CN104918118A - Video recommendation method and device based on historic information - Google Patents
Video recommendation method and device based on historic information Download PDFInfo
- Publication number
- CN104918118A CN104918118A CN201510341831.XA CN201510341831A CN104918118A CN 104918118 A CN104918118 A CN 104918118A CN 201510341831 A CN201510341831 A CN 201510341831A CN 104918118 A CN104918118 A CN 104918118A
- Authority
- CN
- China
- Prior art keywords
- video
- feature
- type
- intensity
- feature group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4665—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms involving classification methods, e.g. Decision trees
-
- 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
- H04N21/462—Content or additional data management, e.g. creating a master electronic program guide from data received from the Internet and a Head-end, controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
-
- 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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- 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
Abstract
The invention discloses a video recommendation method and device based on historic information. The device comprises an information acquisition module; a feature demand strength acquisition module, and a video recommendation module, wherein the feature demand strength acquisition module comprises a feature group determination sub-module for determining each feature group in each of videos of a type according to the feature of each video in the videos of the type, and a feature grouping sub-module for dividing each video in the videos of the type into each feature group. According to the method and device disclosed by the embodiment of the invention, the multi-type and multi-feature video recommendation results can be simply and effectively provided, and a complex video recommendation demand of a user is satisfied.
Description
The divisional application that patent application of the present invention is the applying date is on October 24th, 2012, application number is 201210408686.9, name is called the Chinese invention patent application of " video recommendation method and device based on historical information ".
Technical field
The present invention relates to Online Video technology, particularly relate to a kind of video recommendation method based on historical information and device.
Background technology
Online Video is recommended to be that video website helps user search and watch the Method and kit for of certain specific area video.Relative to traditional videogram browsing mode or video search mode, video recommendations can when the uncertain suitable search word of user, by analyzing user's historical behavior, find the specific area of user's request, recommend in the field, avoid the input of search word and the repeatedly click process of hierarchical directory, make to search and the video watching certain particular type is more easily simple.
Existing video recommendations technology, mainly comprises two kinds of methods-based on video collaborative filtering recommending with based on user collaborative filtered recommendation.The former is by calculating the similarity of video and video, by the video recommendations the most similar to viewing recording of video to user.The latter is then based on viewing record, and calculate user's similarity, the video recommendations similar user seen recently is to user.It is all that whole viewing records based on user are analyzed that these two kinds of modes are given tacit consent to, and the result returned is the video with all history video all similar, and for the user that hobby is more single, recommendation results is better.Such as user has seen one or multi-section action movie, releases action movie the hottest recently, and user experiences can be relatively good.
Fig. 1 shows the flow chart of the video recommendation method of prior art (CN102306178A, " video recommendation method and device ").As shown in Figure 1, in the prior art, (1) extracts the VIDEO (video) of each COOKIE viewing as training sample from user journal database.(2) calculate the transition probability pair in described training sample between all COOKIE and VIDEO, obtain the transition probability matrix of COOKIE to VIDEO and the transition probability matrix of VIDEO to COOKIE.(3) according to transition probability matrix and VIDEO to the COOKIE matrix of described COOKIE to VIDEO, the transition probability matrix between VIDEO is obtained.(4) obtain recommended models according to the transition probability matrix between VIDEO, and embed described user video search system to return recommendation results to user.
Prior art can meet the user's request that video type and feature have single hobby.But along with the surf the Net behavior of viewing video of the development of internet video website and user increases, the demand of user to viewing video type and feature is more various, the video meeting all types and feature will not exist or second-rate, but be likely the video comprised compared with the outstanding feature of multiple features neither one.
In the prior art scheme, eurypalynous video recommendations cannot be met: video type is a strong feature of video resource, and dissimilar video recommendations user impression is often poor.The user spending several hours love South Korean TV soaps weekend is prepared to one, recommend a love film only having 1.5 hours, user experiences not so good, sees that the user of the short-sighted frequency of physical culture recommends the physical film of more than 1.5 hours obviously also not meet consumers' demand equally to liking.In addition, the video recommendations of multiple features also cannot be met: the video of similar or identical feature is applicable combine recommendation, and the video of different characteristic is then not suitable for recommending together.As " Infernal Affairs 1 ", " Infernal Affairs 2 " are applicable to recommending together, recommend " Infernal Affair 3 ", " eavesdropping wind and cloud " relatively good; " pen celestial ", " peach elder sister " is then improper recommends together.
Summary of the invention
In view of the above problems, propose the present invention, to provide a kind of overcoming the problems referred to above or the video recommendation method based on historical information solved the problem at least in part and device.
According to one aspect of the present invention, provide a kind of video recommendation method based on historical information, comprise the following steps:
Obtain the video-see recorded information of user;
According to described video-see recorded information, calculate the type demand intensity of the viewed all types of videos of user;
For each type video, divide into groups according to video features, and obtain the feature requirement intensity of each feature group; And
Based on described type demand intensity and/or described feature requirement intensity, recommend video to user.
According to embodiments of the invention, the described step calculating the type demand intensity of the viewed all types of videos of user according to described video-see recorded information comprises:
The type of the video that counting user is viewed;
For each type video, according to the type number of videos and all video total quantitys, calculate the content requirements intensity of the type video;
The time order and function position residing in the viewing time of all videos according to the viewing time of the type video, calculates the time demand intensity of the type video; And
Based on described content requirements intensity and described time demand intensity, calculate the type demand intensity of the type video.
According to embodiments of the invention, described based on described content requirements intensity and described time demand intensity, calculate in the step of type demand intensity of the type video, based on type demand intensity described in following formulae discovery:
Type demand intensity=a × content requirements intensity+(1-a) × time demand intensity, wherein a is predefined constant.
According to embodiments of the invention, described each type video, the step of carrying out dividing into groups according to video features to be comprised:
According to the feature of video each in the type video, determine each feature group in the type video; And
Each video in the type video is divided in each feature group according to its feature.
According to embodiments of the invention, the step of the described feature according to video each in the type video, each feature group determined in the type video utilizes Canopy clustering algorithm to perform, and comprises the following steps:
Arrange the first distance threshold and second distance threshold value, wherein said first distance threshold is less than described second distance threshold value;
Video feature difference being less than described first distance threshold is divided in identical feature group;
Feature difference with a feature group is less than described second distance threshold value but the video being greater than described first distance threshold is divided into this feature group, and is divided in independent feature group in addition; And
According to the video in feature group, calculate the central feature of each feature group.
According to embodiments of the invention, describedly utilize K-Means clustering algorithm to perform according to its feature step be divided in each feature group each video in the type video, comprise the following steps:
Calculate the difference of the central feature of described each video and each feature group;
Described each video is divided in the feature group minimum with its difference;
According to the video in feature group, recalculate the central feature of each feature group; And
Repeat above-mentioned steps, until the difference between the central feature of the central feature of described each feature group and the front each feature group once calculated is less than predefined threshold value.
According to embodiments of the invention, the feature requirement intensity of feature group is that the time order and function position residing in the viewing time of the video of all feature groups according to the viewing time of the video in this feature group is determined.
According to embodiments of the invention, the feature requirement intensity of feature group is that time order and function position residing in the viewing time according to viewing time video of up-to-date viewing in each feature group of the video of up-to-date viewing in this feature group is determined.
According to embodiments of the invention, described based on described type demand intensity and/or described feature requirement intensity, recommend the step of video to comprise to user:
According to type demand intensity order from high to low, recommend all types of videos to user; And
For each type video, according to feature requirement intensity order from high to low, recommend the video of each feature group to user.
According to embodiments of the invention, described based on described type demand intensity and/or described feature requirement intensity, recommend the step of video also to comprise to user:
Change the request of video type in response to user, switch the video type of recommending to user; And/or
Change the request of video features group in response to user, switch the video features group of recommending to user.
According to embodiments of the invention, described video-see recorded information is included in the Cookie file of user.
According to another aspect of the present invention, provide a kind of video recommendations device based on historical information, comprising:
Data obtaining module, for obtaining the video-see recorded information of user;
Type demand intensity computing module, for according to described video-see recorded information, calculates the type demand intensity of the viewed all types of videos of user;
Feature requirement intensity acquisition module, for for each type video, divides into groups according to video features, and obtains the feature requirement intensity of each feature group; And
Video recommendations module, for based on described type demand intensity and/or described feature requirement intensity, recommends video to user.
According to embodiments of the invention, described type demand intensity computing module comprises:
Type statistics submodule, for the type of the viewed video of counting user;
Content requirements Strength co-mputation submodule, for for each type video, according to the type number of videos and all video total quantitys, calculates the content requirements intensity of the type video;
Time demand intensity calculating sub module, for the time order and function position residing in the viewing time of all videos according to the viewing time of the type video, calculates the time demand intensity of the type video; And
Type demand intensity calculating sub module, for based on described content requirements intensity and described time demand intensity, calculates the type demand intensity of the type video.
According to embodiments of the invention, described type demand intensity calculating sub module (203d) is based on type demand intensity described in following formulae discovery:
Type demand intensity=a × content requirements intensity+(1-a) × time demand intensity, wherein a is predefined constant.
According to embodiments of the invention, described feature requirement intensity acquisition module comprises:
Feature group determination submodule, for the feature according to video each in the type video, determines each feature group in the type video; And
Feature grouping submodule, for being divided into each video in the type video in each feature group according to its feature.
According to embodiments of the invention, described feature group determination submodule utilizes Canopy clustering algorithm, according to the feature of video each in the type video, determines each feature group in the type video, wherein said feature group determination submodule:
Arrange the first distance threshold and second distance threshold value, wherein said first distance threshold is less than described second distance threshold value;
Video feature difference being less than described first distance threshold is divided in identical feature group;
Feature difference with a feature group is less than described second distance threshold value but the video being greater than described first distance threshold is divided into this feature group, and is divided in independent feature group in addition; And
According to the video in feature group, calculate the central feature of each feature group.
According to embodiments of the invention, described feature grouping submodule utilizes K-Means clustering algorithm to be divided in each feature group by each video in the type video according to its feature, wherein said feature grouping submodule (205b):
Calculate the difference of the central feature of described each video and each feature group;
Described each video is divided in the feature group minimum with its difference;
According to the video in feature group, recalculate the central feature of each feature group; And
Repeat above-mentioned steps, until the difference between the central feature of the central feature of described each feature group and the front each feature group once calculated is less than predefined threshold value.
According to embodiments of the invention, the time order and function position that described feature requirement intensity acquisition module is residing in the viewing time of the video of all feature groups according to the viewing time of the video in this feature group, determines the feature requirement intensity of feature group.
According to embodiments of the invention, described feature requirement intensity acquisition module, according to time order and function position residing in the viewing time of viewing time video of up-to-date viewing in each feature group of the video of up-to-date viewing in this feature group, determines the feature requirement intensity of feature group.
According to embodiments of the invention, wherein said video recommendations module comprises:
Type recommends submodule, for according to type demand intensity order from high to low, recommends all types of videos to user; And
Feature group recommends submodule, for for each type video, according to feature requirement intensity order from high to low, recommends the video of each feature group to user.
According to embodiments of the invention, described video recommendations module also comprises:
Type switching submodule, for changing the request of video type in response to user, switches the video type of recommending to user; And/or
Feature group switching submodule, for changing the request of video features group in response to user, switches the video features group of recommending to user.
According to embodiments of the invention, described video-see recorded information is included in the Cookie file of user.
The invention provides the video recommendation method based on historical information and device.According to embodiments of the invention, according to the video-see recorded information of user, calculate the type demand intensity of all types of video, video in each type video is divided into each feature group, and obtain the feature requirement intensity of each feature group, finally recommend video based on type demand intensity and/or feature requirement intensity to user, the video recommendations result of polymorphic type and multiple features can be provided simply and effectively, meet the video recommendations demand of user's complexity.Relative to traditional video recommendation method, the present invention can calculate the type demand intensity of user for dissimilar video, and recommend various types of videos such as film, TV play, animation play, variety show, sports cast with different priority accordingly, and according to the feature requirement intensity of user, the video of the different characteristic under particular video frequency type is recommended with different priority, as the romance movie in film types, science fiction film, war film, domestic play, historical play etc. in TV play type.In addition, in response to the request of user, the video type and/or video features group of recommending to user can also be switched.
Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to technological means of the present invention can be better understood, and can be implemented according to the content of specification, and can become apparent, below especially exemplified by the specific embodiment of the present invention to allow above and other objects of the present invention, feature and advantage.
Accompanying drawing explanation
By reading hereafter detailed description of the preferred embodiment, various other advantage and benefit will become cheer and bright for those of ordinary skill in the art.Accompanying drawing only for illustrating the object of preferred implementation, and does not think limitation of the present invention.And in whole accompanying drawing, represent identical parts by identical reference symbol.In the accompanying drawings:
Fig. 1 is the flow chart of the video recommendation method of prior art;
Fig. 2 is according to an embodiment of the invention based on the flow chart of the video recommendation method of historical information;
Fig. 3 is according to an embodiment of the invention based on the block diagram of the video recommendations device of historical information; And
Fig. 4 is the block diagram of video recommendations module according to an embodiment of the invention.
Embodiment
Below with reference to accompanying drawings exemplary embodiment of the present disclosure is described in more detail.Although show exemplary embodiment of the present disclosure in accompanying drawing, however should be appreciated that can realize the disclosure in a variety of manners and not should limit by the embodiment set forth here.On the contrary, provide these embodiments to be in order to more thoroughly the disclosure can be understood, and complete for the scope of the present disclosure can be conveyed to those skilled in the art.
Fig. 2 schematically illustrates according to an embodiment of the invention based on the flow chart of the video recommendation method of historical information.As shown in Figure 2, in video recommendation method 100 according to an embodiment of the invention, at the beginning, step S101 is performed: the video-see recorded information obtaining user; Then, perform step S103: according to described video-see recorded information, calculate the type demand intensity of the viewed all types of videos of user; Then, step S105 is performed: for each type video, divide into groups according to video features, and obtain the feature requirement intensity of each feature group; Finally, step S107 is performed: based on described type demand intensity and/or described feature requirement intensity, recommend video to user.Below each step is above described in detail.
First, in step S101, obtain the video-see recorded information of user.According to embodiments of the invention, the Cookie file of user can comprise described video-see recorded information, namely, when user watches Online Video at every turn, capital leaves video-see record in Cookie file, and this video-see record at least can comprise the information such as ID title, type, feature, viewing time, author, length of a film, publisher of all videos that user watches.But scope of the present invention is not limited to this, video-see recorded information can also be included in other file of user side or server end.
When user is by such as browser access Online Video website, browser can send page request to Website server, comprising Cookie file, now, just can obtain the Cookie file of user, and obtains the video-see recorded information of user wherein.
Next, in step s 103, according to described video-see recorded information, the type demand intensity of the viewed all types of videos of user is calculated.According to embodiments of the invention, described step S103 can comprise sub-step S103a, S103b, S103c and S103d.
In sub-step S103a, the type of the video that counting user is viewed, can use count distinct function herein, calculate the total quantity TypeN of non-duplicate type.Such as, by the user video viewing recorded information in Cookie file, find viewed 3 films of user, 2 TV play, 1 animation play, new and old by viewing time, film is up-to-date, and TV play is taken second place, and animation play is the oldest, and type total quantity TypeN is 3.
Then, in sub-step S103b, for each type video, according to the type number of videos and all video total quantitys, calculate the content requirements intensity of the type video, its computing formula is: ContentReq
iin=video, type is Type
ithe all video total quantitys of quantity ÷ of video.Still for situation above, respectively, film: 3, TV play: 2, animation is acute: 1 for the content requirements intensity of the video of three types.
Then, in sub-step S103c, the time order and function position residing in the viewing time of all videos according to the viewing time of the type video, calculate the time demand intensity of the type video, its computing formula is: FreshReq
i=Type
ithe time order and function position sum of the viewing time of the time order and function position ÷ all types video of the viewing time of video.Still for situation above, respectively, film: 3, TV play: 2, animation is acute: 1 for the time demand intensity of the video of three types.Alternatively, the viewing time only getting the video that viewing time is up-to-date in every type calculates.
Finally, in sub-step S103d, can based on described content requirements intensity and described time demand intensity, calculate the type demand intensity of the type video, its computing formula is:
TypeReq
i＝a*ContentReq
i+(1-a)*FreshReq
i
Wherein, a is fitting parameter, can choose according to actual needs, such as, get a=0.5.In the above example, respectively, film: 3, TV play: 2, animation is acute: 1 for the type demand intensity of the video of three types.
After step s 103, step S105 is performed: for each type video, divide into groups according to video features, and obtain the feature requirement intensity of each feature group.Wherein, described sub-step S105a and S105b is comprised for each type video, the step of carrying out dividing into groups according to video features.
In sub-step S105a, according to the feature of video each in the type video, determine each feature group in the type video, count distinct function can be utilized to determine the quantity of non-repeating features group.Alternatively, sub-step S105a can utilize Canopy clustering algorithm to perform.In Canopy clustering algorithm, arrange the first distance threshold and second distance threshold value, wherein said first distance threshold is less than described second distance threshold value, and the value of these two distance thresholds can be chosen according to actual needs; Video feature difference being less than described first distance threshold is divided in identical feature group; Feature difference with a feature group is less than described second distance threshold value but the video being greater than described first distance threshold is divided into this feature group, and is divided in independent feature group in addition; According to the video in feature group, calculate the central feature of each feature group.Because the difference in each feature group between video very little (similarity is very high), so Canopy clustering algorithm can provide feature group number and each group switching centre feature; Because certain video may be assigned to and allly be less than in the feature group of described second feature threshold value with its feature difference, namely a video council is assigned in multiple feature group, and therefore this is a packet mode having intersection.
Then, in sub-step S105b, each video in the type video is divided in each feature group according to its feature.Alternatively, sub-step S105b can utilize K-Means clustering algorithm to perform, and the computing formula of K-Means clustering algorithm is: Cluster
i=[video
jthe set of composition, if video
jthe words that distance i-th cluster centre point is nearest].In K-Means clustering algorithm, initial setting K is the group number of Canopy cluster, and K central point is the central point of Canopy Clustering, and circulation cluster is not until K central point moves (new central point and former central point are apart from enough little) substantially; Often taking turns cluster is the distance calculating all videos and K central point, is assigned in the group corresponding apart from minimum central point, after all video packets complete, according to all videos in each group, recalculates K central point.Because algorithm the convergence speed is very fast for this reason, therefore K-Means cluster is a highly effective algorithm; And during algorithmic statement, then carry out taking turns calculating, grouping can not be optimized, therefore this algorithm or the high algorithm of an accuracy rate; In addition, all videos have all only been assigned in a nearest group, and therefore this is an achiasmate packet mode.
For example, suppose that user have viewed " Infernal Affairs 1 ", " Infernal Affairs 2 ", " peach elder sister " these 3 films, " flames of war northwest wolf ", " children's stories 1/2nd " these 2 TV play, " sea thief king " this 1 animation play.Carry out cluster to film types, cluster numbers is 2, and fisrt feature group comprises " Infernal Affairs 1 " and " Infernal Affairs 2 ", and second feature group comprises " peach elder sister ".Carry out cluster to TV play type, cluster numbers is 2, and fisrt feature group comprises " flames of war northwest wolf ", and second feature group comprises " children's stories 1/2nd ", and animation cluster feature group is 1, comprises " sea thief king ".Respectively the video of each feature group is recommended, the fisrt feature group of film types can recommend out the film between policemen and bandits such as " Infernal Affair 3 ", " eavesdropping wind and cloud ", and the second feature group of film types can recommend out the emotion film such as " mist of Tian Shuiwei and night ", " paradise, ocean "; The fisrt feature group of TV play type can recommend out " positive person is unmatched ", " sharp knife team " etc. military acute, and the second feature group of TV play type can recommend out the love story such as " love apartment 3 ", " my family is in the family way "; The feature group of the acute type of animation can recommend out risk animations such as " the U.S. sections of sea thief Wang Na " acute.
According to embodiments of the invention, the feature requirement intensity of feature group can be that the time order and function position residing in the viewing time of the video of all feature groups according to the viewing time of the video in this feature group is determined.Alternatively, described feature requirement intensity can be that time order and function position residing in viewing time according to viewing time video of up-to-date viewing in each feature group of the video of up-to-date viewing in this feature group is determined.Such as, in the above example, suppose in the video of film types, " Infernal Affairs 2 " in fisrt feature group is the video of up-to-date viewing in this feature group, and " the peach elder sister " in second feature group is the video of up-to-date viewing in this feature group, and the viewing time of " Infernal Affairs 2 " is newer than the viewing time of " peach elder sister ".Therefore, in film types, the feature requirement intensity of fisrt feature group is higher than the feature requirement intensity of second feature group.
Finally, in step s 107, based on described type demand intensity and/or described feature requirement intensity, video is recommended to user.According to embodiments of the invention, step S107 can comprise sub-step S107a and/or S107b.
In sub-step S107a, according to type demand intensity order from high to low, recommend all types of videos to user.With situation above, (TV play: 2, animation is acute: be 1) example, first recommend film to user, secondly recommends TV play to user, and most rear line recommends animation acute for time demand intensity, film: 3.Such as, can represent " film recommendation ", " TV play recommendation ", " animation play is recommended " 3 linking buttons in interface, acquiescence represents the content of " film recommendation ".In addition, the request of video type can be changed in response to user, switch the video type of recommending to user, such as, user can watch the recommendation video in TV play type video and the acute type video of animation respectively by selection " TV play recommendation " or " animation play is recommended ".
In sub-step S107b, for each type video, according to feature requirement intensity order from high to low, recommend the video of each feature group to user.Such as, in the above example, in " film recommendation ", can represent film " Infernal Affairs 1 " viewed before in the fisrt feature group that in film types, feature requirement intensity is the highest, " Infernal Affairs 2 " by the left side, the right represents recommendation film " Infernal Affair 3 ", " eavesdropping wind and cloud " etc. in fisrt feature group.And if user have selected " TV play recommendation ", the recommendation video in the fisrt feature group that in TV play type, feature requirement intensity is the highest then can be represented to user, such as, the left side represents viewing TV play " flames of war northwest wolf " viewed in fisrt feature group, and the right represents the TV play " positive person is unmatched ", " sharp knife team " etc. of recommending in fisrt feature group.
In addition, the request of video features group can also be changed in response to user, switch the video features group of recommending to user.That is, the mode being switched to further feature group video recommendations is provided to user, " changing " linking button such as, is provided in interface.As above example, under " film recommendation " type, by clicking " changing " linking button, can recommend to be switched to second feature group film by fisrt feature group film to recommend: the left side represents film " peach elder sister " viewed in second feature group, and the right represents the emotion films such as " mist of Tian Shuiwei and the night ", " paradise, ocean " of recommending in second feature group; By again clicking " changing " linking button, first group of film can be switched back and recommend.
Those skilled in the art can easy understand, and the mode of above-mentioned showing interface is only example, for helping reader understanding's principle of the present invention, but not limits the scope of the invention to this, and other various mode can also be adopted to arrange interface, to recommend video to user.
The invention provides a kind of video recommendation method.According to embodiments of the invention, according to the video-see recorded information of user, calculate the type demand intensity of all types of video, video in each type video is divided into each feature group, and obtain the feature requirement intensity of each feature group, finally recommend video based on type demand intensity and/or feature requirement intensity to user, the video recommendations result of polymorphic type and multiple features can be provided simply and effectively, meet the video recommendations demand of user's complexity.Relative to traditional video recommendation method, the present invention can calculate the type demand intensity of user for dissimilar video, and recommend film with different priority accordingly, TV play, animation is acute, variety show, various types of video such as sports cast, and according to the feature requirement intensity of user, the video of the different characteristic under particular video frequency type is recommended with different priority, as the romance movie in film types, science fiction film, war film, domestic play in TV play type, historical play etc., like this, can divide into groups to carry out video recommendations to user, and user is preferentially provided the video of favorite feature group.In addition, in response to the request of user, the video type and/or video features group of recommending to user can also be switched.That is, user can be switched to the video recommendations result of the type by the video of click other types; User also by clicking " changing " button, can be switched to the video recommendations result corresponding to other features.
Corresponding with above-mentioned method 100, present invention also offers a kind of video recommendations device 200 based on historical information.Fig. 3 schematically illustrates according to an embodiment of the invention based on the block diagram of the video recommendations device 200 of historical information, and see Fig. 3, this device 200 comprises:
Data obtaining module 201, for obtaining the video-see recorded information of user, this data obtaining module 201 may be used for the step S101 in manner of execution 100;
Type demand intensity computing module 203, for according to described video-see recorded information, calculate the type demand intensity of the viewed all types of videos of user, the type demand intensity computing module 203 may be used for the step S103 in manner of execution 100;
Feature requirement intensity acquisition module 205, for for each type video, divides into groups according to video features, and obtains the feature requirement intensity of each feature group, and this feature requirement intensity acquisition module 205 may be used for the step S105 in manner of execution 100; And
Video recommendations module 207, for based on described type demand intensity and/or described feature requirement intensity, recommend video to user, this video recommendations module 207 may be used for the step S107 in manner of execution 100.
In an embodiment of the present invention, described type demand intensity computing module 203 comprises:
Type statistics submodule 203a, for the type of the viewed video of counting user, it may be used for the sub-step S103a in the step S103 of manner of execution 100;
Content requirements Strength co-mputation submodule 203b, for for each type video, according to the type number of videos and all video total quantitys, calculate the content requirements intensity of the type video, it may be used for the sub-step S103b in the step S103 of manner of execution 100;
Time demand intensity calculating sub module 203c, for the time order and function position residing in the viewing time of all videos according to the viewing time of the type video, calculate the time demand intensity of the type video, it may be used for the sub-step S103c in the step S103 of manner of execution 100; And
Type demand intensity calculating sub module 203d, for based on described content requirements intensity and described time demand intensity, calculate the type demand intensity of the type video, it may be used for the sub-step S103d in the step S103 of manner of execution 100, and it can calculate described type demand intensity based on the formula in sub-step S103d above.
In an embodiment of the present invention, described feature requirement intensity acquisition module 205 comprises:
Feature group determination submodule 205a, for the feature according to video each in the type video, determine each feature group in the type video, it may be used for the sub-step S105a in the step S105 of manner of execution 100; And
Feature grouping submodule 205b, for being divided in each feature group according to its feature by each video in the type video, it may be used for the sub-step S105b in the step S105 of manner of execution 100.
In an embodiment of the present invention, described feature group determination submodule 205a utilizes Canopy clustering algorithm, according to the feature of video each in the type video, determines each feature group in the type video, wherein said feature group determination submodule 205a:
Arrange the first distance threshold and second distance threshold value, wherein said first distance threshold is less than described second distance threshold value;
Video feature difference being less than described first distance threshold is divided in identical feature group;
Feature difference with a feature group is less than described second distance threshold value but the video being greater than described first distance threshold is divided into this feature group, and is divided in independent feature group in addition; And
According to the video in feature group, calculate the central feature of each feature group.
In an embodiment of the present invention, described feature grouping submodule 205b utilizes K-Means clustering algorithm to be divided in each feature group by each video in the type video according to its feature, wherein said feature grouping submodule 205b:
Calculate the difference of the central feature of described each video and each feature group;
Described each video is divided in the feature group minimum with its difference;
According to the video in feature group, recalculate the central feature of each feature group; And
Repeat above-mentioned steps, until the difference between the central feature of the central feature of described each feature group and the front each feature group once calculated is less than predefined threshold value.
In an embodiment of the present invention, the time order and function position that described feature requirement intensity acquisition module 205 is residing in the viewing time of the video of all feature groups according to the viewing time of the video in this feature group, determines the feature requirement intensity of feature group.
In an embodiment of the present invention, described feature requirement intensity acquisition module 205, according to time order and function position residing in the viewing time of viewing time video of up-to-date viewing in each feature group of the video of up-to-date viewing in this feature group, determines the feature requirement intensity of feature group.
In an embodiment of the present invention, see Fig. 4, described video recommendations module 207 can comprise:
Type recommends submodule 207a, and for according to type demand intensity order from high to low, recommend all types of videos to user, it may be used for the sub-step S107a in the step S107 of manner of execution 100; And
Feature group recommends submodule 207b, and for for each type video, according to feature requirement intensity order from high to low, recommend the video of each feature group to user, it may be used for the sub-step S107b in the step S107 of manner of execution 100.
In an embodiment of the present invention, described video recommendations module 207 can also comprise:
Type switching submodule, for changing the request of video type in response to user, switches the video type of recommending to user; And/or
Feature group switching submodule, for changing the request of video features group in response to user, switches the video features group of recommending to user.
In an embodiment of the present invention, described video-see recorded information is included in the Cookie file of user.
Because above-mentioned each device embodiment is corresponding with aforementioned approaches method embodiment, therefore no longer each device embodiment is described in detail.
Intrinsic not relevant to any certain computer, virtual system or miscellaneous equipment with display at this algorithm provided.Various general-purpose system also can with use based on together with this teaching.According to description above, the structure constructed required by this type systematic is apparent.In addition, the present invention is not also for any certain programmed language.It should be understood that and various programming language can be utilized to realize content of the present invention described here, and the description done language-specific is above to disclose preferred forms of the present invention.
In specification provided herein, describe a large amount of detail.But can understand, embodiments of the invention can be put into practice when not having these details.In some instances, be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.
Similarly, be to be understood that, in order to simplify the disclosure and to help to understand in each inventive aspect one or more, in the description above to exemplary embodiment of the present invention, each feature of the present invention is grouped together in single embodiment, figure or the description to it sometimes.But, the method for the disclosure should be construed to the following intention of reflection: namely the present invention for required protection requires feature more more than the feature clearly recorded in each claim.Or rather, as claims below reflect, all features of disclosed single embodiment before inventive aspect is to be less than.Therefore, the claims following embodiment are incorporated to this embodiment thus clearly, and wherein each claim itself is as independent embodiment of the present invention.
Those skilled in the art are appreciated that and adaptively can change the module in the device in embodiment and they are arranged in one or more devices different from this embodiment.Some block combiner in embodiment can be become a module or unit or assembly, and multiple submodule or subelement or sub-component can be put them in addition.Except at least some in such feature and/or process or module be mutually repel except, any combination can be adopted to combine all processes of all features disclosed in this specification (comprising adjoint claim, summary and accompanying drawing) and so disclosed any method or equipment or unit.Unless expressly stated otherwise, each feature disclosed in this specification (comprising adjoint claim, summary and accompanying drawing) can by providing identical, equivalent or similar object alternative features replaces.
In addition, those skilled in the art can understand, although embodiments more described herein to comprise in other embodiment some included feature instead of further feature, the combination of the feature of different embodiment means and to be within scope of the present invention and to form different embodiments.Such as, in detail in the claims, the one of any of embodiment required for protection can use with arbitrary compound mode.
Each device embodiment of the present invention with hardware implementing, or can realize with the software module run on one or more processor, or realizes with their combination.It will be understood by those of skill in the art that the some or all functions that microprocessor or digital signal processor (DSP) can be used in practice to realize according to the some or all modules in the device of the embodiment of the present invention.The present invention can also be embodied as part or all the device program (such as, computer program and computer program) for performing method as described herein.Realizing program of the present invention and can store on a computer-readable medium like this, or the form of one or more signal can be had.Such signal can be downloaded from internet website and obtain, or provides on carrier signal, or provides with any other form.
The present invention will be described instead of limit the invention to it should be noted above-described embodiment, and those skilled in the art can design alternative embodiment when not departing from the scope of claims.In the claims, any reference symbol between bracket should be configured to limitations on claims.Word " comprises " not to be got rid of existence and does not arrange element in the claims or step.Word "a" or "an" before being positioned at element is not got rid of and be there is multiple such element.The present invention can by means of including the hardware of some different elements and realizing by means of the computer of suitably programming.In the unit claim listing some devices, several in these devices can be carry out imbody by same hardware branch.Word first, second and third-class use do not represent any order.Can be title by these word explanations.
Claims (10)
1. the video recommendation method based on historical information (100), comprises the following steps:
Obtain the video-see recorded information (S101) of user;
According to described video-see recorded information, calculate the type demand intensity (S103) of the viewed all types of videos of user;
For each type video, divide into groups according to video features, and obtain the feature requirement intensity (S105) of each feature group; And
Based on described type demand intensity and/or described feature requirement intensity, recommend video (S107) to user.
2. the method for claim 1, the wherein said step calculating the type demand intensity (S103) of the viewed all types of videos of user according to described video-see recorded information comprises:
The type (S103a) of the video that counting user is viewed;
For each type video, according to the type number of videos and all video total quantitys, calculate the content requirements intensity (S103b) of the type video;
The time order and function position residing in the viewing time of all videos according to the viewing time of the type video, calculates the time demand intensity (S103c) of the type video; And
Based on described content requirements intensity and described time demand intensity, calculate the type demand intensity (S103d) of the type video.
3. method as claimed in claim 2, wherein described based on described content requirements intensity and described time demand intensity, calculate in the step of type demand intensity (S103d) of the type video, based on type demand intensity described in following formulae discovery:
Type demand intensity=a × content requirements intensity+(1-a) × time demand intensity, wherein a is predefined constant.
4. the method for claim 1, wherein saidly comprises for each type video, the step of carrying out dividing into groups according to video features:
According to the feature of video each in the type video, determine each feature group (S105a) in the type video; And
Each video in the type video is divided in each feature group (S105b) according to its feature.
5. method as claimed in claim 4, the step of the wherein said feature according to video each in the type video, each feature group (S105a) determined in the type video utilizes Canopy clustering algorithm to perform, and comprises the following steps:
Arrange the first distance threshold and second distance threshold value, wherein said first distance threshold is less than described second distance threshold value;
Video feature difference being less than described first distance threshold is divided in identical feature group;
Feature difference with a feature group is less than described second distance threshold value but the video being greater than described first distance threshold is divided into this feature group, and is divided in independent feature group in addition; And
According to the video in feature group, calculate the central feature of each feature group.
6. method as claimed in claim 5, wherein saidly utilizes K-Means clustering algorithm to perform the step that each video in the type video is divided into (S105b) in each feature group according to its feature, comprises the following steps:
Calculate the difference of the central feature of described each video and each feature group;
Described each video is divided in the feature group minimum with its difference;
According to the video in feature group, recalculate the central feature of each feature group; And
Repeat above-mentioned steps, until the difference between the central feature of the central feature of described each feature group and the front each feature group once calculated is less than predefined threshold value.
7. the method as described in any one in claim 1 to 6, wherein the feature requirement intensity of feature group is that the time order and function position residing in the viewing time of the video of all feature groups according to the viewing time of the video in this feature group is determined.
8. method as claimed in claim 7, wherein the feature requirement intensity of feature group is that in viewing time according to viewing time video of up-to-date viewing in each feature group of the video of up-to-date viewing in this feature group, residing time order and function position is determined.
9. the method as described in any one in claim 1 to 6, wherein said based on described type demand intensity and/or described feature requirement intensity, recommend the step of video (S107) to comprise to user:
According to type demand intensity order from high to low, recommend all types of videos (S107a) to user; And/or
For each type video, according to feature requirement intensity order from high to low, recommend the video (S107b) of each feature group to user.
10. one kind based on the video recommendations device (200) of historical information, comprising:
Data obtaining module (201), for obtaining the video-see recorded information of user;
Type demand intensity computing module (203), for according to described video-see recorded information, calculates the type demand intensity of the viewed all types of videos of user;
Feature requirement intensity acquisition module (205), for for each type video, divides into groups according to video features, and obtains the feature requirement intensity of each feature group; And
Video recommendations module (207), for based on described type demand intensity and/or described feature requirement intensity, recommends video to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510341831.XA CN104918118B (en) | 2012-10-24 | 2012-10-24 | Video recommendation method and device based on historical information |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510341831.XA CN104918118B (en) | 2012-10-24 | 2012-10-24 | Video recommendation method and device based on historical information |
| CN201210408686.9A CN102946566B (en) | 2012-10-24 | 2012-10-24 | Video recommending method and device based on historical information |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210408686.9A Division CN102946566B (en) | 2012-10-24 | 2012-10-24 | Video recommending method and device based on historical information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104918118A true CN104918118A (en) | 2015-09-16 |
| CN104918118B CN104918118B (en) | 2019-08-02 |
Family
ID=47729466
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210408686.9A Expired - Fee Related CN102946566B (en) | 2012-10-24 | 2012-10-24 | Video recommending method and device based on historical information |
| CN201510341831.XA Active CN104918118B (en) | 2012-10-24 | 2012-10-24 | Video recommendation method and device based on historical information |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210408686.9A Expired - Fee Related CN102946566B (en) | 2012-10-24 | 2012-10-24 | Video recommending method and device based on historical information |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN102946566B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812834A (en) * | 2016-05-10 | 2016-07-27 | 南京大学 | Video recommendation server, recommendation method and pre-caching method based on cluster information |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN109379608A (en) * | 2018-09-13 | 2019-02-22 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of direct broadcasting room |
| CN110427556A (en) * | 2019-07-30 | 2019-11-08 | 牡丹江师范学院 | A kind of film recommended method based on literature and art study |
| CN111160254A (en) * | 2019-12-30 | 2020-05-15 | 杭州趣维科技有限公司 | Classification method and system suitable for short video recommendation scattering |
| CN112770181A (en) * | 2021-01-12 | 2021-05-07 | 贵州省广播电视信息网络股份有限公司 | Quick verification system and method for recommended content of family group |
| CN113763027A (en) * | 2021-05-10 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Recommendation information processing method, recommendation information generating method and device |
Families Citing this family (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440335B (en) * | 2013-09-06 | 2016-11-09 | 北京奇虎科技有限公司 | Video recommendation method and device |
| CN103647800B (en) * | 2013-11-19 | 2017-12-12 | 乐视致新电子科技（天津）有限公司 | Recommend the method and system of application resource |
| CN103686237B (en) * | 2013-11-19 | 2017-03-08 | 乐视致新电子科技（天津）有限公司 | Recommend the method and system of video resource |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN103678672B (en) * | 2013-12-25 | 2017-05-24 | 北京中兴通德网络科技有限公司 | Method for recommending information |
| CN103995875A (en) * | 2014-05-23 | 2014-08-20 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN105812846B (en) * | 2014-12-30 | 2019-02-01 | Tcl集团股份有限公司 | The acquisition methods and device of network video |
| CN104731950B (en) * | 2015-03-31 | 2018-09-28 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN104735520A (en) * | 2015-04-01 | 2015-06-24 | 百度在线网络技术（北京）有限公司 | Television program play control method and device and television set |
| CN104853248B (en) * | 2015-05-07 | 2017-09-22 | 海信集团有限公司 | A kind of video recommendation method and device |
| CN104869439B (en) * | 2015-05-14 | 2018-03-09 | 无锡天脉聚源传媒科技有限公司 | A kind of video pushing method and device |
| CN105142025A (en) * | 2015-07-16 | 2015-12-09 | Tcl集团股份有限公司 | Information push method and system based on intelligent television terminal |
| CN105163182B (en) * | 2015-08-24 | 2019-06-11 | Tcl集团股份有限公司 | Smart television user behavior acquisition methods and system based on exception mining algorithm |
| CN105554555A (en) * | 2015-12-11 | 2016-05-04 | 广州华多网络科技有限公司 | Channel switching method and device |
| CN105893443A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and apparatus, and server |
| CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video content recommending method, device and system |
| CN105404698A (en) * | 2015-12-31 | 2016-03-16 | 海信集团有限公司 | Education video recommendation method and device |
| CN105678607B (en) * | 2016-01-07 | 2019-05-31 | 合肥工业大学 | A kind of Order Batch method based on improved K-Means algorithm |
| CN105912620A (en) * | 2016-04-07 | 2016-08-31 | 乐视控股（北京）有限公司 | Personalization multimedia recommendation method and device |
| CN105916034A (en) * | 2016-04-14 | 2016-08-31 | 乐视控股（北京）有限公司 | Video recommendation method and apparatus |
| CN105898495A (en) * | 2016-05-26 | 2016-08-24 | 维沃移动通信有限公司 | Method for pushing mobile terminal recommended information and mobile terminal |
| CN107862532B (en) * | 2016-09-22 | 2021-11-26 | 腾讯科技（深圳）有限公司 | User feature extraction method and related device |
| CN106530132A (en) * | 2016-11-14 | 2017-03-22 | 国家电网公司 | Power load clustering method and device |
| CN108205537A (en) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | A kind of video recommendation method and system |
| CN107748759A (en) * | 2017-09-21 | 2018-03-02 | 广州华多网络科技有限公司 | Video pushing method and its equipment |
| CN110035302B (en) * | 2018-01-11 | 2021-06-15 | 斑马智行网络(香港)有限公司 | Information recommendation method and device, model training method and device, computing equipment and storage medium |
| CN108540860B (en) * | 2018-02-28 | 2020-09-01 | 北京奇艺世纪科技有限公司 | Video recall method and device |
| CN111435371B (en) * | 2019-01-15 | 2023-08-11 | 百度在线网络技术（北京）有限公司 | Video recommendation method and system, computer program product and readable storage medium |
| CN111582956A (en) * | 2020-06-29 | 2020-08-25 | 成都新潮传媒集团有限公司 | Advertisement pushing method and device and computer equipment |
| CN112165634B (en) * | 2020-09-29 | 2022-09-16 | 北京百度网讯科技有限公司 | Method for establishing audio classification model and method and device for automatically converting video |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101094372A (en) * | 2007-07-25 | 2007-12-26 | 北京中星微电子有限公司 | Device and method for recommending TV programs |
| CN101287082A (en) * | 2008-05-16 | 2008-10-15 | 华东师范大学 | Collaborative filtered recommendation method introducing hotness degree weight of program |
| US20090158343A1 (en) * | 2007-12-07 | 2009-06-18 | Fujitsu Limited | Recording device of broadcasting program |
| CN101483732A (en) * | 2008-01-10 | 2009-07-15 | 北京视博数字电视科技有限公司 | Electronic program guidance generation method and apparatus, program searching method and searching engine for television terminal |
| CN101489107A (en) * | 2009-01-21 | 2009-07-22 | 华东师范大学 | Collaborative filtering recommendation method based on population attribute keyword vector |
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
-
2012
- 2012-10-24 CN CN201210408686.9A patent/CN102946566B/en not_active Expired - Fee Related
- 2012-10-24 CN CN201510341831.XA patent/CN104918118B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101094372A (en) * | 2007-07-25 | 2007-12-26 | 北京中星微电子有限公司 | Device and method for recommending TV programs |
| US20090158343A1 (en) * | 2007-12-07 | 2009-06-18 | Fujitsu Limited | Recording device of broadcasting program |
| CN101483732A (en) * | 2008-01-10 | 2009-07-15 | 北京视博数字电视科技有限公司 | Electronic program guidance generation method and apparatus, program searching method and searching engine for television terminal |
| CN101287082A (en) * | 2008-05-16 | 2008-10-15 | 华东师范大学 | Collaborative filtered recommendation method introducing hotness degree weight of program |
| CN101489107A (en) * | 2009-01-21 | 2009-07-22 | 华东师范大学 | Collaborative filtering recommendation method based on population attribute keyword vector |
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
Non-Patent Citations (2)
| Title |
|---|
| HYEJEONG LEE: "Personalized Recommendation Schemes for DTV Channel Selectors", 《IEEE TRANSACTIONS ON CONSUMER ELECTRONICS》 * |
| 李应安: "《全国优秀硕士学位论文全文数据库 信息科技辑》", 15 February 2012 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN105812834A (en) * | 2016-05-10 | 2016-07-27 | 南京大学 | Video recommendation server, recommendation method and pre-caching method based on cluster information |
| CN105812834B (en) * | 2016-05-10 | 2019-03-12 | 南京大学 | Video recommendations server, recommended method and pre-cache method based on clustering information |
| CN109379608A (en) * | 2018-09-13 | 2019-02-22 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of direct broadcasting room |
| CN110427556A (en) * | 2019-07-30 | 2019-11-08 | 牡丹江师范学院 | A kind of film recommended method based on literature and art study |
| CN110427556B (en) * | 2019-07-30 | 2022-10-11 | 牡丹江师范学院 | Film recommendation method based on literary and artistic learning |
| CN111160254A (en) * | 2019-12-30 | 2020-05-15 | 杭州趣维科技有限公司 | Classification method and system suitable for short video recommendation scattering |
| CN112770181A (en) * | 2021-01-12 | 2021-05-07 | 贵州省广播电视信息网络股份有限公司 | Quick verification system and method for recommended content of family group |
| CN113763027A (en) * | 2021-05-10 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Recommendation information processing method, recommendation information generating method and device |
| CN113763027B (en) * | 2021-05-10 | 2023-08-01 | 腾讯科技（深圳）有限公司 | Recommendation information processing method, recommendation information generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104918118B (en) | 2019-08-02 |
| CN102946566B (en) | 2015-07-01 |
| CN102946566A (en) | 2013-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102946566B (en) | Video recommending method and device based on historical information | |
| KR102526040B1 (en) | Information search method and apparatus, device, storage medium, and computer program | |
| CN101960447B (en) | Social aspects of content aggregation syndication, sharing, and updating | |
| CN104809154B (en) | The method and device recommended for information | |
| CN102906744B (en) | Infinite browse | |
| CN111782965A (en) | Intention recommendation method, device, equipment and storage medium | |
| CN106686063A (en) | Information recommendation method and apparatus, and electronic device | |
| CN104903886B (en) | Structured search based on social graph information is inquired about | |
| CN110516160A (en) | User modeling method, the sequence of recommendation method of knowledge based map | |
| US20150256499A1 (en) | Ranking, collection, organization, and management of non-subscription electronic messages | |
| CA3034323A1 (en) | Similarity search using polysemous codes | |
| US8874558B1 (en) | Promoting fresh content for authoritative channels | |
| US20120109945A1 (en) | Method and system of improving navigation within a set of electronic documents | |
| CN105245924B (en) | The video player of the push of video information and display methods and application this method | |
| CN105138568B (en) | Search result shows method, apparatus and search engine | |
| CN103092962B (en) | A kind of method and system issuing internet information | |
| CN104503975A (en) | Method and device for customizing recommended card | |
| CN109889891A (en) | Obtain the method, apparatus and storage medium of target media file | |
| CN105009077A (en) | Dynamic user interface | |
| CN111400546B (en) | Video recall method and video recommendation method and device | |
| CN108307239A (en) | A kind of video content recommendation method and apparatus | |
| CN104102733B (en) | Search for content providing and search engine | |
| CN111563198B (en) | Material recall method, device, equipment and storage medium | |
| CN112559901A (en) | Resource recommendation method and device, electronic equipment, storage medium and computer program product | |
| CN107944026A (en) | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220729 Address after: Room 801, 8th floor, No. 104, floors 1-19, building 2, yard 6, Jiuxianqiao Road, Chaoyang District, Beijing 100015 Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Address before: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park) Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Patentee before: Qizhi software (Beijing) Co.,Ltd. |