CN105872837A - User recommendation method and device - Google Patents

User recommendation method and device Download PDF

Info

Publication number
CN105872837A
CN105872837A CN201610256042.0A CN201610256042A CN105872837A CN 105872837 A CN105872837 A CN 105872837A CN 201610256042 A CN201610256042 A CN 201610256042A CN 105872837 A CN105872837 A CN 105872837A
Authority
CN
China
Prior art keywords
user
spectators
spectators user
appointment
direct broadcasting
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
Application number
CN201610256042.0A
Other languages
Chinese (zh)
Other versions
CN105872837B (en
Inventor
姚俊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Kugou Computer Technology Co Ltd
Original Assignee
Guangzhou Kugou Computer Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Kugou Computer Technology Co Ltd filed Critical Guangzhou Kugou Computer Technology Co Ltd
Priority to CN201610256042.0A priority Critical patent/CN105872837B/en
Publication of CN105872837A publication Critical patent/CN105872837A/en
Application granted granted Critical
Publication of CN105872837B publication Critical patent/CN105872837B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/478Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/252Processing of multiple end-users' preferences to derive collaborative data
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866Management of end-user data
    • H04N21/25891Management of end-user data being end-user preferences

Abstract

The invention discloses a user recommendation method and device, and belongs to the technical field of networks. The method comprises the steps that the staying durations of multiple audience users in a live broadcast room are counted; mark information is added for each audience user on the basis of the staying duration of each audience user in multiple audience users, wherein the mark information is used for indicating the favorite degree of the audience user to a live broadcast user corresponding to the live broadcast room; at least two assigned audience users with the same mark information are acquired from the audience users; at least two assigned audience users are mutually recommended. Due to the fact that the different mark information reflects the favorite degrees to the live broadcast user, the hobbies and interests of the audience users are embodied; by mutually recommending the different audience users with the same mark information, it is guaranteed that the two parties subjected to user recommendation have the similar hobbies and interests, and the user recommendation accuracy rate and the good friend adding success rate are increased.

Description

User recommends method and device
Technical field
The present invention relates to networking technology area, recommend method and device particularly to a kind of user.
Background technology
Along with the development of network technology, network direct broadcasting platform arises at the historic moment.Network direct broadcasting platform comprises multiple direct broadcasting room, The corresponding net cast interface of each direct broadcasting room, net cast interface is for playing the live video of corresponding live user.See Many users can watch live video in video playback interface.Additionally, for the different user of network direct broadcasting platform, remove Outside viewing live video, it is also possible to add as a friend mutually or add good friend by modes such as user's recommendations, thus carry out letter Breath is mutual.
Under normal circumstances, user recommends method to may include that in multiple good friend users of user, and user can be by arbitrary Good friend user, it is recommended that to other good friend users so that the good friend user of user can be mutually added as good friend.Such as, user At least include user A and user B in good friend user, then user A can be recommended user B by user, that is to say, by user A's Recommendation message is sent to user B by server so that user B can choose whether to add according to the recommendation message of user A and use Family A is good friend.
During realizing the present invention, inventor finds that prior art at least there is problems in that
Owing to carrying out user's recommendation by the way of friend recommendation, it is difficult to ensure that receive the user of recommendation message with recommended User there is similar hobby so that user recommend accuracy rate low, the success rate being successfully added to good friend is low.
Summary of the invention
In order to solve problem of the prior art, embodiments provide a kind of user and recommend method and device.Described Technical scheme is as follows:
On the one hand, it is provided that a kind of user recommends method, described method to include:
Add up multiple spectators user stay time at direct broadcasting room;
Stay time based on spectators user each in the plurality of spectators user, adds mark for described each spectators user Note information, described label information is for indicating the favorable rating of spectators user live user corresponding to described direct broadcasting room;
From the plurality of spectators user, obtain the identical at least two of label information and specify spectators user;
Spectators user is specified to recommend mutually described at least two.
Alternatively, the multiple spectators user of described statistics includes in the stay time of direct broadcasting room:
At the appointed time in section, obtain described each spectators user and enter the first moment of described direct broadcasting room and leave described Second moment of direct broadcasting room;
Time difference between the first moment and the second moment that calculate described each spectators user;
According to described appointment time period and the time difference of described each spectators user, obtain described each spectators user in institute State the average duration that direct broadcasting room stops.
Alternatively, described stay time based on each spectators user, add label information for described each spectators user Including:
From multiple preset threshold range, determine the predetermined threshold value model at the stay time place of described each spectators user Enclose;
For stay time, the spectators user in same preset threshold range adds identical label information, for stay time Spectators user in different preset threshold range adds different label informations.
Alternatively, described to described at least two specify spectators user recommend mutually to include:
Each appointment spectators user in spectators user is specified for described at least two, generates first user recommendation message, Described first user recommendation message is for specifying other appointment spectators users in spectators user to recommend institute to described at least two State appointment spectators user;
By described first user recommendation message, it is sent to described at least two and specifies other appointment spectators in spectators user User.
Alternatively, described to described at least two specify spectators user recommend mutually to include:
Each appointment spectators user in spectators user is specified for described at least two, generates second user's recommendation message, Described second user's recommendation message for recommend that described at least two specifies in spectators user to the described spectators user of appointment its He specifies spectators user;
Specify each appointment spectators user in spectators user to send described second user to described at least two to recommend to disappear Breath.
On the other hand, it is provided that a kind of user's recommendation apparatus, described device includes:
Statistical module, for adding up multiple spectators user stay time at direct broadcasting room;
Add module, for stay time based on spectators user each in the plurality of spectators user, for described each Spectators user adds label information, and described label information is for indicating the happiness of spectators user live user corresponding to described direct broadcasting room Love degree;
Acquisition module, for from the plurality of spectators user, obtains the identical at least two of label information and specifies spectators User;
Recommending module, for specifying spectators user to recommend mutually described at least two.
Alternatively, described statistical module at the appointed time section, obtain described each spectators user enter described directly The first moment between broadcasting and the second moment leaving described direct broadcasting room;Calculate first moment and second of described each spectators user Time difference between moment;According to described appointment time period and the time difference of described each spectators user, obtain described each sight The average duration that many users stop at described direct broadcasting room.
Alternatively, described interpolation module, for from multiple preset threshold range, determines stopping of described each spectators user Stay the preset threshold range at duration place;For stay time, the spectators user in same preset threshold range adds identical mark Note information, for stay time, the spectators user in different preset threshold range adds different label informations.
Alternatively, described recommending module is for specifying each appointment spectators in spectators user to use for described at least two Family, generates first user recommendation message, and described first user recommendation message is for specifying in spectators user to described at least two Other specify spectators users recommend described appointment spectators user;By described first user recommendation message, be sent to described at least Two other appointment spectators users specified in spectators user.
Alternatively, described recommending module is for specifying each appointment spectators in spectators user to use for described at least two Family, generates second user's recommendation message, described second user's recommendation message for described appointment spectators user recommend described in extremely Few two other appointment spectators users specified in spectators user;The each appointment in spectators user is specified to described at least two Spectators user sends described second user's recommendation message.
The technical scheme that the embodiment of the present invention provides has the benefit that
Owing to different label informations reflects the spectators user's different favorable ratings to live user, and then embody sight The hobby of many users, by according to spectators user in the stay time of direct broadcasting room, add different for different spectators users Label information, and the different spectators users with same tag information are recommended mutually, it is ensured that the both sides that user recommends There is similar hobby, improve the accuracy rate that user recommends and the success rate adding good friend.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, in embodiment being described below required for make Accompanying drawing be briefly described, it should be apparent that, below describe in accompanying drawing be only some embodiments of the present invention, for From the point of view of those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other according to these accompanying drawings Accompanying drawing.
Fig. 1 is a kind of system architecture recommended for user that the embodiment of the present invention provides;
Fig. 2 is the flow chart that a kind of user that the embodiment of the present invention provides recommends method;
Fig. 3 is the flow chart that a kind of user that the embodiment of the present invention provides recommends method;
Fig. 4 is the block diagram of a kind of user's recommendation apparatus that the embodiment of the present invention provides;
Fig. 5 is the block diagram of a kind of user's recommendation apparatus that the embodiment of the present invention provides.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to embodiment party of the present invention Formula is described in further detail.
Fig. 1 is a kind of system architecture recommended for user that the embodiment of the present invention provides, and this system architecture includes clothes Business device, the first terminal at spectators user place and second terminal at live user place.Wherein, first terminal and the second terminal can Think mobile terminal such as mobile phone, panel computer, notebook computer etc., it is also possible to for immobile terminal, such as desktop computer etc., The concrete form of first terminal and the second terminal is not especially limited by the embodiment of the present invention.Wherein, server can correspondence many Individual first terminal and the second terminal, the number of first terminal and the second terminal is not construed as limiting by the embodiment of the present invention.
Wherein, server provides direct broadcast service for live user and the spectators user for network direct broadcasting platform, and also For adding up spectators user's stay time in direct broadcasting room, it is that spectators user adds label information according to stay time, and will The different spectators users that label information is identical recommend mutually.First terminal is for playing the straight of live user for spectators user Broadcast video, and receive user's recommendation message of other spectators users that direct broadcast server sends, afterwards, the user that display receives Recommendation message.Second terminal is for generating the live video stream of live user, and is sent by this live video stream to server, by This live video stream is sent to first terminal by server.
Fig. 2 is the flow chart that a kind of user that the embodiment of the present invention provides recommends method, sees Fig. 2, and the method is used for taking In business device, method flow includes:
201, multiple spectators user stay time at direct broadcasting room is added up.
202, stay time based on spectators user each in multiple spectators users, adds labelling letter for each spectators user Breath, label information is for indicating the favorable rating of spectators user live user corresponding to direct broadcasting room.
203, from multiple spectators users, obtain the identical at least two of label information and specify spectators user.
204, spectators user is specified to recommend mutually at least two.
The method that the embodiment of the present invention provides, owing to different label informations reflects spectators user to live user not Same favorable rating, and then embody the hobby of spectators user, by according to spectators user in the stay time of direct broadcasting room, for Different spectators users add different label informations, and the different spectators users with same tag information are pushed away mutually Recommend, it is ensured that the both sides that user recommends have similar hobby, improve the accuracy rate of user's recommendation and add good friend's Success rate.
Alternatively, add up multiple spectators user to include in the stay time of direct broadcasting room:
At the appointed time in section, obtain each spectators user and enter the first moment of direct broadcasting room and leave the second of direct broadcasting room Moment;
Calculate the time difference between first moment of each spectators user and the second moment;
According to specifying time period and the time difference of each spectators user, obtain each spectators user putting down that direct broadcasting room stops All durations.
Alternatively, stay time based on each spectators user, add label information for each spectators user and include:
From multiple preset threshold range, determine the preset threshold range at the stay time place of each spectators user;
For stay time, the spectators user in same preset threshold range adds identical label information, for stay time Spectators user in different preset threshold range adds different label informations.
Alternatively, spectators user is specified to recommend mutually to include at least two:
Each appointment spectators user in spectators user is specified at least two, generates first user recommendation message, first User's recommendation message is for specifying other appointment spectators users in spectators user to recommend to specify spectators user at least two;
By first user recommendation message, it is sent at least two and specifies other appointment spectators users in spectators user.
Alternatively, spectators user is specified to recommend mutually to include at least two:
Each appointment spectators user in spectators user is specified at least two, generates second user's recommendation message, second User's recommendation message is for specifying spectators user to recommend at least two to specify other appointment spectators users in spectators user;
The each appointment spectators user in spectators user is specified to send second user's recommendation message at least two.
Above-mentioned all optional technical schemes, can use and arbitrarily combine the alternative embodiment forming the disclosure, at this no longer Repeat one by one.
Fig. 3 is the flow chart that a kind of user that the embodiment of the present invention provides recommends method, sees Fig. 3, and the method is used for taking In business device, method flow includes:
301, multiple spectators user stay time at direct broadcasting room is added up.
In embodiments of the present invention, have between direct broadcasting room and the live user of network direct broadcasting platform and close one to one System, spectators user can obtain the live video of live user by direct broadcasting room.In order to according to spectators user to live user's Different favorable ratings carry out user's recommendation, and the embodiment of the present invention can add up spectators user's stay time in direct broadcasting room, stops Stay duration the longest expression spectators user the highest to the favorable rating of live user, oppose that the favorable rating of live user is the lowest mutually. Spectators user may be used for embodying the hobby of spectators user to the favorable rating of live user, and such as, spectators user is to shadow Higher depending on the favorable rating of special column main broadcaster, then can illustrate that this spectators user is interested in video display;Or, spectators user couple The favorable rating of opera special column main broadcaster is higher, then can illustrate that this spectators user is interested in opera.
Specifically, adding up multiple spectators user in the process of the stay time of direct broadcasting room can be: at the appointed time in section, Obtain each spectators user enter the first moment of direct broadcasting room and leave the second moment of direct broadcasting room;Calculate each spectators user's Time difference between first moment and the second moment;According to specifying time period and the time difference of each spectators user, obtain each The average duration that spectators user stops at direct broadcasting room.Wherein, it is intended that the time period can by systemic presupposition, this appointment time period time Between unit can be sky, hour etc., this is not especially limited by the embodiment of the present invention.
The process of average duration that statistics spectators user at direct broadcasting room stop is exemplified below: to calculate spectators user A As a example by the stay time of direct broadcasting room, if specifying the time period is 3 days, the time difference being calculated spectators user A is 6 hours, Then spectators user A the stay time of direct broadcasting room be 6 hours divided by 3 days, i.e. 2 hours/day, that is to say, spectators user A is the most every It stops 2 hours in direct broadcasting room.Wherein, " 2 hour/day " expression " 2 hour every day ".
It should be noted that can store one for direct broadcasting room in server to stop timetable, this stop timetable is used The first moment and the second moment in record each spectators user of stop in this direct broadcasting room so that server can be according to directly The stay time of each spectators user added up by the timetable that stops between broadcasting.Specifically, detect that spectators user enters when server During direct broadcasting room, the moment of this entrance is stored to stopping in timetable as the first moment correspondence of this spectators user.Work as service Device detects when spectators user leaves direct broadcasting room, the moment that this is left as the second moment correspondence of this spectators user store to Stop in timetable.
It should be noted that at the appointed time in section, for same direct broadcasting room, spectators user can repeatedly enter or Leave this direct broadcasting room, correspondingly, spectators user's just the first moment of corresponding many groups and the second moment, then calculate this spectators user at this The process of the stay time of direct broadcasting room can be: often organizes the first moment and the second moment according to this, obtains multiple time difference, to this Multiple time differences are sued for peace, and obtain the total time difference of this spectators user;According to when specifying time period and this spectators user total Between poor, obtain the average duration that this spectators user stops at direct broadcasting room, this average duration is this spectators user at this direct broadcasting room Stay time.
The process of average duration that statistics spectators user at direct broadcasting room stop is exemplified below: to calculate spectators user A As a example by the stay time of direct broadcasting room, if specifying the time period is 3 days, it is little that three corresponding for spectators user A time differences are respectively 2 Time, 3 hours, 2.5 hours, then the total time difference that can be calculated spectators user A is 7.5 hours, then spectators user A is live Between stay time be 7.5 hours divided by 3 days, i.e. 2.5 hours/day, that is to say, spectators user A average every day is in direct broadcasting room Stop 2.5 hours.Wherein, " 2.5 hour/day " expression " 2.5 hour every day ".
It should be noted that above-mentioned statistics spectators user is in the mode of the stay time of direct broadcasting room, only make with average duration For adding up as a example by stay time, it is also possible to the total duration stopped in direct broadcasting room according to spectators user or other default systems Calculating method is added up, and the statistical of stay time is not construed as limiting by the embodiment of the present invention.
During it should be noted that the embodiment of the present invention enters direct broadcasting room to spectators user, whether direct broadcasting room is in live shape State is not construed as limiting.Certainly, in order to obtain spectators user's favorable rating to live user more accurately, can detect in terminal To spectators user enter direct broadcasting room time, it is judged that whether be in live state between current live, if direct broadcasting room is in live state, Then this spectators user is entered first moment as this spectators user in the moment of direct broadcasting room.If direct broadcasting room is not at live shape State, then, when terminal detects that direct broadcasting room enters live state, the moment that direct broadcasting room enters live state is used as these spectators First moment at family.
302, from multiple preset threshold range, the predetermined threshold value model at the stay time place of each spectators user is determined Enclose;For stay time, the spectators user in same preset threshold range adds identical label information, for stay time not Different label informations is added with the spectators user in preset threshold range.
Wherein, the numerical intervals of multiple preset threshold range instruction can pre-set according to user's request, and these are many Multiple numerical intervals indicated by individual preset threshold range can form a continuous print numerical intervals.Different preset threshold range For the instruction different favorable ratings to live user, wherein, the numerical value that preset threshold range is comprised is the biggest, represents directly The favorable rating of broadcasting user is the highest.For example, it is assumed that system pre-sets 2 preset threshold range, preset threshold range 1 indicates Numerical intervals be [4,6), preset threshold range 2 instruction numerical intervals be [6,24), then preset threshold range 1 and default threshold Numerical intervals indicated by value scope 2 can form a continuous print numerical intervals [4,24).Wherein, " [" expression includes border Value, ") " represent do not include boundary value.
Wherein, label information is for indicating the favorable rating of spectators user live user corresponding to direct broadcasting room.Have identical The spectators user of label information is close to the favorable rating of live user.This label information can come to use the form of class information Represent.Server can safeguard a label information list for each direct broadcasting room, and this label information list is used for storing access Cross all spectators users and the label information of each spectators user of this direct broadcasting room.Wherein, for direct broadcasting room 1, believe with grade The form of breath represents that label information can be as shown in table 1.
Table 1
Spectators user Label information
Spectators user A Grade 1
Spectators user B Grade 2
Spectators user C Grade 3
Additionally, in order to make label information embody the hobby of spectators user more neatly, this label information is all right The live mark using live user adds the form of class information and represents.This label information comprises live mark and adds grade letter The group number of breath can be one group can also be many groups.When label information only comprising one group of live mark and adding class information, table Show that this spectators user is only interested in a live user.When in label information, the live mark of many groups adds class information, represent Spectators user is the most interesting to multiple live users.
Correspondingly, server can safeguard an overall label information list, and this label information listuser stores institute There are whole spectators users and the label information of each spectators user in system.The label information list of this overall situation can be such as table 2 Shown in, wherein, the label information of spectators user B only comprises " live mark 1+ grade 2 ", represent that spectators user B is only to live The live user identifying 1 correspondence is interested.The label information of spectators user A comprises " live mark 1+ grade 1 " and " live mark Know 2+ grade 1 ", represent that spectators user A is to the live user of live mark 1 correspondence and the live user of live mark 2 correspondence Interested.
Table 2
It should be noted that the grade of above-mentioned class information instruction is the highest, represent that live user is liked by spectators user Degree is the highest.Using live mark to add the form of class information under the mode representing label information, label information is all right Interest tags as spectators user is stored in the user profile of spectators user, concrete to label information of the embodiment of the present invention Form and storage mode are not especially limited.
In embodiments of the present invention, each spectators user is being got after the stay time of direct broadcasting room, it may be determined that should The preset threshold range at the stay time place of spectators user, and may determine that live user is liked journey by this spectators user Degree.In order to the spectators user that live user's favorable rating is different being made a distinction, in order to follow-up live user will be liked journey Spending close spectators user to recommend mutually, the embodiment of the present invention can be based on spectators user each in multiple spectators users Stay time, adds label information for each spectators user, and process may include that as stay time in same preset threshold range Interior spectators user adds identical label information, and for stay time, the spectators user in different preset threshold range adds not Same label information.
Specifically, each preset threshold range corresponding can have the label information of given level information, is determining spectators After the preset threshold range at the stay time place of user, obtain the label information corresponding with the preset threshold range determined, and The label information correspondence of this spectators user is added in label information list.
It should be noted that above-mentioned steps 302 is only a kind of alternative adding label information for each spectators user, This kind of alternative, by dividing multiple preset threshold range, can distinguish different spectators user to live user in more fine granularity ground Favorable rating so that the interest that label information more accurately embodies different spectators user is the most close.Certainly, in order to make More spectators are mutually added as good friend with having an opportunity per family, in another the optional place adding label information for spectators user In case, a predetermined threshold value also can be only set so that can be that stay time reaches all spectators of this predetermined threshold value with per family Label information can be added, close to represent the interest of these spectators users.
303, from multiple spectators users, obtain the identical at least two of label information and specify spectators user.
In embodiments of the present invention, the label information of multiple spectators user can be obtained, and according to the labelling got Information, the number of the spectators user that statistics same tag information is corresponding.For every kind of label information, if this kind of labelling letter The number of the spectators user that breath is corresponding is two or more, then spectators user corresponding for this kind of label information is defined as mark At least two that note information is identical specifies spectators user.
304, spectators user is specified to recommend mutually at least two.
In embodiments of the present invention, after getting at least two appointment spectators user, spectators are specified to use at least two The mode that family is recommended mutually can be the following two kinds:
The first, specify each appointment spectators user in spectators user at least two, generate first user and recommend to disappear Breath, first user recommendation message is for specifying other appointment spectators users in spectators user to recommend to specify spectators at least two User;By first user recommendation message, it is sent at least two and specifies other appointment spectators users in spectators user.
Wherein, first user recommendation message can comprise the user profile specifying spectators user, such as specify spectators to use The ID at family, or the good friend of this appointment spectators user adds link etc..This first user recommendation message only carries one Specify the user profile of spectators user.Such as, this at least two specifies spectators user to include spectators user A and spectators user B, then Server can generate user's recommendation message 1 of spectators user A, and user's recommendation message 2 of spectators user B respectively, and will use Family recommendation message 1 is sent to spectators user B, and user's recommendation message 2 is sent to spectators user A.Wherein, user's recommendation message 1 Content can be " interest of you and spectators user A is the most close, clicks on following link and adds him for good friend ", user recommends to disappear The content of breath 2 can be " you are the most close with the interest of spectators user B, clicks on following link and adds him for good friend ".
Specifically, after other specify the terminal at spectators user place to receive first user recommendation message, first is shown User's recommendation message so that other specify spectators user can choose whether to add this appointment according to this first user recommendation message Spectators user is good friend.
Wherein, other specify spectators users to add the process that this appointment spectators user be good friend and can be: when terminal detection When to other spectators users the good friend of this appointment spectators user added the clicking operation of link, show this appointment spectators user's Good friend adds interface, when terminal detects that the good friend of this appointment spectators user is added operation by other spectators users, to service Device sends other and specifies spectators user that the good friend of this appointment spectators user is added request, and server adds based on the good friend received Add request to send good friend to this appointment spectators user and add information, add when server receives the good friend of this appointment spectators user When confirming message, spectators user is specified to be mutually added as good friend with other this appointment spectators user.One is only comprised by sending The first user recommendation message of the individual user profile specifying spectators user so that the appointment receiving first user recommendation message is seen Many users can know the user profile of recommended spectators user more targetedly, exactly, improves what user recommended Accuracy.
The second, specifies each appointment spectators user in spectators user at least two, generates the second user and recommend to disappear Breath, second user's recommendation message is for specifying spectators user to recommend at least two to specify other appointment spectators in spectators user User;The each appointment spectators user in spectators user is specified to send second user's recommendation message at least two.
Wherein, can comprise other user profile specifying spectators user in second user's recommendation message, such as, other refer to Determine the ID of spectators user, or these other specify the good friend of spectators user to add link.These other specify spectators user Number can be one or more, that is to say, second user's recommendation message can comprise multiple specify spectators user use Family information.Such as, this at least two specifies spectators user to include spectators user A, spectators user B and spectators user C, then for sight Many user A, user's recommendation message 1 that server generates includes spectators user B and the user profile of spectators user C, and should User's recommendation message 1 is sent to spectators user A.The content of this user's recommendation message 1 can be " you and spectators user B, Guan Zhongyong The interest of family C is the most close, and the link clicking on them adds them for good friend ", this user's recommendation message 1 can pass through list Form show, the concrete form of second user's recommendation message is not construed as limiting by the embodiment of the present invention.For spectators user B and sight The content and form of many second corresponding for user C user's recommendation message with spectators user A in like manner, does not repeats them here.
Specifically, for each appointment spectators user, when the terminal at this appointment spectators user place receives second After user's recommendation message, show second user's recommendation message.This appointment spectators user can be known simultaneously multiple recommended The user profile of spectators user, it is possible to choose whether that adding other appointment spectators users is according to this second user recommendation message Good friend.Second user's recommendation message of multiple user profile specifying spectators user is comprised so that receive second by transmission The spectators user that specifies of user's recommendation message can disposably know the user profile of multiple recommended spectators user, improves The efficiency that user recommends.
Wherein, this appointment spectators user adds other processes specifying spectators user to be good friend and above-mentioned first kind of way Process in like manner, does not repeats them here.
In another embodiment, in order to know the different spectators users that hobby is close more accurately, permissible Determine different spectators user simultaneously to multiple identical live users interested time, then this difference spectators user is carried out mutually Recommend;Or, further, determining that different spectators user is simultaneously interested in multiple identical live users and favorable rating Time close, then this difference spectators user is recommended mutually.Wherein, the number of the plurality of live user can set in advance Fixed, concrete numerical value can be 2,3 etc., this is not especially limited by disclosure embodiment.By to live use interested Number and the favorable rating at family limit, and the different spectators users that can be more nearly by hobby recommend, and enter Improve to one step the accuracy rate that user recommends and the success rate adding good friend.
The method that the embodiment of the present invention provides, owing to different label informations reflects spectators user to live user not Same favorable rating, and then embody the hobby of spectators user, by according to spectators user in the stay time of direct broadcasting room, for Different spectators users add different label informations, and the different spectators users with same tag information are pushed away mutually Recommend, it is ensured that the both sides that user recommends have similar hobby, improve the accuracy rate of user's recommendation and add good friend's Success rate.
Fig. 4 is the block diagram of a kind of user's recommendation apparatus that the embodiment of the present invention provides, and sees Fig. 4, including: statistical module 401, add module 402, acquisition module 403 and recommending module 404.
Wherein, statistical module 401 is connected with adding module 402, for adding up multiple spectators user stop at direct broadcasting room Duration;Add module 402 and acquisition module 403, when stop based on spectators user each in the plurality of spectators user Long, add label information for described each spectators user, described label information is used for indicating spectators user to described direct broadcasting room pair Answer the favorable rating of live user;Acquisition module 403 is connected with recommending module 404, for from the plurality of spectators user, obtains Take the identical at least two of label information and specify spectators user;Recommending module 404, for specifying spectators to use described at least two Family is recommended mutually.
Alternatively, described statistical module 401, at the appointed time section, obtains described each spectators user and enters described First moment of direct broadcasting room and the second moment leaving described direct broadcasting room;Calculate first moment and of described each spectators user Time difference between two moment;According to described appointment time period and the time difference of described each spectators user, obtain described each The average duration that spectators user stops at described direct broadcasting room.
Alternatively, described interpolation module 402, for from multiple preset threshold range, determines described each spectators user's The preset threshold range at stay time place;For stay time, the spectators user in same preset threshold range adds identical Label information, for stay time, the spectators user in different preset threshold range adds different label informations.
Alternatively, described recommending module 404 is for specifying each appointment spectators in spectators user for described at least two User, generates first user recommendation message, and described first user recommendation message is for specifying spectators user to described at least two In other specify spectators users recommend described appointment spectators user;By described first user recommendation message, be sent to described in extremely Few two other appointment spectators users specified in spectators user.
Alternatively, described recommending module 404 is for specifying each appointment spectators in spectators user for described at least two User, generates second user's recommendation message, and described second user's recommendation message is for recommending described to described appointment spectators user At least two specifies other appointment spectators users in spectators user;The each finger in spectators user is specified to described at least two Determine spectators user and send described second user's recommendation message.
The device that the embodiment of the present invention provides, owing to different label informations reflects spectators user to live user not Same favorable rating, and then embody the hobby of spectators user, by according to spectators user in the stay time of direct broadcasting room, for Different spectators users add different label informations, and the different spectators users with same tag information are pushed away mutually Recommend, it is ensured that the both sides that user recommends have similar hobby, improve the accuracy rate of user's recommendation and add good friend's Success rate.
It should be understood that user's recommendation apparatus that above-described embodiment provides is when recommending user, only with above-mentioned each function The division of module is illustrated, and in actual application, can distribute above-mentioned functions by different function moulds as desired Block completes, and the internal structure of equipment will be divided into different functional modules, to complete all or part of merit described above Energy.It addition, user's recommendation apparatus that above-described embodiment provides recommends embodiment of the method to belong to same design with user, it is specifically real Existing process refers to embodiment of the method, repeats no more here.
Fig. 5 is the block diagram of a kind of user's recommendation apparatus that the embodiment of the present invention provides.Such as, device 500 can be provided It it is a server.With reference to Fig. 5, device 500 includes processing assembly 522, and it farther includes one or more processor, Yi Jiyou Memory resource representated by memorizer 532, can be by the instruction of the execution of processing component 522, such as application program for storage. In memorizer 532 storage application program can include one or more each corresponding to one group instruction module. It is configured to perform instruction additionally, process assembly 522, recommends method performing said method user.
Device 500 can also include that a power supply module 526 is configured to perform the power management of device 500, and one has Line or radio network interface 550 are configured to be connected to device 500 network, and input and output (I/O) interface 558.Dress Put 500 and can operate based on the operating system being stored in memorizer 532, such as Windows ServerTM, Mac OS XTM, UnixTM,LinuxTM, FreeBSDTMOr it is similar.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can pass through hardware Completing, it is also possible to instruct relevant hardware by program and complete, described program can be stored in a kind of computer-readable In storage medium, storage medium mentioned above can be read only memory, disk or CD etc..
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all spirit in the present invention and Within principle, any modification, equivalent substitution and improvement etc. made, should be included within the scope of the present invention.

Claims (10)

1. a user recommends method, it is characterised in that described method includes:
Add up multiple spectators user stay time at direct broadcasting room;
Stay time based on spectators user each in the plurality of spectators user, adds labelling letter for described each spectators user Breath, described label information is for indicating the favorable rating of spectators user live user corresponding to described direct broadcasting room;
From the plurality of spectators user, obtain the identical at least two of label information and specify spectators user;
Spectators user is specified to recommend mutually described at least two.
Method the most according to claim 1, it is characterised in that the multiple spectators user of described statistics is when the stop of direct broadcasting room Length includes:
At the appointed time in section, obtain described each spectators user and enter the first moment of described direct broadcasting room and leave described live Between the second moment;
Time difference between the first moment and the second moment that calculate described each spectators user;
According to described appointment time period and the time difference of described each spectators user, obtain described each spectators user described directly The average duration stopped between broadcasting.
Method the most according to claim 1, it is characterised in that described stay time based on each spectators user, for institute State each spectators user to add label information and include:
From multiple preset threshold range, determine the preset threshold range at the stay time place of described each spectators user;
For stay time, the spectators user in same preset threshold range adds identical label information, for stay time not Different label informations is added with the spectators user in preset threshold range.
Method the most according to claim 1, it is characterised in that described to described at least two specify spectators user carry out mutually Recommend mutually to include:
Each appointment spectators user in spectators user is specified for described at least two, generates first user recommendation message, described First user recommendation message is for specifying other appointment spectators users in spectators user to recommend described finger to described at least two Determine spectators user;
By described first user recommendation message, it is sent to described at least two and specifies other appointment spectators in spectators user to use Family.
Method the most according to claim 1, it is characterised in that described to described at least two specify spectators user carry out mutually Recommend mutually to include:
Each appointment spectators user in spectators user is specified for described at least two, generates second user's recommendation message, described Second user's recommendation message refers to for other recommending that described at least two specifies in spectators user to the described spectators user of appointment Determine spectators user;
The each appointment spectators user in spectators user is specified to send described second user's recommendation message to described at least two.
6. user's recommendation apparatus, it is characterised in that described device includes:
Statistical module, for adding up multiple spectators user stay time at direct broadcasting room;
Add module, for stay time based on spectators user each in the plurality of spectators user, for described each spectators User adds label information, and described label information likes journey for indicating spectators user live user corresponding to described direct broadcasting room Degree;
Acquisition module, for from the plurality of spectators user, obtains the identical at least two of label information and specifies spectators user;
Recommending module, for specifying spectators user to recommend mutually described at least two.
Device the most according to claim 6, it is characterised in that described statistical module, at the appointed time section, obtains Described each spectators user enters the first moment of described direct broadcasting room and leaves the second moment of described direct broadcasting room;Calculate described often Time difference between first moment and second moment of individual spectators user;Use according to described appointment time period and described each spectators The time difference at family, obtains the average duration that described each spectators user stops at described direct broadcasting room.
Device the most according to claim 6, it is characterised in that described interpolation module is for from multiple preset threshold range In, determine the preset threshold range at the stay time place of described each spectators user;For stay time in same predetermined threshold value In the range of spectators user add identical label information, for stay time, the spectators user in different preset threshold range adds Add different label informations.
Device the most according to claim 6, it is characterised in that described recommending module is for specifying for described at least two In spectators user, each appointment spectators user, generates first user recommendation message, and described first user recommendation message is for institute Stating at least two specifies other appointment spectators users in spectators user to recommend described appointment spectators user;By described first user Recommendation message, is sent to described at least two and specifies other appointment spectators users in spectators user.
Device the most according to claim 6, it is characterised in that described recommending module is for referring to for described at least two Determine in spectators user each appointment spectators user, generate second user's recommendation message, described second user's recommendation message for The described spectators user of appointment recommends described at least two to specify other appointment spectators users in spectators user;To described at least two The individual each appointment spectators user specified in spectators user sends described second user's recommendation message.
CN201610256042.0A 2016-04-21 2016-04-21 User's recommended method and device Active CN105872837B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610256042.0A CN105872837B (en) 2016-04-21 2016-04-21 User's recommended method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610256042.0A CN105872837B (en) 2016-04-21 2016-04-21 User's recommended method and device

Publications (2)

Publication Number Publication Date
CN105872837A true CN105872837A (en) 2016-08-17
CN105872837B CN105872837B (en) 2019-01-29

Family

ID=56632979

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610256042.0A Active CN105872837B (en) 2016-04-21 2016-04-21 User's recommended method and device

Country Status (1)

Country Link
CN (1) CN105872837B (en)

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791900A (en) * 2016-12-15 2017-05-31 北京小米移动软件有限公司 Live recommendation method and device
CN107562917A (en) * 2017-09-12 2018-01-09 广州酷狗计算机科技有限公司 User recommends method and device
CN107734393A (en) * 2017-10-10 2018-02-23 武汉斗鱼网络科技有限公司 Video friend-making adaptation method, storage medium, electronic equipment and system
CN107743251A (en) * 2017-10-10 2018-02-27 武汉斗鱼网络科技有限公司 Video friend-making duration adaptation method, storage medium, electronic equipment and system
CN107801047A (en) * 2017-10-10 2018-03-13 武汉斗鱼网络科技有限公司 Object designation method, storage medium, electronic equipment and the system that video is made friends
CN108271050A (en) * 2016-12-30 2018-07-10 武汉斗鱼网络科技有限公司 The method and device that a kind of direct broadcasting room program is recommended
CN108322829A (en) * 2018-03-02 2018-07-24 北京奇艺世纪科技有限公司 Personalized main broadcaster recommends method, apparatus and electronic equipment
CN108419135A (en) * 2018-03-22 2018-08-17 武汉斗鱼网络科技有限公司 Similarity determines method, apparatus and electronic equipment
CN108900924A (en) * 2018-07-20 2018-11-27 广州华多网络科技有限公司 The method and apparatus of commending friends in direct broadcasting room
CN109286821A (en) * 2018-09-30 2019-01-29 武汉斗鱼网络科技有限公司 A kind of direct broadcasting room recommended method, device, server and storage medium
CN109348260A (en) * 2018-12-06 2019-02-15 武汉瓯越网视有限公司 A kind of direct broadcasting room recommended method, device, equipment and medium
CN109408647A (en) * 2018-10-15 2019-03-01 北京字节跳动网络技术有限公司 Method and apparatus for handling information
CN109446442A (en) * 2018-10-15 2019-03-08 北京字节跳动网络技术有限公司 Method and apparatus for handling information
CN109586822A (en) * 2018-11-10 2019-04-05 东莞市华睿电子科技有限公司 A kind of broadcast audience method applied to shared bicycle
CN109615731A (en) * 2018-11-10 2019-04-12 东莞市华睿电子科技有限公司 A kind of audio-frequency inputting method based on recognition of face
CN109660492A (en) * 2017-10-10 2019-04-19 武汉斗鱼网络科技有限公司 Live video making friends method, storage medium, electronic equipment and system
CN110929151A (en) * 2019-11-20 2020-03-27 咪咕文化科技有限公司 User recommendation method, electronic device and storage medium
CN111629236A (en) * 2020-06-08 2020-09-04 广州繁星互娱信息科技有限公司 Friend relationship establishing method, device, equipment and computer readable storage medium
CN113365088A (en) * 2021-05-31 2021-09-07 北京达佳互联信息技术有限公司 Data processing method, data processing apparatus, electronic device, storage medium, and program product
CN115065836A (en) * 2022-05-19 2022-09-16 广州方硅信息技术有限公司 Live broadcast room switching display processing method, server, electronic terminal and storage medium
CN115336281A (en) * 2020-09-29 2022-11-11 多玩国株式会社 Moving picture distribution device, moving picture distribution method, and recording medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103327045A (en) * 2012-03-21 2013-09-25 腾讯科技(深圳)有限公司 User recommendation method and system in social network
KR20130134352A (en) * 2012-05-30 2013-12-10 한홍집 Customer interactive store management device and system using the same

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103327045A (en) * 2012-03-21 2013-09-25 腾讯科技(深圳)有限公司 User recommendation method and system in social network
KR20130134352A (en) * 2012-05-30 2013-12-10 한홍집 Customer interactive store management device and system using the same

Cited By (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791900A (en) * 2016-12-15 2017-05-31 北京小米移动软件有限公司 Live recommendation method and device
CN108271050A (en) * 2016-12-30 2018-07-10 武汉斗鱼网络科技有限公司 The method and device that a kind of direct broadcasting room program is recommended
CN108271050B (en) * 2016-12-30 2020-01-03 武汉斗鱼网络科技有限公司 Live broadcast room program recommendation method and device
CN107562917A (en) * 2017-09-12 2018-01-09 广州酷狗计算机科技有限公司 User recommends method and device
CN107801047A (en) * 2017-10-10 2018-03-13 武汉斗鱼网络科技有限公司 Object designation method, storage medium, electronic equipment and the system that video is made friends
CN109660492A (en) * 2017-10-10 2019-04-19 武汉斗鱼网络科技有限公司 Live video making friends method, storage medium, electronic equipment and system
CN107743251A (en) * 2017-10-10 2018-02-27 武汉斗鱼网络科技有限公司 Video friend-making duration adaptation method, storage medium, electronic equipment and system
CN107801047B (en) * 2017-10-10 2020-07-10 武汉斗鱼网络科技有限公司 Object specifying method, storage medium, electronic device and system for making friends through video
CN107743251B (en) * 2017-10-10 2020-06-16 武汉斗鱼网络科技有限公司 Video friend-making duration adapting method, storage medium, electronic device and system
CN107734393A (en) * 2017-10-10 2018-02-23 武汉斗鱼网络科技有限公司 Video friend-making adaptation method, storage medium, electronic equipment and system
CN107734393B (en) * 2017-10-10 2019-11-15 武汉斗鱼网络科技有限公司 Video friend-making adaptation method, storage medium, electronic equipment and system
WO2019071826A1 (en) * 2017-10-10 2019-04-18 武汉斗鱼网络科技有限公司 Object designation method, storage medium, electronic device and system for random video chat
WO2019071827A1 (en) * 2017-10-10 2019-04-18 武汉斗鱼网络科技有限公司 Video dating adaptation method, storage medium, electronic device, and system
CN108322829A (en) * 2018-03-02 2018-07-24 北京奇艺世纪科技有限公司 Personalized main broadcaster recommends method, apparatus and electronic equipment
CN108322829B (en) * 2018-03-02 2020-11-27 北京奇艺世纪科技有限公司 Personalized anchor recommendation method and device and electronic equipment
CN108419135A (en) * 2018-03-22 2018-08-17 武汉斗鱼网络科技有限公司 Similarity determines method, apparatus and electronic equipment
CN108419135B (en) * 2018-03-22 2020-07-10 武汉斗鱼网络科技有限公司 Similarity determination method and device and electronic equipment
CN108900924A (en) * 2018-07-20 2018-11-27 广州华多网络科技有限公司 The method and apparatus of commending friends in direct broadcasting room
CN108900924B (en) * 2018-07-20 2021-03-09 广州方硅信息技术有限公司 Method and device for recommending friends in live broadcast room
CN109286821A (en) * 2018-09-30 2019-01-29 武汉斗鱼网络科技有限公司 A kind of direct broadcasting room recommended method, device, server and storage medium
CN109446442A (en) * 2018-10-15 2019-03-08 北京字节跳动网络技术有限公司 Method and apparatus for handling information
CN109408647A (en) * 2018-10-15 2019-03-01 北京字节跳动网络技术有限公司 Method and apparatus for handling information
CN109586822A (en) * 2018-11-10 2019-04-05 东莞市华睿电子科技有限公司 A kind of broadcast audience method applied to shared bicycle
CN109615731A (en) * 2018-11-10 2019-04-12 东莞市华睿电子科技有限公司 A kind of audio-frequency inputting method based on recognition of face
CN109348260A (en) * 2018-12-06 2019-02-15 武汉瓯越网视有限公司 A kind of direct broadcasting room recommended method, device, equipment and medium
CN110929151A (en) * 2019-11-20 2020-03-27 咪咕文化科技有限公司 User recommendation method, electronic device and storage medium
CN111629236A (en) * 2020-06-08 2020-09-04 广州繁星互娱信息科技有限公司 Friend relationship establishing method, device, equipment and computer readable storage medium
CN111629236B (en) * 2020-06-08 2022-03-25 广州繁星互娱信息科技有限公司 Friend relationship establishing method, device, equipment and computer readable storage medium
CN115336281A (en) * 2020-09-29 2022-11-11 多玩国株式会社 Moving picture distribution device, moving picture distribution method, and recording medium
CN113365088A (en) * 2021-05-31 2021-09-07 北京达佳互联信息技术有限公司 Data processing method, data processing apparatus, electronic device, storage medium, and program product
CN113365088B (en) * 2021-05-31 2023-02-21 北京达佳互联信息技术有限公司 Data processing method, data processing apparatus, electronic device, storage medium, and program product
CN115065836A (en) * 2022-05-19 2022-09-16 广州方硅信息技术有限公司 Live broadcast room switching display processing method, server, electronic terminal and storage medium

Also Published As

Publication number Publication date
CN105872837B (en) 2019-01-29

Similar Documents

Publication Publication Date Title
CN105872837A (en) User recommendation method and device
EP2820616B1 (en) Empirical expert determination and question routing system and method
CN108563670B (en) Video recommendation method and device, server and computer-readable storage medium
US20120066212A1 (en) Monitoring hashtags in micro-blog posts to provide one or more crowd-based features
CN103686237A (en) Method and system for recommending video resource
CN107864192B (en) Information pushing method and device, server and readable storage medium
CN106294497A (en) Information recommendation method and device
CN109862013B (en) Live broadcast room recommendation method, storage medium, electronic device and system
CN103686236A (en) Method and system for recommending video resource
CN105791902A (en) User recommendation method and user recommendation device
CN106713985B (en) Method and device for recommending network video
US9800922B2 (en) Integrating social media with recordation of broadcast data
CN109547807B (en) Information processing method and device based on live broadcast and server
CN107770624A (en) It is a kind of it is live during multimedia file player method, device and storage medium
CN109272393A (en) A kind of laboratory personnel shopping recommended method and device based on block chain technology
CN104484406A (en) Recommended data issuing analysis method and recommended data issuing analysis device
CN111026969B (en) Content recommendation method and device, storage medium and server
CN106303591A (en) A kind of video recommendation method and device
CN104252541B (en) A kind of webpage information method for pushing, data server and terminal
CN103678624A (en) Searching method, searching server, and searching request executing method and terminal
CN105956061B (en) Method and device for determining similarity between users
CN109451334A (en) User, which draws a portrait, generates processing method, device and electronic equipment
CN104834728B (en) A kind of method for pushing and device for subscribing to video
CN111224796A (en) Method, device and storage medium for creating group for specified group object
CN109284444A (en) A kind of recommended method of good friend, device, server and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 510660 Guangzhou City, Guangzhou, Guangdong, Whampoa Avenue, No. 315, self - made 1-17

Applicant after: Guangzhou KuGou Networks Co., Ltd.

Address before: 510000 B1, building, No. 16, rhyme Road, Guangzhou, Guangdong, China 13F

Applicant before: Guangzhou KuGou Networks Co., Ltd.

GR01 Patent grant
GR01 Patent grant