receive strategy, when receiving the recommendation strategy that the user sends or receiving the policy update instruction, preserve the recommendation strategy that the user upgrades or receive strategy.
Further, computing module 402 in the above-mentioned server that the embodiment of the present invention provides, specifically be used for the recommendation strategy to current to be recommended according to the active user, each targeted customer in buddy list is screened, obtain meeting the candidate target user list of recommending strategy; According to the reception strategy of each targeted customer in buddy list to current to be recommended, the targeted customer who meets in the candidate target user list of recommending strategy is screened, obtain meeting the candidate target user list that receives strategy.
Further, confirmation module 403 in the above-mentioned server that the embodiment of the present invention provides, also for before the list of targeted subscribers of confirming according to the candidate target user list the reception active user and returning, revise when recommending strategy when getting the active user, upgrade the candidate target user list, and the candidate target user list after upgrading is presented to the active user.
The embodiment of the present invention also provides a kind of supplying system of recommendation items, comprising: recommendation server, service server and information promulgating platform server;
Recommendation server is used for obtaining active user's buddy list according to active user's sign when the operation of determining the active user triggers the recommendation event; To the reception strategy of each targeted customer in current to be recommended recommendation strategy and buddy list to current to be recommended, produce the candidate target user list according to the active user; The candidate target user list is presented to the active user, receive the list of targeted subscribers that the active user determines and returns according to the candidate target user list; The confirmation that sends according to the active user sends the instruction of recommending, and each targeted customer pushes current to be recommended in the list of targeted subscribers;
Service server is for friend information and recommendation items information that the user is provided;
The information promulgating platform server is used for current to be recommended the receiving platform that is published to the targeted customer that recommendation server is pushed.
Further, can also comprise in the said system that the embodiment of the present invention provides: external data source;
Recommendation server is also for obtain user's friend information from external data source.
Below by instantiation, the said system that the embodiment of the present invention provides is described, as shown in Figure 5, comprise recommendation server, service server, information promulgating platform server and external data source (information promulgating platform server and external data source are not shown).
Wherein, the concrete structure of recommendation server can comprise as shown in Figure 6 with lower module: recommend trigger control module 601, recommendation target computing module 602, social networks administration module 603, preference computing module 604, recommend strategic control module 605 and recommend sending module 606.Wherein, recommend trigger control module 601, social administration module 603, recommend strategic control module 605, recommend sending module 606 may with system in service server (for example e-commerce platform), external data source (for example the open good friend of social network sites obtains Web service), information promulgating platform server (for example microblogging distribution platform) generation information transmit.
Particularly, recommend trigger control module 601, be used for receiving the recommendation trigger event from service server, and to recommending target computing module 602 to submit the request of propelling movement to.Recommend trigger event to be determined by the service needed of system, typical event includes but not limited to: 1) user has completed the payment of online order; 2) user has downloaded certain software in using the store; 3) user has delivered comment to certain information; 4) user initiatively selects the friend of Information Sharing to oneself.
Recommend target computing module 602, be used for receiving the propelling movement request from recommending trigger control module 601, this propelling movement request comprises the id of an active user id, current item to be recommended, recommend target computing module 602 and to recommend strategic control module 605 to carry out alternately according to these two signs and social networks administration module 603, preference computing module 604, determine to be fit to the transmission targeted customer colony of active user and current item to be recommended.
Particularly, recommend target computing module 602 to comprise: social networks request module 6021, strategy request module 6022, preference request module 6023, historical behavior request module 6024 and policy filtering module 6025.
when concrete the application, recommend target computing module 602 to call successively social networks request module 6021 and strategy request module 6022, and whether call preference request module 6023 and historical behavior request module 6024 according to the strategy decision that gets, to obtain required user's buddy list, user's historical behavior and the good friend information such as preference to current item to be recommended, afterwards, recommend 6025 pairs of user's buddy lists of target computing module 602 regulative strategy filtering module to carry out policy filtering, produce final candidate target user list, offer and recommend sending module 606 to carry out user's confirmation, and complete transmission.
Social networks administration module 603 is used for safeguarding user's buddy list, after receiving the request of recommending target computing module 602, returns to its buddy list according to active user id.
Particularly, social networks administration module 603 comprises: inner good friend's administration module 6031 and outside good friend's administration module 6032, be respectively used to leading subscriber the good friend of internal system and the good friend of system outside, wherein, inner good friend refers to that the user utilizes the friend making function that internal system provides that other users are directly added as a friend; Outside good friend refers to good friend's relation that the user imports from the data sources such as mail address book, social network sites and chat tool.When concrete the application, outside good friend's administration module 6032 may comprise that also one is invited the invitation that external user becomes internal user to confirm function, perhaps, the API that also can utilize open platforms such as Google Open Social, Facebook Friend Connect to provide, direct and external data source carries out alternately.
Particularly, preference computing module 604 comprises: content-based preference computing module 6041, based on the preference computing module 6042 of collaborative filtering and based on the preference computing module 6043 of mixed strategy.The text feature of the text feature of the historical access object of content-based preference computing module 6041 Users and item to be recommended calculates the preference that this user treats recommendation items.Generally speaking, the algorithm that adopts of this module all needs user's preference and item to be recommended are expressed as property vector.Based on 6042 similitudes by tolerance user history access record of preference computing module of collaborative filtering, according to other users' similar to the user Visitor Logs, calculate this user to the preference of current item to be recommended.Combine content-based preference computing module 6041 and based on the characteristics of the preference computing module 6042 of collaborative filtering based on the preference computing module 6043 of mixed strategy, to promote comprehensive that preference calculates.In the specific implementation, the preference request that can send according to preference request module 6023 (comprising sign and the buddy list of current to be recommended), the preference of targeted customer in the calculating buddy list to current item to be recommended, and return to recommendation target computing module 602 for follow-up policy filtering calculating with buddy list.
Recommend strategic control module 605, corresponding recommendation strategy is set and receives strategy according to the needs of oneself for the user.These strategies include but are not limited to circle of influence strategy, black and white lists strategy, preference strategy etc.
Particularly, recommend strategic control module 605 to comprise: black and white lists policy module 6051, circle of influence policy module 6052 and preference policy module 6053, the user can arrange by above-mentioned three modules the recommendation strategy of three types: black and white lists strategy, circle of influence strategy, preference strategy.
Recommend sending module 606, be used for according to the output of recommending target computing module 602, recommendation items being sent to corresponding targeted customer colony.This module comprises a process of being edited and being confirmed by the active user before sending recommendation items.
Particularly, recommend sending module 606 to comprise: inner sending module 6061 and outside sending module 6062.Inner sending module 6061 is used for recommendation items is presented in intrasystem displayed page, after recommended targeted customer's login system, will see in respective page the content of recommendation items.Outside sending module 6062 is sent to recommendation items the displaying position of external system for the interface that utilizes external system to provide, and wherein, typical external system approach comprises the Web service interface that Email, microblogging and social network sites provide etc.Further, for the accept situation of track user for recommendation items, recommend sending module 606 will add a uniqueness sign in the access links that generates, that can identify that user x clicks by this sign is recommendation items rather than the user z of user y.Operation system physical record user is to the click of recommendation items/purchase conversion situation, and by the interface of recommending strategic control module 605, these data offered native system and use.At last, for the needs of respecting privacy of user, recommend sending module all should provide the user to confirm function in any embodiment, and allow the user that final list of targeted subscribers is manually adjusted.
The supplying system of the above-mentioned recommendation items that the embodiment of the present invention provides just illustrates, and the supplying system of recommendation items also comprises other forms in the specific implementation, does not elaborate at this.
Through the above description of the embodiments, those skilled in the art can be well understood to the embodiment of the present invention and can realize by hardware, also can realize by the mode that software adds necessary general hardware platform.Based on such understanding, the technical scheme of the embodiment of the present invention can embody with the form of software product, it (can be CD-ROM that this software product can be stored in a non-volatile memory medium, USB flash disk, portable hard drive etc.) in, comprise some instructions with so that computer equipment (can be personal computer, server, the perhaps network equipment etc.) carry out the described method of each embodiment of the present invention.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the module in accompanying drawing or flow process might not be that enforcement the present invention is necessary.
It will be appreciated by those skilled in the art that the module in the device in embodiment can be distributed in the device of embodiment according to the embodiment description, also can carry out respective change and be arranged in the one or more devices that are different from the present embodiment.The module of above-described embodiment can be merged into a module, also can further split into a plurality of submodules.
The invention described above embodiment sequence number does not represent the quality of embodiment just to description.
The method for pushing of a kind of recommendation items that the embodiment of the present invention provides, system and recommendation server, when the operation of determining the active user triggers the recommendation event, to the reception strategy of each targeted customer in current to be recommended recommendation strategy and active user's buddy list to current to be recommended, produce the candidate target user list according to the active user; Receive that the active user determines according to the candidate target user list and the list of targeted subscribers returned after, each targeted customer recommends current to be recommended in the list of targeted subscribers.the method for pushing of the recommendation items that the embodiment of the present invention provides is when the list of targeted subscribers that produces current to be recommended, comprehensive reference between active user and targeted customer the recommendation strategy and receive strategy, filter out and be fit to the targeted customer of current to be recommended, and finally confirm each targeted customer in list of targeted subscribers via the active user, for the active user who sends recommendation items, can reduce to adopting the low targeted customer of probability and push recommendation items, saved the recommendation resource, and on the basis of the success rate that the raising recommendation items is adopted, increased the flexibility that the active user pushes, for pushed targeted customer, avoided receiving a large amount of uninterested recommendation items, saved the recommendation resource, improved the probability of adopting to current to be recommended.
Obviously, those skilled in the art can carry out various changes and modification and not break away from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of claim of the present invention and equivalent technologies thereof, the present invention also is intended to comprise these changes and modification interior.
Claims (11)
1. the method for pushing of a recommendation items, is characterized in that, comprising:
When the operation of determining the active user triggers the recommendation event, obtain described active user's buddy list according to described active user's sign;
To the reception strategy of each targeted customer in current to be recommended recommendation strategy and described buddy list to current to be recommended, produce the candidate target user list according to described active user;
Described candidate target user list is presented to described active user, receive the list of targeted subscribers that described active user determines and returns according to described candidate target user list;
The confirmation that sends according to described active user sends the instruction of recommending, and each targeted customer pushes described current to be recommended in the described list of targeted subscribers.
2. the method for claim 1, is characterized in that, before the operation of determining the active user triggers the recommendation event, also comprises:
For each user who reaches the standard grade, obtain the user to each current to be recommended recommendation strategy that arranges and receive strategy;
According to the reception strategy of each targeted customer in described user's recommendation strategy and described user's buddy list to current to be recommended, predict that the targeted customer in described buddy list adopts ratio to current to be recommended; Or according to the recommendation strategy of each targeted customer in described user's reception strategy and described user's buddy list, predict the recommended amount that described user can receive over a period to come;
To predict the outcome and present to described user; When the recommendation strategy that receives described user's transmission or reception strategy confirmation instruction, preserve recommendation strategy or reception strategy that described user arranges, when the recommendation strategy that receives described user's transmission or the instruction of reception policy update, preserve recommendation strategy or reception strategy that described user upgrades.
3. the method for claim 1, is characterized in that, to the reception strategy of each targeted customer in current to be recommended recommendation strategy and described buddy list to current to be recommended, produces the candidate target user list according to described active user, specifically comprises:
According to the recommendation strategy of described active user to current to be recommended, each targeted customer in described buddy list is screened, obtain meeting the described candidate target user list of recommending strategy;
According to the reception strategy of each targeted customer in described buddy list to described current to be recommended, the targeted customer in the candidate target user list that meets described recommendation strategy is screened, obtain meeting the described candidate target user list that receives strategy.
4. method as claimed in claim 3, is characterized in that, described recommendation strategy or described reception strategy are one of following strategy:
The combined strategy of black and white lists strategy, circle of influence strategy, preference strategy and circle of influence strategy and preference strategy; Wherein, described circle of influence strategy is for adopting to described active user's recommendation the strategy that situation arranges to the recommendation number of times of each targeted customer in its buddy list and each targeted customer according to described active user.
5. as the described method of claim 1-4 any one, it is characterized in that, receive that described active user determines according to described candidate target user list and the list of targeted subscribers returned before, also comprise:
When getting described active user and revise described recommendation strategy, upgrade the candidate target user list, and the candidate target user list after upgrading is presented to described active user.
6. a recommendation server, is characterized in that, comprising:
Acquisition module is used for obtaining described active user's buddy list according to described active user's sign when the operation of determining the active user triggers the recommendation event;
Computing module is used for according to described active user the recommendation strategy of current to be recommended and each targeted customer of described buddy list reception strategy to current to be recommended is produced the candidate target user list;
Confirm module, be used for described candidate target user list is presented to described active user, receive the list of targeted subscribers that described active user determines and returns according to described candidate target user list;
Recommending module, the confirmation that is used for sending according to described active user sends the instruction of recommending, and each targeted customer pushes described current to be recommended in the described list of targeted subscribers.
7. server as claimed in claim 6, is characterized in that, also comprises:
Strategy is preserved module, is used for for each user who reaches the standard grade, and obtains the user to each current to be recommended recommendation strategy that arranges and receives strategy; According to the reception strategy of each targeted customer in described user's recommendation strategy and described user's buddy list to current to be recommended, predict that the targeted customer in described buddy list adopts ratio to current to be recommended; Or according to the recommendation strategy of each targeted customer in described user's reception strategy and described user's buddy list, predict the recommended amount that described user can receive over a period to come; To predict the outcome and present to described user; When the recommendation strategy that receives described user's transmission or reception strategy confirmation instruction, preserve recommendation strategy or reception strategy that described user arranges, when the recommendation strategy that receives described user's transmission or the instruction of reception policy update, preserve recommendation strategy or reception strategy that described user upgrades.
8. server as claimed in claim 6, it is characterized in that described computing module specifically is used for the recommendation strategy to current to be recommended according to described active user, each targeted customer in described buddy list is screened, obtain meeting the described candidate target user list of recommending strategy; According to the reception strategy of each targeted customer in described buddy list to described current to be recommended, the targeted customer in the candidate target user list that meets described recommendation strategy is screened, obtain meeting the described candidate target user list that receives strategy.
9. as the described server of claim 6-8 any one, it is characterized in that, described confirmation module, also for before the list of targeted subscribers of confirming according to described candidate target user list the described active user of reception and returning, when getting described active user and revise described recommendation strategy, upgrade the candidate target user list, and the candidate target user list after upgrading is presented to described active user.
10. the supplying system of a recommendation items, is characterized in that, comprising: recommendation server, service server and information promulgating platform server;
Described recommendation server is used for obtaining described active user's buddy list according to described active user's sign when the operation of determining the active user triggers the recommendation event; To the reception strategy of each targeted customer in current to be recommended recommendation strategy and described buddy list to current to be recommended, produce the candidate target user list according to described active user; Described candidate target user list is presented to described active user, receive the list of targeted subscribers that described active user determines and returns according to described candidate target user list; The confirmation that sends according to described active user sends the instruction of recommending, and each targeted customer pushes described current to be recommended in the described list of targeted subscribers;
Described service server is for friend information and recommendation items information that the user is provided;
Described information promulgating platform server is used for current to be recommended the receiving platform that is published to the targeted customer that described recommendation server is pushed.
11. system as claimed in claim 10 is characterized in that, also comprises: external data source;
Described recommendation server is also for obtain user's friend information from described external data source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110397617.8A CN103138954B (en) | 2011-12-02 | 2011-12-02 | A kind of method for pushing of recommendation items, system and recommendation server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110397617.8A CN103138954B (en) | 2011-12-02 | 2011-12-02 | A kind of method for pushing of recommendation items, system and recommendation server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103138954A true CN103138954A (en) | 2013-06-05 |
| CN103138954B CN103138954B (en) | 2015-11-04 |
Family
ID=48498304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110397617.8A Active CN103138954B (en) | 2011-12-02 | 2011-12-02 | A kind of method for pushing of recommendation items, system and recommendation server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103138954B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103312816A (en) * | 2013-07-01 | 2013-09-18 | 青岛海信传媒网络技术有限公司 | Method and equipment for message distribution |
| CN103561067A (en) * | 2013-10-24 | 2014-02-05 | 青岛英网资讯股份有限公司 | Invitation method based on cellphone applications |
| CN104144196A (en) * | 2013-07-05 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Webpage information sharing method, device and server |
| CN104281599A (en) * | 2013-07-02 | 2015-01-14 | 北京千橡网景科技发展有限公司 | Method and device for recommending information to user in social network |
| WO2015085768A1 (en) * | 2013-12-09 | 2015-06-18 | Tencent Technology (Shenzhen) Company Limited | Systems and methods for message pushing |
| CN104765738A (en) * | 2014-01-03 | 2015-07-08 | 腾讯科技（北京）有限公司 | Method and system for controlling counter of user generated contents |
| CN105677881A (en) * | 2016-01-12 | 2016-06-15 | 腾讯科技（深圳）有限公司 | Information recommendation method and device and server |
| CN105786813A (en) * | 2014-12-17 | 2016-07-20 | 北京邮电大学 | Method and device for sending task information |
| CN106789564A (en) * | 2016-12-08 | 2017-05-31 | 广州爱九游信息技术有限公司 | Social invitation system, unit and method |
| WO2017101305A1 (en) * | 2015-12-15 | 2017-06-22 | 乐视控股（北京）有限公司 | Method and apparatus for displaying user manual of smartphone |
| CN107103490A (en) * | 2017-04-11 | 2017-08-29 | 华为机器有限公司 | A kind of data processing method, the webserver and terminal |
| CN107193984A (en) * | 2017-05-25 | 2017-09-22 | 上海喆之信息科技有限公司 | A kind of high-quality user's commending system |
| CN107249023A (en) * | 2017-05-27 | 2017-10-13 | 维沃移动通信有限公司 | The processing method and processing device that file is sent |
| CN107292646A (en) * | 2016-04-01 | 2017-10-24 | 中国移动通信集团河北有限公司 | A kind of method and apparatus of generation business |
| CN107766441A (en) * | 2017-09-21 | 2018-03-06 | 北京百度网讯科技有限公司 | Resource updates based reminding method, device and storage medium based on artificial intelligence |
| CN107835120A (en) * | 2017-11-03 | 2018-03-23 | 上海掌门科技有限公司 | For providing the method and apparatus to release news of target good friend |
| CN107979624A (en) * | 2016-10-24 | 2018-05-01 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and the client with quick access function |
| 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 |
| CN108737535A (en) * | 2018-05-14 | 2018-11-02 | 平安科技（深圳）有限公司 | A kind of information push method, storage medium and server |
| CN111988642A (en) * | 2019-05-24 | 2020-11-24 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for recommending videos |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090222348A1 (en) * | 2008-03-03 | 2009-09-03 | Victoria Ransom | Method and system for providing online promotions through a social network-based platform |
| 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 |
| CN101916286A (en) * | 2010-08-23 | 2010-12-15 | 宇龙计算机通信科技(深圳)有限公司 | Information recommendation method and system |
| CN102118324A (en) * | 2010-01-06 | 2011-07-06 | 腾讯科技（深圳）有限公司 | Method and system for inviting friend to access related product |
| CN102129639A (en) * | 2011-01-28 | 2011-07-20 | Tcl集团股份有限公司 | Method and system for sharing application procedure |
-
2011
- 2011-12-02 CN CN201110397617.8A patent/CN103138954B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090222348A1 (en) * | 2008-03-03 | 2009-09-03 | Victoria Ransom | Method and system for providing online promotions through a social network-based platform |
| 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 |
| CN102118324A (en) * | 2010-01-06 | 2011-07-06 | 腾讯科技（深圳）有限公司 | Method and system for inviting friend to access related product |
| CN101916286A (en) * | 2010-08-23 | 2010-12-15 | 宇龙计算机通信科技(深圳)有限公司 | Information recommendation method and system |
| CN102129639A (en) * | 2011-01-28 | 2011-07-20 | Tcl集团股份有限公司 | Method and system for sharing application procedure |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103312816B (en) * | 2013-07-01 | 2016-04-27 | 青岛海信传媒网络技术有限公司 | A kind of message distributing method and equipment |
| CN103312816A (en) * | 2013-07-01 | 2013-09-18 | 青岛海信传媒网络技术有限公司 | Method and equipment for message distribution |
| CN104281599A (en) * | 2013-07-02 | 2015-01-14 | 北京千橡网景科技发展有限公司 | Method and device for recommending information to user in social network |
| CN104144196A (en) * | 2013-07-05 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Webpage information sharing method, device and server |
| CN103561067A (en) * | 2013-10-24 | 2014-02-05 | 青岛英网资讯股份有限公司 | Invitation method based on cellphone applications |
| US20150222583A1 (en) * | 2013-12-09 | 2015-08-06 | Tencent Technology (Shenzhen) Company Limited | Systems and Methods for Message Pushing |
| US10104030B2 (en) * | 2013-12-09 | 2018-10-16 | Tencent Technology (Shenzhen) Company Limited | Systems and methods for message pushing |
| WO2015085768A1 (en) * | 2013-12-09 | 2015-06-18 | Tencent Technology (Shenzhen) Company Limited | Systems and methods for message pushing |
| CN104765738A (en) * | 2014-01-03 | 2015-07-08 | 腾讯科技（北京）有限公司 | Method and system for controlling counter of user generated contents |
| CN104765738B (en) * | 2014-01-03 | 2019-03-26 | 腾讯科技（北京）有限公司 | The method and system that the counter of user-generated content is controlled |
| CN105786813A (en) * | 2014-12-17 | 2016-07-20 | 北京邮电大学 | Method and device for sending task information |
| WO2017101305A1 (en) * | 2015-12-15 | 2017-06-22 | 乐视控股（北京）有限公司 | Method and apparatus for displaying user manual of smartphone |
| CN105677881A (en) * | 2016-01-12 | 2016-06-15 | 腾讯科技（深圳）有限公司 | Information recommendation method and device and server |
| CN107292646A (en) * | 2016-04-01 | 2017-10-24 | 中国移动通信集团河北有限公司 | A kind of method and apparatus of generation business |
| CN107979624A (en) * | 2016-10-24 | 2018-05-01 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and the client with quick access function |
| CN106789564A (en) * | 2016-12-08 | 2017-05-31 | 广州爱九游信息技术有限公司 | Social invitation system, unit and method |
| CN107103490A (en) * | 2017-04-11 | 2017-08-29 | 华为机器有限公司 | A kind of data processing method, the webserver and terminal |
| CN107193984A (en) * | 2017-05-25 | 2017-09-22 | 上海喆之信息科技有限公司 | A kind of high-quality user's commending system |
| CN107249023A (en) * | 2017-05-27 | 2017-10-13 | 维沃移动通信有限公司 | The processing method and processing device that file is sent |
| CN107766441A (en) * | 2017-09-21 | 2018-03-06 | 北京百度网讯科技有限公司 | Resource updates based reminding method, device and storage medium based on artificial intelligence |
| 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 |
| CN107835120A (en) * | 2017-11-03 | 2018-03-23 | 上海掌门科技有限公司 | For providing the method and apparatus to release news of target good friend |
| CN108737535A (en) * | 2018-05-14 | 2018-11-02 | 平安科技（深圳）有限公司 | A kind of information push method, storage medium and server |
| CN111988642A (en) * | 2019-05-24 | 2020-11-24 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for recommending videos |
| CN111988642B (en) * | 2019-05-24 | 2022-05-24 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for recommending videos |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103138954B (en) | 2015-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103138954B (en) | A kind of method for pushing of recommendation items, system and recommendation server | |
| US9647968B2 (en) | Systems and methods for invoking chatbots in a channel based communication system | |
| US9641470B2 (en) | Channel based communication and transaction system | |
| JP6703003B2 (en) | Techniques for automatic determination of routine responses | |
| US10868789B2 (en) | Social matching | |
| WO2014062762A1 (en) | Propagating information through networks | |
| CN106789598B (en) | Social relation chain-based public number message pushing method, device and system | |
| US20190034974A1 (en) | Social media profile monetization using viewer engagement tools | |
| US20160292734A1 (en) | Systems and methods for advertising into online conversation context based on real time conversation content | |
| AU2014374421B2 (en) | Object recommendation based upon similarity distances | |
| US9503410B2 (en) | Sharing of activity metadata via messaging systems | |
| US20140229541A1 (en) | Method and system for content management of social networking data | |
| US20200034914A1 (en) | System and method for automated gift determination and delivery | |
| US9871833B2 (en) | Adjusting the display of social media updates to varying degrees of richness based on environmental conditions and importance of the update | |
| CN112446736A (en) | Click through rate CTR prediction method and device | |
| US11188846B1 (en) | Determining a sequential order of types of events based on user actions associated with a third party system | |
| CN111221449A (en) | Method and device for establishing and displaying sharing type activity and electronic equipment | |
| KR20170125593A (en) | Method for sharing schedule | |
| US10924568B1 (en) | Machine learning system for networking | |
| US10007737B2 (en) | Tailored interpersonal communication platform (ICP) management | |
| US20220358539A1 (en) | Systems and methods for managing advertisements in social networks | |
| US11017438B2 (en) | Method and systems for automatic management of sponsorship of a user's contact information | |
| CN111222840A (en) | Crowd funding system, method and device, computer equipment and storage medium | |
| US20190333084A1 (en) | Continual audience synchronization | |
| Dyagilev et al. | On information propagation in mobile call networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |