CN107454442A - A kind of method and apparatus for recommending video - Google Patents
A kind of method and apparatus for recommending video Download PDFInfo
- Publication number
- CN107454442A CN107454442A CN201710800982.6A CN201710800982A CN107454442A CN 107454442 A CN107454442 A CN 107454442A CN 201710800982 A CN201710800982 A CN 201710800982A CN 107454442 A CN107454442 A CN 107454442A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- preference
- library
- videos
- 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]
- H04N21/20—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
-
- 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
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a kind of method and apparatus for recommending video.Methods described includes：All videos in the video library that traverse user was watched within default one period, and a video being watched every time based on the user during traversal determines preference of the user to other each videos in the video library；A number of video is chosen based on the preference in the video library by predetermined manner to the user to recommend.
Description
Technical field
The present invention relates to technical field of information processing, in particular to a kind of method and apparatus for recommending video.
Background technology
With the development and the popularization of 3G and 4G mobile communications networks and the popularization of intelligent terminal of internet, largely
Using also arising at the historic moment.The information that internet provides is also increasingly abundanter, and webpage information of traditional word with picture is not
Can meet the needs of user, the business scenario information that new development is got up is " short-sighted frequency " information, such as second beats APP, it is beautiful clap APP,
Micro- third-party application popular depending on APP etc. can provide the user the functions such as upload and the viewing of " short-sighted frequency "." short-sighted frequency " provides
News mainly show that the shorter and high-quality video content of duration is watched to user to user, as shown in figure 3, in order to make user fast
Speed understands the general contents of short-sighted frequency, also for the interest for attracting user, there is provided the service provider of short Video service can be added to
Each short one title of video editing of video library, in addition to classify to short-sighted frequency, such as laugh at class, small category, video display class,
Information class, amusement class, self-timer class etc..But the flow of video is more than the flow of word, watched in 3G and 4G wireless network
Substantial amounts of short video council allows user to consume excessive flow, brings too high communication to consume to user.
In addition, user also increasingly likes shooting something occurred at one's side conveniently, then upload and shared on the net, also
Micro- film for having amateur to shoot and sharing on the net etc., these at present can be to provide video as main services
Can largely it be browsed on website, such as Yoqoo etc..But user want to find in the video database of magnanimity it is interested
Video, it is desired nonetheless to spend many times.
It is therefore desirable to when showing " short-sighted frequency " information to user, recommend its " short-sighted frequency " interested to provide to user
News；Or logged in user and when shooting the video certainly of other users upload is browsed such as Yoqoo, such as provided on Yoqoo
Objective column is clapped, recommends its video content interested to user.But the preference of different user is different, for easily tens
Ten thousandth, user group up to a million, personalized recommendation video content or " short-sighted frequency " information is realized, i.e., is pushed away for different user to it
It is a technical barrier to recommend its different video interested or " short-sighted frequency " information.
The content of the invention
It is an object of the invention to provide a kind of method and apparatus for recommending video, to improve above mentioned problem.
First embodiment of the invention provides a kind of method for recommending video, and it includes：
S1：All videos in the video library that traverse user was watched within default one period, and during traversal
A video being watched every time based on the user determines the user to the inclined of other each videos in the video library
Good degree；
S2：A number of video in the video library is chosen to the user by predetermined manner based on the preference
Recommend.
Wherein, the video watched based on the user determines that the user each regards to other in the video library
The method of the preference of frequency includes：
Wherein：Pa,bRepresent that the user is to the video library based on determined by the video a in the video library that user watched
In other video b preference；
V (a) represents to have viewed user's set of the video a in video library；
V (b) represents to have viewed user's set of the video b in video library；
S (b) represents all users set that video b was demonstrated in the terminal that different user uses；
KClassification residing for aRepresent hobby coefficient of the user to classification residing for video a, the KClassification residing for aComputational methods it is as follows：
Wherein | LmClassification residing for a| represent the quantity for multiple videos that the user was watched in video classification residing for video a；
| Sm | represent the quantity of all videos shown in the terminal that the user uses.
Wherein, default one period includes but is not limited to：1 day, 3 days, 7 days or 15 days.
Wherein, further comprise after step S1：
By the user determined respectively based on multiple videos that the user watched to same in video library
Multiple preference angle value of video are added up, and using final preference of the cumulative sum as the user to the same video
Value, obtains preference of the user to all videos in the video library in this way.
Wherein, in step s 2, a number of video is chosen to user based on the preference angle value descending order
Recommend, or randomly select from the video corresponding to the preference more than or equal to predetermined threshold value a number of video to
Family is recommended, wherein when the multiple videos chosen based on difference preference's angle value are same video by the quantity of the plurality of same video
Merge into 1.
Second embodiment of the invention additionally provides a kind of device for recommending video, including：
Preference determining unit, all in the video library watched for traverse user within default one period regard
Frequently, the video watched every time based on the user and during traversal determines the user to its in the video library
The preference of its each video；
Recommendation unit, for choosing a number of video in the video library by predetermined manner based on the preference
Recommend to the user.
Wherein, the preference determining unit determines the user couple for the video watched based on the user
The method of the preference of other each videos in the video library includes：
Wherein：Pa,bRepresent that the user is to the video library based on determined by the video a in the video library that user watched
In other video b preference；
V (a) represents to have viewed user's set of the video a in video library；
V (b) represents to have viewed user's set of the video b in video library；
S (b) represents all users set that video b was demonstrated in the terminal that different user uses；
KClassification residing for aRepresent hobby coefficient of the user to classification residing for video a, the KClassification residing for aComputational methods it is as follows：
Wherein | LmClassification residing for a| represent the quantity for multiple videos that the user was watched in video classification residing for video a；
| Sm | represent the quantity of all videos shown in the terminal that the user uses.
Wherein, the preference determining unit is in the video library that traverse user was watched within default one period
All videos, and a video being watched every time based on the user during traversal determines the user to the video library
In other each videos preference after, be further used for：
By the user determined respectively based on multiple videos that the user watched to same in video library
Multiple preference angle value of video are added up, and using final preference of the cumulative sum as the user to the same video
Value, obtains preference of the user to all videos in the video library in this way.
Wherein, being chosen by predetermined manner includes：The mode chosen based on the preference angle value descending order, Huo Zhecong
More than or equal to the mode randomly selected in the video corresponding to the preference of predetermined threshold value, wherein when based on difference preference's angle value
The quantity of the plurality of same video is merged into 1 when the multiple videos chosen are same video.
Third embodiment of the invention additionally provides a kind of storage device, wherein being stored with a plurality of instruction, the instruction is suitable to
As processor load and perform above-mentioned first embodiment and/or preferred embodiment described in method.
According to a kind of method and apparatus of recommendation video of the present invention, by the video library watched based on user
Video determines preference of the user to other each videos in the video library, realize according to the preference of different user to
User recommends different videos or short-sighted frequency, so as to realize the purpose of personalized recommendation video for different user.
Brief description of the drawings
Fig. 1 is the flow chart of the method for the recommendation video that first embodiment of the invention provides；
Fig. 2 is the schematic block diagram of the device for the recommendation video that second embodiment of the invention provides；
Fig. 3 is the sectional drawing for an example for having headed short-sighted frequency.
Embodiment
Below in conjunction with the embodiment of the present invention and accompanying drawing, the technical scheme in embodiment is clearly and completely described,
Obviously, described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Generally here in accompanying drawing
The component for the embodiment of the present invention for describing and showing can be configured to arrange and design with a variety of.Therefore, below to
The detailed description of the embodiments of the invention provided in accompanying drawing is not intended to limit the scope of claimed invention, but only
Only represent the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not making creative labor
The every other embodiment obtained on the premise of dynamic, belongs to the scope of protection of the invention.
Video involved in the present invention is the video for being not limited to a certain specific duration, can be regarding for any playable duration
Frequently.The reproduction time of currently a popular video feeds is generally more than ten seconds-a few minutes, such as -6 minutes 12 seconds, but with user
Demand constantly lifted, also there are certain customers to be longer than the video feeds of 10 minutes appealing to make, therefore in some such as physical culture
The reproduction time of the video provided in the video column of program can be up to 15 minutes or so, even more than 20 minutes, such as excellent
The cruel various types of videos provided on the net, therefore service side is meets that the various reproduction times that numerous user's needs are released are grown
The video of degree is suitable for the present invention, such as the short short-sighted frequency as between -10 minutes 10 seconds, long such as from about -120 minutes 90 minutes
Movie program video etc..
Fig. 1 is the flow chart of the method for the recommendation video that first embodiment of the invention provides.As shown in figure 1, the present invention
The method of video is recommended to comprise the following steps：
S1：All videos in the video library that traverse user was watched within default one period, and during traversal
A video being watched every time based on the user determines the user to the inclined of other each videos in the video library
Good degree.
The video preserved in video library and video library described here can be the video of any playing duration.It is general next
Say, there is provided the third-party application of Video service all can pre-establish video library in service end, and various playing durations are deposited in the inside
Video, in addition to the video that user uploads, there are the video of tens seconds durations, such as more than 10 seconds, more than 30 seconds etc., also have several
The video of minute duration, such as more than 1 minute, more than 2 minutes, more than 5 minutes etc., also have more than regarding for 20 minutes durations
Frequently, for example, see the various types of videos provided on Yoqoo.Underneath with term video library or short video library, as upper
Described in face, so-called short-sighted frequency is comparatively, for realizing that technical scheme does not limit, although some places use
Short-sighted frequency or short video library term, but preferably use general phrase video or video library.
In general, user wants to watch video, such as tablet personal computer or smart mobile phone online by intelligent mobile terminal, needs
The various APP installed on intelligent terminal are used to watch desired video, such as today's tops, UC browsers by network
Deng the short-sighted frequency information service of offer, or pass through all kinds of video player APP products, such as youku.com APP etc..And these APP
Service provider can pre-establish video library on the server of rear end, the inside preserves all kinds of playing durations that can be provided a user
Video, including short video feeds, TV play and film video etc..And different user watches all kinds of videos, such as TV play, electricity
The frequency of shadow, short video feeds etc. is different, and some users are watching daily, and some users can watch every several talentes.But use
When family is using different APP products viewing video, it watches the behavior of video can be as log recording in the APP product phases with using
On the server of association.
In addition, as being introduced in background technology, either short video feeds, or the video such as film, TV play, it is
It is easy to user's fast searching it is expected the video seen, there is provided all videos that the service provider of Video service is often given in video library
Classified, for example, including but is not limited to for the class categories of film video：By the name classification of star：Zhou Runfa, Cheng Long
Deng；By geographic classification：Chinese, the U.S., Europe etc.；Classify by type：Comedy, love, action etc.；Also have for TV play similar
Classification, and for the classification of short video feeds, be related in the introduction, these information are either to art technology
For personnel, or to often watching for the user of various videos, the information of general knowledge class is belonged to, therefore be not situated between excessively here
Continue.
Related introduction based on more than, step S1 of the invention is firstly the need of traverse user u within default one period
All videos in the video library watched, i.e., know the user u at default one section by the user journal of traversal record
Which video all watched in period in video library.Default one period can freely set in practice, such as
It can be default one day or default three days, five days or seven days；Can certainly be big according to big data analysis in advance
Measure the temporal frequency that user watches video, then set a proper period, for example, it is assumed that 15 days (certainly
Can be other number of days) it is proper, then can be with all videos in video library that traverse user was watched in 15 days.And
During traversal, a video being watched every time based on the user u determines the user u to other in the video library
The preference of each video.That is, during traversal, the video (such as video A) that the user u was watched is found every time
When, video A is based on to determine the user u to other each videos (such as video B, video C, the video in the video library
D ...) preference.
A video being watched based on user determines the user to the inclined of other each videos in the video library
The method spent well includes：
Wherein：Pa,bRepresent that the user is to the video library based on determined by the video a in the video library that user watched
In other video b preference；
V (a) represents to have viewed user's set of the video a in video library；
V (b) represents to have viewed user's set of the video b in video library；
S (b) represents all users set that video b was demonstrated in the terminal that different user uses；
KClassification residing for aRepresent hobby coefficient of the user to classification residing for video a, the KClassification residing for aComputational methods it is as follows：
Wherein | LmClassification residing for a| represent the quantity for multiple videos that the user was watched in video classification residing for video a；
| Sm | represent the quantity of all videos shown in the terminal that the user uses.
In superincumbent formula,Represent：When recommending video b to all users for watching video a, Yong Huhui
Watch video b probability.
S2：A number of video in the video library is chosen to the user by predetermined manner based on the preference
Recommend.
Preference by obtained user to the video in the video library of for example short video library, it is possible to know user couple
Which video is interested, so chooses a number of video by predetermined manner based on the preference and recommends to user.It is excellent
Choosing, a number of video is chosen based on the preference angle value descending order and recommended to user.The certain amount can
With according to practical application scene come arbitrarily selected particular number, such as can be 5-20, either 20-50 or can also
It is greater number of video, such as 100.So, realize and different videos is recommended to user according to the preference of different user
Personalized recommendation purpose.
Except using above-mentioned preferred embodiment come choose recommend video in addition to, a threshold value can also be pre-set, from more than
Or recommend equal to a number of video is randomly selected in the video corresponding to the preference of predetermined threshold value to user, such as can be with
It it is 5-20, either 20-50 is individual or can also be greater number of video, such as 100.
In this first embodiment, by the institute in the video library watched in traverse user within default one period
During having video, a video being watched every time based on the user determines the user to other in the video library
The preference of each video, therefore when watching videos different in video library for a user, all can respectively calculate and be directed to
The preference of same video, for example, when a user watched video A different in video library, video B, video C, all can evidence
This calculates preference of the user for same video D respectively, will calculate user in this example embodiment for same video D's
3 preference angle value, it is also in this way, for example can equally calculate user for same video E 3 are inclined certainly for other videos
Good angle value.So, a number of video is being chosen in the video library by predetermined manner based on the preference to described
User recommend when, it is possible to there is user in the case of multiple preference angle value of same video come above, for example, when with
Different video A, video B, video C belong to same classification in the video library that family was watched, and the video D not yet watched also with regarding
Frequency A, video B, video C belong to same classification, it is assumed for example that video A, video B, video C and video D starring actors are Zhou Run
Hair, 3 preferences of the user that video A, video B, the video C now watched based on user is calculated respectively for video D
Angle value is possible to identical or approximately the same, so occurs to 3 situations for all recommending video D of the user.In order to avoid this
Situation occurs, it is preferred that when the multiple videos chosen based on difference preference's angle value are same video by the plurality of same video
Quantity merge into 1.Also illustrated with above-mentioned example, all regarded when based on 3 videos that 3 preference angle value are chosen respectively
During frequency D, the video D of this 3 times selections are incorporated as 1 video and recommended to the user, are thus avoided the occurrence of to the user 3 times all
Video D situation is recommended to occur.
In first embodiment described above, it is possible that watching different in video library regard based on a user
Frequency A, video B, video C have greatly very much to calculate the user respectively for the value having in same video D multiple preference angle value
Be worth the situation of very little, for example, when video A and video D belong to same class categories, and class categories where video B and video C with
Video D class categories fall far short, then the preference based on the user that the video A that user watched is calculated for video D
Angle value is very big, and the user that the video B or video C watched based on the user is calculated respectively is for video D preference
Value is then smaller, in some instances it may even be possible to the situation of very small (being such as close to 0) occurs.In order to which further accurate recommendation video is to use
Family, the present invention is on the basis of first embodiment, it is further provided a preferred embodiment, wherein after step S1, i.e.,
All videos in the video library that traverse user was watched within default one period, and the base every time during traversal
Determine that the user completes to the preference of other each videos in the video library in the video that the user watched
Afterwards, by based on the user that multiple videos that the user watched are determined respectively to the same video in video library
Multiple preference angle value added up, and using final preference angle value of the cumulative sum as the user to the same video,
Preference of the user to all videos in the video library is obtained in this way.User is calculated to wherein one in video library
The formula of the final preference angle value of individual video is as follows：
Wherein：Pu,bRepresent final preferences of the user u to the video b in video library；
UuRepresent the video collection in the video library that user u was watched；
Pa,bRepresent that the user is in the video library based on determined by the video a in the video library that user watched
Other video b preference；
a∈UuRepresent the video collection that the video a that user u was watched belongs in the video library that the user u was watched.
So, the formula just clearly shows：All videos in the video library watched based on user u, are counted respectively
Multiple preference angle value of the user u to the video b in video library are calculated, the plurality of preference angle value is added up, and will be cumulative
Final preference angle value P of the sum as the user u to the video bu,b。
So handling is advantageous in that：1st, avoiding to a user repeatedly all recommends the situation of same video to occur, such as
It will not occur in the preferred embodiment to 3 all recommendation video D of user situation in above-mentioned example；2nd, user will be based on
The user that multiple videos in the video library watched are determined respectively is more to the same video in the video library
The cumulative sum of individual preference angle value, the final preference angle value as the user to the same video, so based on described in most
The size of whole preference angle value is recommended to choose a number of video in the video library to the user, the recommendation results meeting
More accurately meet the preference of user, this can greatly improve satisfaction of the user to recommendation video.
According to the method for the recommendation video of the various embodiments described above introduction of the present invention, the preference according to different user is realized
Recommend the purpose of the personalized recommendation of different videos to user.
Fig. 2 is the schematic block diagram of the device for the recommendation video that second embodiment of the invention provides.As shown in Fig. 2 this hair
The device of bright recommendation video includes：
Preference determining unit, all in the video library watched for traverse user within default one period regard
Frequently, the video watched every time based on the user and during traversal determines the user to its in the video library
The preference of its each video；
Recommendation unit, for choosing a number of video in the video library by predetermined manner based on the preference
Recommend to the user.
Wherein, default one period includes but is not limited to：1 day, 3 days, 7 days, 15 days or other number of days.
Wherein, the preference determining unit determines the user couple for the video watched based on the user
The method of the preference of other each videos in the video library includes：
Wherein：Pa,bRepresent that the user is to the video library based on determined by the video a in the video library that user watched
In other video b preference；
V (a) represents to have viewed user's set of the video a in video library；
V (b) represents to have viewed user's set of the video b in video library；
S (b) represents all users set that video b was demonstrated in the terminal that different user uses；
KClassification residing for aRepresent hobby coefficient of the user to classification residing for video a, the KClassification residing for aComputational methods it is as follows：
Wherein | LmClassification residing for a| represent the quantity for multiple videos that the user was watched in video classification residing for video a；
| Sm | represent the quantity of all videos shown in the terminal that the user uses.
Wherein, the recommendation unit be based on the preference chosen by predetermined manner in the video library it is a number of
The method that video is recommended to the user includes：Based on the preference angle value descending order choose a number of video to
User recommends, or a number of video is randomly selected from the video corresponding to the preference more than or equal to predetermined threshold value
Recommend to user.Wherein when the multiple videos chosen based on difference preference's angle value are same video by the plurality of same video
Quantity merges into 1.
In a preferred embodiment, the preference determining unit is watched in traverse user within default one period
All videos in the video library crossed, and a video being watched every time based on the user during traversal determines this
After user is to the preference of other each videos in the video library, it is further used for：
By the user determined respectively based on multiple videos that the user watched to same in video library
Multiple preference angle value of video are added up, and using final preference of the cumulative sum as the user to the same video
Value, obtains preference of the user to all videos in the video library in this way.
It is apparent to those skilled in the art that for convenience and simplicity of description, the device of foregoing description
Specific work process, may be referred to aforementioned first embodiment description implementation corresponding process, aforementioned first embodiment
Middle row illustrated example and associated description, the course of work of interpreting means is equally applicable to, is not repeated to describe herein.
According to the device of the recommendation video of the present invention, realize and different regard is recommended to user according to the preference of different user
The purpose of the personalized recommendation of frequency.
A kind of computer program product of the method for recommendation video that the embodiment of the present invention is provided, including store program
The computer-readable recording medium of code, the instruction that described program code includes can be used for performing described in previous methods embodiment
Method, specific implementation can be found in embodiment of the method, will not be repeated here.
Therefore, present invention also offers a kind of storage device, wherein being stored with a plurality of instruction, the instruction is suitable to by handling
Device load and perform above-mentioned first embodiment and corresponding preferred embodiment described in method and step.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, Intelligent flat computer, smart mobile phone, server, or network equipment etc.) perform described in each embodiment of the present invention
The all or part of step of method.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM), deposit at random
Access to memory (RAM), magnetic disc or CD etc. are various can be with the medium of store program codes.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of method for recommending video, it includes：
S1：All videos in the video library that traverse user was watched within default one period, and during traversal every time
A video that the user watched is all based on to determine preference of the user to other each videos in the video library；
S2：A number of video is chosen based on the preference in the video library by predetermined manner to push away to the user
Recommend.
2. according to the method for claim 1, it is characterised in that a video being watched based on the user determines this
User includes to the method for the preference of other each videos in the video library：
Wherein：Pa,bRepresent that the user is in the video library based on determined by the video a in the video library that user watched
Other video b preference；
V (a) represents to have viewed user's set of the video a in video library；
V (b) represents to have viewed user's set of the video b in video library；
S (b) represents all users set that video b was demonstrated in the terminal that different user uses；
KClassification residing for aRepresent hobby coefficient of the user to classification residing for video a, the KClassification residing for aComputational methods it is as follows：
Wherein | LmClassification residing for a| represent the quantity for multiple videos that the user was watched in video classification residing for video a；
| Sm | represent the quantity of all videos shown in the terminal that the user uses.
3. according to the method for claim 1, it is characterised in that default one period includes but is not limited to：1 day, 3
My god, 7 days or 15 days.
4. according to the method for claim 1, it is characterised in that further comprise after step S1：
By based on the user that multiple videos that the user watched are determined respectively to the same video in video library
Multiple preference angle value added up, and using final preference angle value of the cumulative sum as the user to the same video,
Preference of the user to all videos in the video library is obtained in this way.
5. according to the method for claim 1, it is characterised in that in step s 2, suitable from big to small based on the preference angle value
Sequence is chosen a number of video and recommended to user, or from the video corresponding to the preference more than or equal to predetermined threshold value
Randomly select a number of video to user to recommend, wherein when the multiple videos chosen based on difference preference's angle value are regarded to be identical
The quantity of the plurality of same video is merged into 1 during frequency.
6. a kind of device for recommending video, including：
Preference determining unit, all videos in the video library watched for traverse user within default one period,
And a video being watched during traversal based on the user determines the user to other in the video library every time
The preference of each video；
Recommendation unit, in the video library choosing a number of video to institute by predetermined manner based on the preference
State user's recommendation.
7. device according to claim 6, it is characterised in that the preference determining unit is used to be seen based on the user
The video seen determines that the user includes to the method for the preference of other each videos in the video library：
Wherein：Pa,bRepresent that the user is in the video library based on determined by the video a in the video library that user watched
Other video b preference；
V (a) represents to have viewed user's set of the video a in video library；
V (b) represents to have viewed user's set of the video b in video library；
S (b) represents all users set that video b was demonstrated in the terminal that different user uses；
KClassification residing for aRepresent hobby coefficient of the user to classification residing for video a, the KClassification residing for aComputational methods it is as follows：
Wherein | LmClassification residing for a| represent the quantity for multiple videos that the user was watched in video classification residing for video a；
| Sm | represent the quantity of all videos shown in the terminal that the user uses.
8. device according to claim 6, it is characterised in that the preference determining unit is in traverse user default
All videos in the video library watched in one period, and one watched every time based on the user during traversal
Individual video after determining the user to the preference of other each videos in the video library, is further used for：
By based on the user that multiple videos that the user watched are determined respectively to the same video in video library
Multiple preference angle value added up, and using final preference angle value of the cumulative sum as the user to the same video,
Preference of the user to all videos in the video library is obtained in this way.
9. device according to claim 6, it is characterised in that being chosen by predetermined manner includes：Based on the preference angle value from
The mode that small order is chosen is arrived greatly, or randomly selected from the video corresponding to the preference more than or equal to predetermined threshold value
Mode, wherein closing the quantity of the plurality of same video when the multiple videos chosen based on difference preference's angle value are same video
And for 1.
10. a kind of storage device, wherein being stored with a plurality of instruction, the instruction is suitable to by processor loading and perform claim requirement
Method described in one of 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710800982.6A CN107454442B (en) | 2017-09-07 | 2017-09-07 | Method and device for recommending video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710800982.6A CN107454442B (en) | 2017-09-07 | 2017-09-07 | Method and device for recommending video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107454442A true CN107454442A (en) | 2017-12-08 |
| CN107454442B CN107454442B (en) | 2021-02-05 |
Family
ID=60495924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710800982.6A Active CN107454442B (en) | 2017-09-07 | 2017-09-07 | Method and device for recommending video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107454442B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133031A (en) * | 2017-12-29 | 2018-06-08 | 北京搜狐新媒体信息技术有限公司 | A kind of method and device of filtered recommendation video candidate result |
| CN108733842A (en) * | 2018-05-29 | 2018-11-02 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN108810637A (en) * | 2018-06-12 | 2018-11-13 | 优视科技有限公司 | Video broadcasting method, device and terminal device |
| CN109145210A (en) * | 2018-08-17 | 2019-01-04 | 腾讯科技（深圳）有限公司 | A kind of method, apparatus and storage medium of information recommendation |
| CN110874435A (en) * | 2018-08-31 | 2020-03-10 | 努比亚技术有限公司 | Recommendation method, cloud server, service server, terminal and storage medium |
| CN111031339A (en) * | 2019-12-18 | 2020-04-17 | 网易（杭州）网络有限公司 | Live video processing method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102970605A (en) * | 2012-11-21 | 2013-03-13 | Tcl集团股份有限公司 | Program recommendation method |
| US20130097624A1 (en) * | 2011-10-17 | 2013-04-18 | Electronics And Telecommunications Research Institute | System for recommending favorite channel/program based on tv watching pattern and method thereof |
| US9055343B1 (en) * | 2013-06-07 | 2015-06-09 | Google Inc. | Recommending content based on probability that a user has interest in viewing the content again |
| US9129227B1 (en) * | 2012-12-31 | 2015-09-08 | Google Inc. | Methods, systems, and media for recommending content items based on topics |
| CN105306972A (en) * | 2014-06-26 | 2016-02-03 | 中兴通讯股份有限公司 | Television program recommending method and server |
| CN105550334A (en) * | 2015-12-22 | 2016-05-04 | 海信集团有限公司 | Video recommendation method and device |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN105847984A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommending method and apparatus |
| CN105898410A (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 server |
| CN106372101A (en) * | 2016-07-20 | 2017-02-01 | Tcl集团股份有限公司 | Video recommendation method and apparatus |
-
2017
- 2017-09-07 CN CN201710800982.6A patent/CN107454442B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130097624A1 (en) * | 2011-10-17 | 2013-04-18 | Electronics And Telecommunications Research Institute | System for recommending favorite channel/program based on tv watching pattern and method thereof |
| CN102970605A (en) * | 2012-11-21 | 2013-03-13 | Tcl集团股份有限公司 | Program recommendation method |
| US9129227B1 (en) * | 2012-12-31 | 2015-09-08 | Google Inc. | Methods, systems, and media for recommending content items based on topics |
| US9055343B1 (en) * | 2013-06-07 | 2015-06-09 | Google Inc. | Recommending content based on probability that a user has interest in viewing the content again |
| CN105306972A (en) * | 2014-06-26 | 2016-02-03 | 中兴通讯股份有限公司 | Television program recommending method and server |
| CN105898410A (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 server |
| CN105550334A (en) * | 2015-12-22 | 2016-05-04 | 海信集团有限公司 | Video recommendation method and device |
| CN105847984A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommending method and apparatus |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN106372101A (en) * | 2016-07-20 | 2017-02-01 | Tcl集团股份有限公司 | Video recommendation method and apparatus |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133031A (en) * | 2017-12-29 | 2018-06-08 | 北京搜狐新媒体信息技术有限公司 | A kind of method and device of filtered recommendation video candidate result |
| CN108733842A (en) * | 2018-05-29 | 2018-11-02 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN108733842B (en) * | 2018-05-29 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN108810637A (en) * | 2018-06-12 | 2018-11-13 | 优视科技有限公司 | Video broadcasting method, device and terminal device |
| CN109145210A (en) * | 2018-08-17 | 2019-01-04 | 腾讯科技（深圳）有限公司 | A kind of method, apparatus and storage medium of information recommendation |
| CN109145210B (en) * | 2018-08-17 | 2023-03-21 | 深圳市雅阅科技有限公司 | Information recommendation method and device and storage medium |
| CN110874435A (en) * | 2018-08-31 | 2020-03-10 | 努比亚技术有限公司 | Recommendation method, cloud server, service server, terminal and storage medium |
| CN111031339A (en) * | 2019-12-18 | 2020-04-17 | 网易（杭州）网络有限公司 | Live video processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107454442B (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107454442A (en) | A kind of method and apparatus for recommending video | |
| US10437896B2 (en) | Singular, collective, and automated creation of a media guide for online content | |
| US10356462B1 (en) | Recommending a composite channel | |
| US10185767B2 (en) | Systems and methods of classifying content items | |
| US9736503B1 (en) | Optimizing timing of display of a mid-roll video advertisement based on viewer retention data | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| US9967628B2 (en) | Rating videos based on parental feedback | |
| US10129596B2 (en) | Adaptive row selection | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| US20190045273A1 (en) | Enhanced program guide | |
| CN107562848A (en) | A kind of video recommendation method and device | |
| US9369514B2 (en) | Systems and methods of selecting content items | |
| US20140032468A1 (en) | Predicting user activity based on usage data received from client devices | |
| CN108595492B (en) | Content pushing method and device, storage medium and electronic device | |
| US20220107978A1 (en) | Method for recommending video content | |
| WO2013077983A1 (en) | Adaptive media recommendation systems, methods, and computer readable media | |
| CN106599165B (en) | content recommendation method and server based on playing behavior | |
| CN108476344B (en) | Content selection for networked media devices | |
| US20140067827A1 (en) | Automatically generating music playlists based on an implicitly selected seed | |
| EP2765526A1 (en) | Creating playlists | |
| CN112507163B (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| CN106980666B (en) | Method and device for recommending video | |
| CN105956061B (en) | Method and device for determining similarity between users | |
| CN110569447B (en) | Network resource recommendation method and device and storage medium | |
| US11977599B2 (en) | Matching video content to podcast episodes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200902 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |