CN105307023B - Using recommendation method, apparatus and video recommendation method, device - Google Patents

Using recommendation method, apparatus and video recommendation method, device Download PDF

Info

Publication number
CN105307023B
CN105307023B CN201510727303.8A CN201510727303A CN105307023B CN 105307023 B CN105307023 B CN 105307023B CN 201510727303 A CN201510727303 A CN 201510727303A CN 105307023 B CN105307023 B CN 105307023B
Authority
CN
China
Prior art keywords
application
information aggregate
associated video
information
video
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.)
Active
Application number
CN201510727303.8A
Other languages
Chinese (zh)
Other versions
CN105307023A (en
Inventor
刘致远
周燕红
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.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and 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 Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201510727303.8A priority Critical patent/CN105307023B/en
Publication of CN105307023A publication Critical patent/CN105307023A/en
Application granted granted Critical
Publication of CN105307023B publication Critical patent/CN105307023B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management 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
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies

Abstract

The embodiment of the invention discloses application to recommend method, apparatus and video recommendation method, device, wherein, video recommendation method includes：In the case where detecting that user has the user behavior for intended application, determine the information aggregate corresponding to at least one application of the information aggregate corresponding to intended application with correlation, the information aggregate corresponding to an application includes the identification information for applying corresponding associated video with this using the identification information and application associated video sharing platform side of the application of download platform side；The identification information of the video in information aggregate according to corresponding to identified, at least one application, determines that corresponding relevant video is applied in associated video sharing platform side with this；Video determined by recommending in the lateral user of application download platform.Technical scheme, adds the species of the recommendation of each platform, user is while the recommendation information of one platform of selection, it is also an option that the relevant information of another platform.

Description

Using recommendation method, apparatus and video recommendation method, device
Technical field
The present invention relates to internet arena, method, apparatus and video recommendation method, device are recommended in more particularly to application.
Background technology
All it is the internet product that user likes and largely uses using download platform and using associated video sharing platform. But be independent system using download platform and application associated video sharing platform, have no to associate each other.
Under normal circumstances, when user is generating user behavior using download platform, such as browse, download using after A, answer With download platform can according to the behavior record of the relevant information of the application in this platform and the user and other users, analyze with The relevant applications of A, then recommend user.
Likewise, work as user is generating user behavior using associated video sharing platform, such as click on, watch and apply phase After closing video, it can also recommend the associated video of some other applications to user using associated video sharing platform.
As can be seen that relatively simple using the recommendation species of download platform and application associated video sharing platform, user is only The recommendation information of corresponding platform can be selected, may not select the relevant information of another platform.
The content of the invention
The embodiment of the invention discloses application to recommend method, apparatus and video recommendation method, device, for solving each platform The problem of species of recommendation is relatively simple.Technical solution is as follows：
First aspect of the embodiment of the present invention provides a kind of video recommendation method, including：
Detect user and be directed to the user behavior of intended application in application download platform side；
In the case where detecting that user has the user behavior for intended application,
Determine the information collection corresponding to at least one application of the information aggregate corresponding to intended application with correlation Close, the information aggregate corresponding to an application is included using the identification information of the application of download platform side and using associated video The identification information of corresponding associated video is applied with this in sharing platform side；
In information aggregate according to corresponding to identified, at least one application corresponding associated video is applied with this Identification information, determines associated video sharing platform side and the relevant video of intended application；
Recommend the identified and relevant video of intended application in the lateral user of application download platform；
Wherein it is determined that there is the letter corresponding at least one application of correlation with the information aggregate corresponding to intended application The method of breath set includes：
Determine the size of the multi-feature vector of intended application and the corresponding information aggregate of other application, wherein, often The multi-feature vector of one application includes that M is default apply corresponding characteristic element with this, it is N number of default and this using pair The corresponding characteristic element of associated video answered, M >=1, N >=1；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
According to default vector similarity computational methods, the multi-feature vector of the corresponding information aggregate of intended application is determined Similarity between the multi-feature vector of information aggregate corresponding with other application；
If any multi-feature vector using corresponding information aggregate information aggregate corresponding with intended application is comprehensive The similarity for closing feature vector is more than predetermined threshold value, it is determined that this applies corresponding information aggregate information corresponding with intended application There is correlation between set.
It is described to be further included with using corresponding characteristic element in a kind of preferred embodiment of the present embodiment：According to should The characteristic element that relevant information determines, and preset its size.
In a kind of preferred embodiment of the present embodiment, determining that there is phase with the information aggregate corresponding to intended application After information aggregate corresponding at least one application of closing property, further include：
The identification information of the application in information aggregate according to corresponding to identified, at least one application, determines application Download platform side and the relevant application of intended application；
Recommend the identified and relevant application of intended application in the lateral user of application download platform.
In a kind of preferred embodiment of the present embodiment, vector similarity computational methods are selected from：
One kind in cosine similarity computational methods, Euclidean distance computational methods and Jie Kade distance calculating methods.
Second aspect of the embodiment of the present invention provides one kind and applies recommendation method, including：
Detect user row of the user in application associated video sharing platform side for the associated video corresponding to intended application For；
In the case where detecting that user has the user behavior for the corresponding associated video of intended application,
Determine the information collection corresponding to at least one application of the information aggregate corresponding to intended application with correlation Close, the information aggregate corresponding to an application is included using the identification information of the application of download platform side and using associated video The identification information of corresponding associated video is applied with this in sharing platform side；
The identification information of the application in information aggregate according to corresponding to identified, at least one application, determining should With the relevant application of associated video corresponding to download platform side and intended application；
Associated video determined by recommending in the lateral user of application associated video sharing platform and corresponding to intended application Relevant application；
Wherein it is determined that there is the letter corresponding at least one application of correlation with the information aggregate corresponding to intended application The method of breath set includes：
Determine the size of the multi-feature vector of intended application and the corresponding information aggregate of other application, wherein, often The multi-feature vector of one application includes that M is default apply corresponding characteristic element with this, it is N number of default and this using pair The corresponding characteristic element of associated video answered, M >=1, N >=1；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
According to default vector similarity computational methods, the multi-feature vector of the corresponding information aggregate of intended application is determined Similarity between the multi-feature vector of information aggregate corresponding with other application；
If any multi-feature vector using corresponding information aggregate information aggregate corresponding with intended application is comprehensive The similarity for closing feature vector is more than predetermined threshold value, it is determined that this applies corresponding information aggregate information corresponding with intended application There is correlation between set.
It is described to be further included with using corresponding characteristic element in a kind of preferred embodiment of the present embodiment：According to should The characteristic element that relevant information determines, and preset its size.
In a kind of preferred embodiment of the present embodiment, determining that there is phase with the information aggregate corresponding to intended application After information aggregate corresponding at least one application of closing property, further include：
The identification information of the video in information aggregate according to corresponding to identified, at least one application, determines correlation The video sharing platform side video relevant with the associated video corresponding to intended application；
It is related to the associated video corresponding to intended application determined by recommending in the lateral user of associated video sharing platform Video.
The third aspect of the embodiment of the present invention provides a kind of video recommendations device, it is characterised in that including：
First user behavior detection module, user's row of intended application is directed to for detecting user in application download platform side For；
First information set determining module, target is directed to for detecting that user exists in the first user behavior detection module In the case of the user behavior of application, at least one application that there is correlation with the information aggregate corresponding to intended application is determined Corresponding information aggregate, the mark that the information aggregate corresponding to an application includes the lower application using download platform side are believed Breath and application associated video sharing platform side apply the identification information of corresponding associated video with this；
First video determining module, for regarding in the information aggregate according to corresponding to identified, at least one application The identification information of frequency, determines associated video sharing platform side and the relevant video of intended application；
First video recommendations module is identified related to intended application for recommending in the lateral user of application download platform Video；
Wherein, first information set determining module includes：
First multi-feature vector determination sub-module, for determining intended application and the corresponding information collection of other application Wherein, the multi-feature vector of each application is default corresponding with the application including M for the size of the multi-feature vector of conjunction Characteristic element, it is N number of default to apply the corresponding characteristic element of corresponding associated video, M >=1, N >=1 with this；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
First similarity measure submodule, for according to default vector similarity computational methods, determining intended application pair Similarity between the multi-feature vector of the multi-feature vector for the information aggregate answered information aggregate corresponding with other application；
First correlation determination sub-module, if for any multi-feature vector and mesh using corresponding information aggregate The similarity of the multi-feature vector of the corresponding information aggregate of mark application is more than predetermined threshold value, it is determined that this applies corresponding information There is correlation between set information aggregate corresponding with intended application.
It is described to be further included with using corresponding characteristic element in a kind of preferred embodiment of the present embodiment：According to should The characteristic element that relevant information determines, and preset its size.
In a kind of preferred embodiment of the present embodiment, further include：First application determining module and the first application are recommended Module；It is described first application determining module be used for the first information set determining module determine with intended application corresponding to After information aggregate has the information aggregate corresponding at least one application of correlation,
The identification information of the application in information aggregate according to corresponding to identified, at least one application, determines application Download platform side and the relevant application of intended application；
Described first applies recommending module, for recommending identified and intended application in the lateral user of application download platform Relevant application.
In a kind of preferred embodiment of the present embodiment, vector similarity computational methods are selected from：
One kind in cosine similarity computational methods, Euclidean distance computational methods and Jie Kade distance calculating methods.
Fourth aspect of the embodiment of the present invention provides one kind and applies recommendation apparatus, including：
Second user behavioral value module, intended application is directed to for detecting user in application associated video sharing platform side The user behavior of corresponding associated video；
Second information aggregate determining module, target is directed to for detecting that user exists in second user behavioral value module In the case of user behavior using corresponding associated video, determine that there is correlation with the information aggregate corresponding to intended application At least one application corresponding to information aggregate, information aggregate corresponding to an application include using download platform side should The identification information of application and application associated video sharing platform side apply the identification information of corresponding associated video with this；
Second applies determining module, for answering in the information aggregate according to corresponding to identified, at least one application Identification information, determines using download platform side and the relevant application of associated video corresponding to intended application；
Second applies recommending module, for recommending identified and target in the lateral user of application associated video sharing platform Using the corresponding relevant application of associated video；
Wherein, the second information aggregate determining module includes：
Second multi-feature vector determination sub-module, for determining intended application and the corresponding information collection of other application The size of the multi-feature vector of conjunction, wherein, the multi-feature vector of each application is default corresponding with the application including M Characteristic element, it is N number of default to apply the corresponding characteristic element of corresponding associated video, M >=1, N >=1 with this；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
Second similarity measure submodule, for according to default vector similarity computational methods, determining intended application pair Similarity between the multi-feature vector of the multi-feature vector for the information aggregate answered information aggregate corresponding with other application；
Second correlation determination sub-module, if for any multi-feature vector and mesh using corresponding information aggregate The similarity of the multi-feature vector of the corresponding information aggregate of mark application is more than predetermined threshold value, it is determined that this applies corresponding information There is correlation between set information aggregate corresponding with intended application.
It is described to be further included with using corresponding characteristic element in a kind of preferred embodiment of the present embodiment：According to should The characteristic element that relevant information determines, and preset its size.
In a kind of preferred embodiment of the present embodiment, further include：Second video determining module and the second video recommendations Module；The second video determining module is used to determine and the information corresponding to intended application in the second information aggregate determining module It is right according to identified, at least one application institute after information aggregate corresponding at least one application of the set with correlation The identification information of video in the information aggregate answered, determines that associated video sharing platform side is related to corresponding to intended application and regards Frequently relevant video；
The second video recommendations module, for recommending identified and target in the lateral user of associated video sharing platform Using the corresponding relevant video of associated video.
Technical scheme, the identification information of the application of application download platform side is flat with applying associated video to share Platform side is integrated in using a corresponding information aggregate with this using the identification information of corresponding associated video；And determine respectively should With the correlation between corresponding set.
In this way, in application download platform side, in the case where detecting that user has the user behavior for intended application, It can determine the information aggregate corresponding to at least one application of the information aggregate corresponding to intended application with correlation, so Determine the video in the information aggregate with correlation again afterwards, recommend identified and target in the lateral user of application download platform Using relevant video.
Similarly, in application associated video sharing platform side, the corresponding correlation of intended application is directed to detecting that user exists In the case of the user behavior of video, it may be determined that going out information aggregate corresponding with intended application has the information aggregate of correlation In application, and related to corresponding to intended application determined by recommending in the lateral user of application associated video sharing platform regard Frequently relevant application.
As it can be seen that technical scheme, by increasing capacitance it is possible to increase the species of the recommendation of each platform, user is in one platform of selection While recommendation information, it is also an option that the relevant information of another platform.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of video recommendation method flow chart provided in an embodiment of the present invention；
Fig. 2 recommends method flow diagram for a kind of application provided in an embodiment of the present invention；
Fig. 3 is a kind of video recommendations apparatus structure schematic diagram provided in an embodiment of the present invention；
Fig. 4 applies recommendation apparatus structure diagram for one kind provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts Embodiment, belongs to the scope of protection of the invention.
First, an embodiment of the present invention provides a kind of video recommendation method, the executive agent of this method can be an energy Enough recommend the device of video using download platform side, which, which can be located at, applies download platform side, can also be located at and apply phase Close video sharing platform side, may be located on be different from using download platform and should with application associated video sharing platform the 3rd Square platform side.Described application associated video sharing platform has with applying some relevant videos, and user can be in the platform Upper some oneself corresponding videos of application interested of viewing.It is flat than more typical application to be that game is downloaded using download platform Platform, using associated video sharing platform than more typical application be game associated video sharing platform.User can be under game Carrying platform download games A, can browse in game associated video sharing platform, watch and the game relevant videos of A.
As shown in Figure 1, this method can include：
S101, detection user are directed to the user behavior of intended application in application download platform side；
Described " being directed to the user behavior of intended application in application download platform side " includes：User is using download platform Side for the browsing of application, download and other with applying relevant behavior.
S102, in the case where detecting that user has the user behavior for intended application,
Determine the information collection corresponding to at least one application of the information aggregate corresponding to intended application with correlation Close, the information aggregate corresponding to an application is included using the identification information of the application of download platform side and using associated video The identification information of corresponding associated video is applied with this in sharing platform side.
Recommend video in application download platform side to realize, to establish in advance application using download platform side with using phase The correspondence of the associated video of the pass video sharing platform side application, that is, determine to apply corresponding information aggregate.Should The identification information that can include application in set applies the identification information of associated video with this.Described identification information includes at least Using or video title and ID.The correlation technique of the prior art can be used by determining the scheme of the corresponding information aggregate of application Scheme realizes that the present invention is herein not especially limited.For example, can application associated video platform side according to video topic, Video tab, video speech information etc. determine each video corresponding to an application, and determine the identification information of each video, then from The identification information of the application is determined using download platform side, then combines to obtain this by each identification information and applies corresponding information collection Close.
After intended application and the corresponding information aggregate of other application is determined, need further exist for determining to answer with target There is the information aggregate corresponding at least one application of correlation with corresponding information aggregate.
In practical applications, the described definite and information aggregate corresponding to intended application has at least one of correlation It can include using the method for corresponding information aggregate：
Determine the size of the multi-feature vector of intended application and the corresponding information aggregate of other application, wherein, often The multi-feature vector of one application is default with applying corresponding characteristic element including M, N number of default corresponding with the application The corresponding characteristic element of associated video, M >=1, N >=1；Include with using corresponding characteristic element：According to using download platform The characteristic element that the user behavior of side determines, and recorded according to user behavior and determine its size；With applying corresponding associated video Corresponding characteristic element includes：The characteristic element determined according to the user behavior of application associated video sharing platform side, and according to User behavior record determines its size.
According to default vector similarity computational methods, the multi-feature vector of the corresponding information aggregate of intended application is determined Similarity between the multi-feature vector of information aggregate corresponding with other application；
If any multi-feature vector using corresponding information aggregate information aggregate corresponding with intended application is comprehensive The similarity for closing feature vector is more than predetermined threshold value, it is determined that this applies corresponding information aggregate information corresponding with intended application There is correlation between set.
It should be noted that the similarity of the multi-feature vector of the corresponding information aggregate of intended application with itself is most Big, it is bound to be more than predetermined threshold value, therefore, the corresponding information aggregate of intended application has correlation with itself.
Due to containing the information using and with application associated video using corresponding information aggregate, information collection The multi-feature vector of conjunction also includes two parts characteristic element, and a part is to apply corresponding characteristic element, and another part is to regard Frequently the characteristics of corresponding characteristic element, such multi-feature vector can preferably embody information aggregate.It should be noted that The number of two-part characteristic element can be determined by one skilled in the art, and the present invention is not required to be defined herein.
For that can include with using corresponding characteristic element：By those skilled in the art according to application download platform side The characteristic element that user behavior determines, and recorded according to user behavior and determine its size；Characteristic element is being determined according to user behavior When plain, it can be determined without considering the otherness between user, for example, can include with using corresponding characteristic element：Using The number browsed, using the number being downloaded, using number being scored etc..In this case, these characteristic elements Size, that is, score value representated by these characteristic elements can also be carried out by those skilled in the art by historical experience it is true It is fixed, for example, using being browsed once, the size of this feature element can be set as 1.
It is also contemplated that otherness between user is determined with applying corresponding characteristic element.For example, characteristic element can With including：User A downloads browse application, and user B downloads browse application etc., likewise, the size of these characteristic elements, also It is that score value representated by these characteristic elements can also be determined by those skilled in the art by historical experience.For example, with The size that family A downloads browse application is 5, and the size that user B downloads browse application is 10.
Likewise, include for characteristic element corresponding with the corresponding associated video of application：According to application associated video point The characteristic element that the user behavior of platform side determines is enjoyed, and is recorded according to user behavior and determines its size.Similar, it can also examine The otherness between user is considered to determine characteristic element, can not also consider the otherness between user to determine characteristic element.
For example, in the case of without considering the otherness between user, characteristic element can include：Associated video is watched Number, the number that associated video is commented on etc..In the case of the otherness between considering user, if related using A Video have three, be video 1, video 2 and video 3 respectively, characteristic element can include：User A have viewed video 1, user B Video 2 is have viewed, user C has commented on video 3 etc..
In practical applications, can also include with using corresponding characteristic element：Determined according to the relevant information of application Characteristic element, and preset its size.Such characteristic element can include：The type of application, the developer of application, application Theme etc., likewise, can also be that these characteristic elements distribute certain score value.
It should be noted that respectively the dimension of the multi-feature vector of the corresponding information aggregate of application is consistent, that is, Say, the number of the element that multi-feature vector is included is consistent.
For the computational methods of vector similarity, using computational methods commonly used in the art, for example, cosine can be used Similarity calculating method, Euclidean distance computational methods, Pearson correlation coefficients computational methods or Jie Kade distance calculating methods.
Described predetermined threshold value can by those skilled in the art according to the public examination of similarity measure and by historical experience come Determine, predetermined threshold value should not form the limitation to technical solution of the present invention in itself.
S103, in the information aggregate according to corresponding to identified, at least one application to this using corresponding related The identification information of video, determines associated video sharing platform side and the relevant video of intended application.
After information aggregate corresponding with application of the information aggregate corresponding to intended application with correlation is determined, just It can determine that these apply the identification information of the video in corresponding information aggregate, and the video corresponding to by these identification informations It is determined as in associated video sharing platform side and the relevant video of intended application.
S104, recommends the identified and relevant video of intended application in the lateral user of application download platform.
The specific implementation of this step can be realized using the related art scheme of the prior art.The present invention is herein not It is described in detail.
In practical applications, using download platform side while recommending to apply to user, identified will can own Video is recommended to user, some videos can also be further filtered out according to some conditions to recommend to user.Screening Condition can be screened according to temperature of video etc..
As it can be seen that using method as shown in Figure 1, the identification information of the application of application download platform side is regarded to using related Frequency division is enjoyed platform side and is integrated in this using the identification information of corresponding associated video using a corresponding information aggregate；And Determine each correlation using between corresponding set.
In this way, in application download platform side, in the case where detecting that user has the user behavior for intended application, It can determine the information aggregate corresponding to at least one application of the information aggregate corresponding to intended application with correlation, so Determine the video in the information aggregate with correlation again afterwards, recommend identified and target in the lateral user of application download platform Using associated video.
In addition to video determined by recommending in the lateral user of application download platform, can also further it recommend to user Using specifically, its implementation can be as follows：Determine that there is phase with the information aggregate corresponding to intended application in step S102 After information aggregate corresponding at least one application of closing property, further include：
The identification information of the application in information aggregate according to corresponding to identified, at least one application, determines application Download platform side and the relevant application of intended application；The application corresponding to identification information is determined as in application download platform side With the relevant application of intended application.
Recommend the identified and relevant application of intended application in the lateral user of application download platform.
In actual application, it can be recommended using download platform side using the way of recommendation of the prior art to user Using, while technical solution using the present invention is recommended video, further, technical solution also using the present invention to user To recommend to apply to user；
It can also come to recommend video to user only with technical scheme using download platform side and use this hair Bright technical solution is recommended to apply to user.
Below with application download platform and application one of associated video sharing platform than more typical application：Game is downloaded Exemplified by platform and game associated video sharing platform, further technical scheme is illustrated.
When user has downloaded game a in game download platform, it is possible to determine that information aggregate corresponding with game a has phase The corresponding information aggregate of at least one game of closing property, it is assumed here that the information aggregate information corresponding with game a for the b that only plays Set has correlation.And include the mark of game a in the corresponding information aggregates of game a, and two videos relevant with a The identification information of a1, a2.Include the mark of game b, and two videos relevant with b in the corresponding information aggregates of game b The identification information of b1, b2.Thus can be according to the identification information of a1, a2, b1, b2, in game associated video sharing platform side Determine corresponding video, and it is all or part of in the lateral user's recommendation of application download platform.Further, can also play The lateral user's recommended games b of download platform.
The embodiment of the present invention additionally provides one kind and applies recommendation method, and the executive agent of this method can be that a kind of application pushes away Device is recommended, which, which can be located at, applies download platform side, can also be located at and apply associated video sharing platform side, can be with position In different from application download platform and should be with the third-party platform side of associated video sharing platform.
As shown in Fig. 2, this method can include：
S201, use of the detection user in application associated video sharing platform side for the associated video corresponding to intended application Family behavior；
S202, in the case where detecting that user has the user behavior for the corresponding associated video of intended application,
Determine the information collection corresponding to at least one application of the information aggregate corresponding to intended application with correlation Close, the information aggregate corresponding to an application is included using the identification information of the application of download platform side and using associated video The identification information of corresponding associated video is applied with this in sharing platform side；
S203, the identification information of the application in information aggregate according to corresponding to identified, at least one application, determines Using the relevant application of the associated video corresponding to download platform side and intended application；
After information aggregate corresponding with application of the information aggregate corresponding to intended application with correlation is determined, just It can determine that these apply the identification information applied in corresponding information aggregate, and the application corresponding to these identification informations is true It is set in application download platform side and the relevant application of associated video corresponding to intended application.
S204, recommends identified related to corresponding to intended application in the lateral user of application associated video sharing platform The relevant application of video；
In practical applications, using associated video sharing platform side to user recommend video while, can by really Fixed all applications are recommended to user, some applications can also be further filtered out according to some conditions to be pushed away to user Recommend.The condition of screening can be screened according to temperature of application etc..
Wherein it is determined that there is the letter corresponding at least one application of correlation with the information aggregate corresponding to intended application The method of breath set includes：
Determine the size of the multi-feature vector of intended application and the corresponding information aggregate of other application, wherein, often The multi-feature vector of one application includes that M is default apply corresponding characteristic element with this, it is N number of default and this using pair The corresponding characteristic element of associated video answered, M >=1, N >=1；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
According to default vector similarity computational methods, the multi-feature vector of the corresponding information aggregate of intended application is determined Similarity between the multi-feature vector of information aggregate corresponding with other application；
If any multi-feature vector using corresponding information aggregate information aggregate corresponding with intended application is comprehensive The similarity for closing feature vector is more than predetermined threshold value, it is determined that this applies corresponding information aggregate information corresponding with intended application There is correlation between set.
It should be noted that the similarity of the multi-feature vector of the corresponding information aggregate of intended application with itself is most Big, it is bound to be more than predetermined threshold value, therefore, the corresponding information aggregate of intended application has correlation with itself.
In some embodiments of this method, further included with using corresponding characteristic element：According to the phase of application The characteristic element that information determines is closed, and presets its size.
In other embodiments of this method, vector similarity computational methods can be selected from：
Cosine similarity computational methods, Euclidean distance computational methods, Pearson correlation coefficients computational methods and Jie Kade away from From one kind in computational methods.
As it can be seen that using method as shown in Figure 2, the identification information of the application of application download platform side is regarded to using related Frequency division is enjoyed platform side and is integrated in this using the identification information of corresponding associated video using a corresponding information aggregate；And Determine each correlation using between corresponding set.
In application associated video sharing platform side, the corresponding associated video of intended application is directed to detecting that user exists In the case of user behavior, it may be determined that go out answering in information aggregate of the information aggregate corresponding with intended application with correlation With, and related to the associated video corresponding to intended application determined by the lateral user's recommendation of application associated video sharing platform Application.
In practical applications, except application associated video sharing platform to user recommend determined by application, can be with Recommend video to user, its implementation can be as follows：
In step S202, it is right with least one application institute of the information aggregate corresponding to intended application with correlation to determine After the information aggregate answered, further include：
The identification information of the video in information aggregate according to corresponding to identified, at least one application, determines correlation Video sharing platform side and the relevant video of associated video corresponding to intended application；It is i.e. that the video corresponding to identification information is true It is set to associated video sharing platform side and the relevant video of associated video corresponding to intended application.
Associated video determined by recommending in the lateral user of application associated video sharing platform and corresponding to intended application Relevant video.
In actual application, associated video sharing platform side can be using the way of recommendation of the prior art come to user Recommend video, while technical solution using the present invention is recommended to apply to user, further, technology also using the present invention Scheme is recommended video to user；
It can also recommend video simultaneously to user only with technical scheme using associated video sharing platform side Technical solution using the present invention is recommended to apply to user.
It should be noted that each embodiment corresponding to above-mentioned video recommendation method, you can individually implement also may be used Partly or entirely to combine implementation, specific embodiment is determined by one skilled in the art, and the present invention is herein not It is construed as limiting.Likewise, each embodiment corresponding to above application recommendation method, you can individually implement can also part or Implementation all is combined, specific embodiment is determined by one skilled in the art, and the present invention is not limited thereto.
Corresponding to the method shown in Fig. 1, the embodiment of the present invention additionally provides a kind of video recommendations device, as shown in figure 3, can With including：
First user behavior detection module 101, the use of intended application is directed to for detecting user in application download platform side Family behavior；
First information set determining module 102, for detecting user in the first user behavior detection module 101, there are pin To in the case of the user behavior of intended application, determining and at least one of the information aggregate corresponding to intended application with correlation Information aggregate corresponding to a application, the information aggregate corresponding to an application include the mark of the application using download platform side Know information and application associated video sharing platform side applies the identification information of corresponding associated video with this；
First video determining module 103, in the information aggregate according to corresponding to identified, at least one application The identification information of corresponding associated video is applied with this, determines associated video sharing platform side and the relevant video of intended application；
First video recommendations module 104, for recommending identified and intended application in the lateral user of application download platform Relevant video；
Wherein, first information set determining module 102 can include：
First multi-feature vector determination sub-module, for determining intended application and the corresponding information collection of other application The size of the multi-feature vector of conjunction, wherein, the multi-feature vector of each application is default corresponding with the application including M Characteristic element, it is N number of default to apply the corresponding characteristic element of corresponding associated video, M >=1, N >=1 with this；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
First similarity measure submodule, for according to default vector similarity computational methods, determining intended application pair Similarity between the multi-feature vector of the multi-feature vector for the information aggregate answered information aggregate corresponding with other application；
First correlation determination sub-module, if for any multi-feature vector and mesh using corresponding information aggregate The similarity of the multi-feature vector of the corresponding information aggregate of mark application is more than predetermined threshold value, it is determined that this applies corresponding information There is correlation between set information aggregate corresponding with intended application.
It is described to be further included with using corresponding characteristic element in some embodiments of the device：According to application The characteristic element that determines of relevant information, and preset its size.
In other embodiments of the device, further include：First application determining module and the first application are recommended Module；It is described first application determining module be used for first information set determining module 102 determine with intended application corresponding to After information aggregate has the information aggregate corresponding at least one application of correlation, according to identified, at least one application The identification information of application in corresponding information aggregate, determines using download platform side and the relevant application of intended application；Institute State first and apply recommending module, for recommending identified and intended application is relevant should in the lateral user of application download platform With.
In still other embodiment of the device, vector similarity computational methods can be selected from：
Cosine similarity computational methods, Euclidean distance computational methods, Pearson correlation coefficients computational methods and Jie Kade away from From one kind in computational methods.
Using device as shown in Figure 3, by the identification information of the application of application download platform side and application associated video point Platform side is enjoyed to be integrated in using a corresponding information aggregate using the identification information of corresponding associated video with this；And determine Respectively apply the correlation between corresponding set.
In this way, in application download platform side, in the case where detecting that user has the user behavior for intended application, It can determine the information aggregate corresponding to at least one application of the information aggregate corresponding to intended application with correlation, so Determine the video in the information aggregate with correlation again afterwards, recommend identified and target in the lateral user of application download platform Using relevant video.
Corresponding to method as shown in Figure 2, the embodiment of the present invention additionally provides one kind and applies recommendation apparatus, as shown in figure 4, It can include：
Second user behavioral value module 201, target is directed to for detecting user in application associated video sharing platform side Using the user behavior of corresponding associated video；
Second information aggregate determining module 202, for detecting user in second user behavioral value module 201, there are pin To in the case of the user behavior of the corresponding associated video of intended application, determining to have with the information aggregate corresponding to intended application Information aggregate corresponding at least one application of correlation, the information aggregate corresponding to an application include applying download platform The identification information of the application of side and application associated video sharing platform side apply the identification information of corresponding associated video with this；
Second applies determining module 203, in the information aggregate according to corresponding to identified, at least one application The identification information of the application, determines using download platform side and the relevant application of associated video corresponding to intended application；
Second applies recommending module 204, for determined by recommending in the lateral user of application associated video sharing platform with The relevant application of associated video corresponding to intended application；
Wherein, the second information aggregate determining module 202 can include：
Second multi-feature vector determination sub-module, for determining intended application and the corresponding information collection of other application The size of the multi-feature vector of conjunction, wherein, the multi-feature vector of each application is default corresponding with the application including M Characteristic element, it is N number of default to apply the corresponding characteristic element of corresponding associated video, M >=1, N >=1 with this；
Wherein, include with using corresponding characteristic element：The feature determined according to the user behavior of application download platform side Element, and recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to The characteristic element determined using the user behavior of associated video sharing platform side, and recorded according to user behavior and determine its size；
Second similarity measure submodule, for according to default vector similarity computational methods, determining intended application pair Similarity between the multi-feature vector of the multi-feature vector for the information aggregate answered information aggregate corresponding with other application；
Second correlation determination sub-module, if for any multi-feature vector and mesh using corresponding information aggregate The similarity of the multi-feature vector of the corresponding information aggregate of mark application is more than predetermined threshold value, it is determined that this applies corresponding information There is correlation between set information aggregate corresponding with intended application.
It is described to be further included with using corresponding characteristic element in some embodiments of the device：According to application The characteristic element that determines of relevant information, and preset its size.
In other embodiments of the device, device can also include：Second video determining module and second Video recommendations module；The second video determining module is used to determine in the second information aggregate determining module 202 and intended application After corresponding information aggregate has the information aggregate corresponding at least one application of correlation, according to identified, at least The identification information of the video in information aggregate corresponding to one application, determines associated video sharing platform side and intended application institute The corresponding relevant video of associated video.
The second video recommendations module, for recommending identified and target in the lateral user of associated video sharing platform Using the corresponding relevant video of associated video.
Using device as shown in Figure 4, by the identification information of the application of application download platform side and application associated video point Platform side is enjoyed to be integrated in using a corresponding information aggregate using the identification information of corresponding associated video with this；And determine Respectively apply the correlation between corresponding set.
In application associated video sharing platform side, the corresponding associated video of intended application is directed to detecting that user exists In the case of user behavior, it may be determined that go out answering in information aggregate of the information aggregate corresponding with intended application with correlation With, and related to the associated video corresponding to intended application determined by the lateral user's recommendation of application associated video sharing platform Application.
It should be noted that each embodiment corresponding to above-mentioned video recommendations device, you can individually implement also may be used Partly or entirely to combine implementation, specific embodiment is determined by one skilled in the art, and the present invention is herein not It is construed as limiting.Likewise, each embodiment corresponding to above application recommendation apparatus, you can individually implement can also part or Implementation all is combined, specific embodiment is determined by one skilled in the art, and the present invention is not limited thereto.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to Non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only will including those Element, but also including other elements that are not explicitly listed, or further include as this process, method, article or equipment Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that Also there are other identical element in process, method, article or equipment including the key element.
Each embodiment in this specification is described using relevant mode, identical similar portion between each embodiment Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for device For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method Part explanation.
Can one of ordinary skill in the art will appreciate that realizing that all or part of step in above method embodiment is To instruct relevant hardware to complete by program, the program can be stored in computer read/write memory medium, The storage medium designated herein obtained, such as：ROM/RAM, magnetic disc, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention It is interior.

Claims (14)

  1. A kind of 1. video recommendation method, it is characterised in that including：
    Detect user and be directed to the user behavior of intended application in application download platform side；
    In the case where detecting that user has the user behavior for intended application,
    The definite information aggregate having with the information aggregate corresponding to intended application corresponding at least one application of correlation, one Information aggregate corresponding to a application includes sharing using the identification information of the application of download platform side and using associated video Platform side applies the identification information of corresponding associated video with this；
    The mark that corresponding associated video is applied with this in information aggregate according to corresponding to identified, at least one application Information, determines associated video sharing platform side and the relevant video of intended application；
    Recommend the identified and relevant video of intended application in the lateral user of application download platform；
    Wherein, the letter corresponding at least one application for determining that there is correlation with the information aggregate corresponding to intended application The method of breath set includes：
    Determine the size of the multi-feature vector of intended application and the corresponding information aggregate of other application, wherein, each The multi-feature vector of application includes that M is default to apply corresponding characteristic element with this, it is N number of it is default with this apply it is corresponding The corresponding characteristic element of associated video, M >=1, N >=1；
    Wherein, include with using corresponding characteristic element：The characteristic element determined according to the user behavior of application download platform side, And recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to application The characteristic element that the user behavior of associated video sharing platform side determines, and recorded according to user behavior and determine its size；
    According to default vector similarity computational methods, determine the corresponding information aggregate of intended application multi-feature vector and its It is using the similarity between the multi-feature vector of corresponding information aggregate；
    If any multi-feature vector using corresponding information aggregate information aggregate corresponding with intended application is comprehensive special The similarity of sign vector is more than predetermined threshold value, it is determined that this applies corresponding information aggregate information aggregate corresponding with intended application Between there is correlation.
  2. 2. the method as described in claim 1, it is characterised in that described to be further included with using corresponding characteristic element：According to should The characteristic element that relevant information determines, and preset its size.
  3. 3. method as claimed in claim 1 or 2, it is characterised in that determining have with the information aggregate corresponding to intended application After having the information aggregate corresponding at least one application of correlation, further include：
    The identification information of the application in information aggregate according to corresponding to identified, at least one application, determines that application is downloaded Platform side and the relevant application of intended application；
    Recommend the identified and relevant application of intended application in the lateral user of application download platform.
  4. 4. method as claimed in claim 1, it is characterised in that vector similarity computational methods are selected from：
    One kind in cosine similarity computational methods, Euclidean distance computational methods and Jie Kade distance calculating methods.
  5. 5. one kind applies recommendation method, it is characterised in that including：
    Detect user behavior of the user in application associated video sharing platform side for the associated video corresponding to intended application；
    In the case where detecting that user has the user behavior for the corresponding associated video of intended application,
    The definite information aggregate having with the information aggregate corresponding to intended application corresponding at least one application of correlation, one Information aggregate corresponding to a application includes sharing using the identification information of the application of download platform side and using associated video Platform side applies the identification information of corresponding associated video with this；
    The identification information of the application in information aggregate according to corresponding to identified, at least one application, determines under application Carrying platform side and the relevant application of associated video corresponding to intended application；
    It is related to the associated video corresponding to intended application determined by recommending in the lateral user of application associated video sharing platform Application；
    Wherein, the letter corresponding at least one application for determining that there is correlation with the information aggregate corresponding to intended application The method of breath set includes：
    Determine the size of the multi-feature vector of intended application and the corresponding information aggregate of other application, wherein, each The multi-feature vector of application includes that M is default to apply corresponding characteristic element with this, it is N number of it is default with this apply it is corresponding The corresponding characteristic element of associated video, M >=1, N >=1；
    Wherein, include with using corresponding characteristic element：The characteristic element determined according to the user behavior of application download platform side, And recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to application The characteristic element that the user behavior of associated video sharing platform side determines, and recorded according to user behavior and determine its size；
    According to default vector similarity computational methods, determine the corresponding information aggregate of intended application multi-feature vector and its It is using the similarity between the multi-feature vector of corresponding information aggregate；
    If any multi-feature vector using corresponding information aggregate information aggregate corresponding with intended application is comprehensive special The similarity of sign vector is more than predetermined threshold value, it is determined that this applies corresponding information aggregate information aggregate corresponding with intended application Between there is correlation.
  6. 6. method as claimed in claim 5, it is characterised in that described to be further included with using corresponding characteristic element：According to should The characteristic element that relevant information determines, and preset its size.
  7. 7. the method as described in claim 5 or 6, it is characterised in that determining have with the information aggregate corresponding to intended application After having the information aggregate corresponding at least one application of correlation, further include：
    The identification information of the video in information aggregate according to corresponding to identified, at least one application, determines associated video Sharing platform side and the relevant video of associated video corresponding to intended application；
    Determined by recommending in the lateral user of associated video sharing platform with the associated video corresponding to intended application is relevant regards Frequently.
  8. A kind of 8. video recommendations device, it is characterised in that including：
    First user behavior detection module, the user behavior of intended application is directed to for detecting user in application download platform side；
    First information set determining module, target is directed to for detecting that user exists in the first user behavior detection module In the case of the user behavior of application, at least one application that there is correlation with the information aggregate corresponding to intended application is determined Corresponding information aggregate, the information aggregate corresponding to an application include the identification information of the application using download platform side And application associated video sharing platform side applies the identification information of corresponding associated video with this；
    First video determining module, for being answered in the information aggregate according to corresponding to identified, at least one application with this With the identification information of corresponding associated video, associated video sharing platform side and the relevant video of intended application are determined；
    First video recommendations module, for determined by recommending in the lateral user of application download platform with intended application is relevant regards Frequently；
    Wherein, the first information set determining module includes：
    First multi-feature vector determination sub-module, for determining intended application and the corresponding information aggregate of other application The size of multi-feature vector, wherein, multi-feature vector of each application includes that M is default to apply corresponding spy with this Element is levied, it is N number of default to apply the corresponding characteristic element of corresponding associated video, M >=1, N >=1 with this；
    Wherein, include with using corresponding characteristic element：The characteristic element determined according to the user behavior of application download platform side, And recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to application The characteristic element that the user behavior of associated video sharing platform side determines, and recorded according to user behavior and determine its size；
    First similarity measure submodule, for according to default vector similarity computational methods, determining that intended application is corresponding Similarity between the multi-feature vector of the multi-feature vector of information aggregate information aggregate corresponding with other application；
    First correlation determination sub-module, if should for any multi-feature vector using corresponding information aggregate and target It is more than predetermined threshold value with the similarity of the multi-feature vector of corresponding information aggregate, it is determined that this applies corresponding information aggregate There is correlation between information aggregate corresponding with intended application.
  9. 9. device as claimed in claim 8, it is characterised in that described to be further included with using corresponding characteristic element：According to should The characteristic element that relevant information determines, and preset its size.
  10. 10. device as claimed in claim 8 or 9, it is characterised in that further include：First application determining module and the first application Recommending module；It is right with intended application institute that the first application determining module is used to determine in the first information set determining module After the information aggregate answered has the information aggregate corresponding at least one application of correlation,
    The identification information of the application in information aggregate according to corresponding to identified, at least one application, determines that application is downloaded Platform side and the relevant application of intended application；
    Described first applies recommending module, identified related to intended application for recommending in the lateral user of application download platform Application.
  11. 11. device as claimed in claim 8, it is characterised in that vector similarity computational methods are selected from：
    One kind in cosine similarity computational methods, Euclidean distance computational methods and Jie Kade distance calculating methods.
  12. 12. one kind applies recommendation apparatus, it is characterised in that including：
    Second user behavioral value module is right for intended application institute in application associated video sharing platform side for detecting user The user behavior for the associated video answered；
    Second information aggregate determining module, target is directed to for detecting that user exists in the second user behavioral value module In the case of user behavior using corresponding associated video, determine that there is correlation with the information aggregate corresponding to intended application At least one application corresponding to information aggregate, information aggregate corresponding to an application include using download platform side should The identification information of application and application associated video sharing platform side apply the identification information of corresponding associated video with this；
    Second applies determining module, for the application in the information aggregate according to corresponding to identified, at least one application Identification information, determine using the relevant application of associated video corresponding to download platform side and intended application；
    Second applies recommending module, for recommending identified and intended application in the lateral user of application associated video sharing platform The relevant application of corresponding associated video；
    Wherein, the second information aggregate determining module includes：
    Second multi-feature vector determination sub-module, for determining intended application and the corresponding information aggregate of other application The size of multi-feature vector, wherein, multi-feature vector of each application includes that M is default to apply corresponding spy with this Element is levied, it is N number of default to apply the corresponding characteristic element of corresponding associated video, M >=1, N >=1 with this；
    Wherein, include with using corresponding characteristic element：The characteristic element determined according to the user behavior of application download platform side, And recorded according to user behavior and determine its size；Characteristic element corresponding with the corresponding associated video of application includes：According to application The characteristic element that the user behavior of associated video sharing platform side determines, and recorded according to user behavior and determine its size；
    Second similarity measure submodule, for according to default vector similarity computational methods, determining that intended application is corresponding Similarity between the multi-feature vector of the multi-feature vector of information aggregate information aggregate corresponding with other application；
    Second correlation determination sub-module, if should for any multi-feature vector using corresponding information aggregate and target It is more than predetermined threshold value with the similarity of the multi-feature vector of corresponding information aggregate, it is determined that this applies corresponding information aggregate There is correlation between information aggregate corresponding with intended application.
  13. 13. device as claimed in claim 12, it is characterised in that described to be further included with using corresponding characteristic element：According to The characteristic element that the relevant information of application determines, and preset its size.
  14. 14. the device as described in claim 12 or 13, it is characterised in that further include：Second video determining module and second regard Frequency recommending module；The second video determining module is used to determine and intended application institute in the second information aggregate determining module Corresponding information aggregate have correlation at least one application corresponding to information aggregate after, according to it is identified, at least one The identification information of the video in information aggregate corresponding to a application, determines that associated video sharing platform side and intended application institute are right The relevant video of associated video answered；
    The second video recommendations module, for recommending identified and intended application in the lateral user of associated video sharing platform The relevant video of corresponding associated video.
CN201510727303.8A 2015-10-30 2015-10-30 Using recommendation method, apparatus and video recommendation method, device Active CN105307023B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510727303.8A CN105307023B (en) 2015-10-30 2015-10-30 Using recommendation method, apparatus and video recommendation method, device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510727303.8A CN105307023B (en) 2015-10-30 2015-10-30 Using recommendation method, apparatus and video recommendation method, device

Publications (2)

Publication Number Publication Date
CN105307023A CN105307023A (en) 2016-02-03
CN105307023B true CN105307023B (en) 2018-04-13

Family

ID=55203693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510727303.8A Active CN105307023B (en) 2015-10-30 2015-10-30 Using recommendation method, apparatus and video recommendation method, device

Country Status (1)

Country Link
CN (1) CN105307023B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106331158A (en) * 2016-09-27 2017-01-11 珠海市魅族科技有限公司 Information synchronization method and apparatus
CN107223341A (en) * 2017-04-01 2017-09-29 深圳市智晟达科技有限公司 The method and commending system for recommending video are used according to app

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102999588A (en) * 2012-11-15 2013-03-27 广州华多网络科技有限公司 Method and system for recommending multimedia applications
WO2014109388A1 (en) * 2013-01-11 2014-07-17 日本電気株式会社 Text mining device, text mining system, text mining method, and recording medium
CN103942316A (en) * 2014-04-24 2014-07-23 江西迈思科技有限公司 Information processing method and device
CN104158865A (en) * 2014-08-01 2014-11-19 北京奇虎科技有限公司 Method and system for pushing applications to terminal
CN104243590A (en) * 2014-09-19 2014-12-24 广州华多网络科技有限公司 Resource object recommendation method and device
CN104239571A (en) * 2014-09-30 2014-12-24 北京奇虎科技有限公司 Method and device for application recommendation
CN104572846A (en) * 2014-12-12 2015-04-29 百度在线网络技术（北京）有限公司 Method, device and system for recommending hot words
CN104717302A (en) * 2015-03-31 2015-06-17 北京奇艺世纪科技有限公司 Method and device for information push

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102999588A (en) * 2012-11-15 2013-03-27 广州华多网络科技有限公司 Method and system for recommending multimedia applications
WO2014109388A1 (en) * 2013-01-11 2014-07-17 日本電気株式会社 Text mining device, text mining system, text mining method, and recording medium
CN104919458A (en) * 2013-01-11 2015-09-16 日本电气株式会社 Text mining device, text mining system, text mining method, and recording medium
CN103942316A (en) * 2014-04-24 2014-07-23 江西迈思科技有限公司 Information processing method and device
CN104158865A (en) * 2014-08-01 2014-11-19 北京奇虎科技有限公司 Method and system for pushing applications to terminal
CN104243590A (en) * 2014-09-19 2014-12-24 广州华多网络科技有限公司 Resource object recommendation method and device
CN104239571A (en) * 2014-09-30 2014-12-24 北京奇虎科技有限公司 Method and device for application recommendation
CN104572846A (en) * 2014-12-12 2015-04-29 百度在线网络技术（北京）有限公司 Method, device and system for recommending hot words
CN104717302A (en) * 2015-03-31 2015-06-17 北京奇艺世纪科技有限公司 Method and device for information push

Also Published As

Publication number Publication date
CN105307023A (en) 2016-02-03

Similar Documents

Publication Publication Date Title
Morris Curation by code: Infomediaries and the data mining of taste
CN102693495B (en) Filtering and the method and computer readable storage medium for promoting application shop application
Liang et al. Privacy protection and self-disclosure across societies: A study of global Twitter users
US9269090B2 (en) Method, apparatus and computer program product for providing indications regarding recommended content
CN104731950B (en) A kind of video recommendation method and device
CN102446330B (en) Content recommendation system and method
CA3153598A1 (en) Method of and device for predicting video playback integrity
US8626771B2 (en) Container reputation
US20100088327A1 (en) Method, Apparatus, and Computer Program Product for Identifying Media Item Similarities
CN104346464B (en) Processing method, device and the browser client of web page element information
CN102662919A (en) Bookmarking segments of content
KR20110128953A (en) System and methods for promotional media item selection and promotional program unit generation
CN108260008A (en) A kind of video recommendation method, device and electronic equipment
CN107562848A (en) A kind of video recommendation method and device
CN106961636A (en) Commodity information recommendation method and device and electronic equipment
KR102505973B1 (en) Image processing apparatus, control method thereof and computer readable medium having computer program recorded therefor
CN105307023B (en) Using recommendation method, apparatus and video recommendation method, device
EP3346396A1 (en) Multimedia resource quality assessment method and apparatus
CN107454442A (en) A kind of method and apparatus for recommending video
US8838729B2 (en) Gathering statistics based on container exchange
KR20100045195A (en) Method and apparatus for recommending content
CN106452808A (en) Data processing method and data processing device
CN106658161A (en) Set-top box information push method based on connection relation and set-top box
US8429691B2 (en) Computational recommendation engine
US20150331863A1 (en) Selection method, method for maintaining data list and electronic device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant