CN106162351A - A kind of video recommendation method and device - Google Patents
A kind of video recommendation method and device Download PDFInfo
- Publication number
- CN106162351A CN106162351A CN201610624780.6A CN201610624780A CN106162351A CN 106162351 A CN106162351 A CN 106162351A CN 201610624780 A CN201610624780 A CN 201610624780A CN 106162351 A CN106162351 A CN 106162351A
- Authority
- CN
- China
- Prior art keywords
- video
- group
- recommendation list
- recommendation
- tabulation
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—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
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of video recommendation method and device, including: obtain the identification information of the first video；According to the identification information of described first video, determine the second video of association, described first video and the tabulation group belonging to the second video and the recommendation list group belonging to described second video；Described first video, for the incorporation way of described second video, is incorporated into described recommendation list group by the first video described in the parameter value calculation according to described tabulation group and described recommendation list group；Described first video is recommended according to the position in described recommendation list group.Thus, it is possible to improve the recommendation results of the first video newly uploaded, it is achieved recommending the first video newly uploaded fast and effectively, also improve the clicking rate of video while improve user satisfaction, Consumer's Experience is good.
Description
Technical field
The present invention relates to computer video field, particularly relate to a kind of video recommendation method and device.
Background technology
Recently as the high speed development of computer internet technology, increasing data message is published on the net for people
Browse and consult.And on the basis of the network platform of the magnanimity existed, also have every day substantial amounts of new data information to produce
And be sent in the network platform.In the prior art, the most all can be shown by the page of each platform refreshing oneself, or logical
Crossing the classification associated user of making can point out display new data message when viewing a certain content, thus reaches to show new number
It is believed that the purpose of breath.But this mode is owing to being limited by page layout, algorithm of correlation degree etc., cannot demonstrate far away whole
New data information, thus cause a large amount of new data information cannot be shown to user.
As a example by video, the existing process for new video, more of other videos that new video is to be recommended are entered
Row association, such as key word or the same uploader etc. of this video of foundation video.And enter with other existing videos for new video
Row association is promoted, and owing to being difficult to get the wanted expression content of new video technically, causes cannot be carried out new video correctly
Identify and judge, the most just cannot be carried out corresponding relevance and recommend.The most feasible way is that the title according to new video is carried out
Association analysis, thus video is promoted.But this mode still cannot solve the problem that new video is shown very well.
Therefore, how providing a kind of new video recommendation method is the problem that the present invention needs to solve.
Summary of the invention
Present invention is primarily targeted at a kind of video recommendation method of offer and device, to solve new video in prior art
The problem shown.
A kind of video recommendation method that the present invention provides, including:
Obtain the identification information of the first video；
According to the identification information of described first video, determine the second video of association, described first video and the second video
Recommendation list group belonging to affiliated tabulation group and described second video；
First video described in parameter value calculation according to described tabulation group and described recommendation list group is for described
The incorporation way of two videos, is incorporated into described recommendation list group by described first video；
Described first video is recommended according to the position in described recommendation list group.
A kind of video recommendations device that the present invention provides, including: identification information obtaining unit, list group acquiring unit, regard
Frequency introduces unit and video recommendations unit；
Described identification information obtaining unit, for obtaining the identification information of the first video；
Described list group acquiring unit, for according to the identification information of described first video, determine association the second video,
Tabulation group belonging to described first video and the second video and the recommendation list group belonging to described second video；
Described video introduces unit, for the parameter value calculation institute according to described tabulation group and described recommendation list group
State first video incorporation way for described second video, described first video is incorporated into described recommendation list group；
Described video recommendations unit, for recommending described first video according to the position in described recommendation list group.
The video recommendations device that the present invention provides, for the first video of newly uploading according to the category column belonging to the first video
Having there is video and carried out classification judgement in the recommendation information of table group, determines the mode of final first video recommendations before combining.By
This, can improve the recommendation results of the first video newly uploaded, it is achieved pushes away the first video newly uploaded fast and effectively
Recommending, also improve the clicking rate of video while improve user satisfaction, Consumer's Experience is good.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this
Bright schematic description and description is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of a kind of video recommendation method first embodiment that the present invention provides；
Fig. 2 is the structured flowchart of a kind of video recommendations device first embodiment that the present invention provides.
Detailed description of the invention
Various exemplary embodiments, feature and the aspect of the present invention is described in detail below with reference to accompanying drawing.In accompanying drawing identical
Reference represent the same or analogous element of function.Although the various aspects of embodiment shown in the drawings, but remove
Non-specifically is pointed out, it is not necessary to accompanying drawing drawn to scale.
The most special word " exemplary " means " as example, embodiment or illustrative ".Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
It addition, in order to better illustrate the present invention, detailed description of the invention below gives numerous details.
It will be appreciated by those skilled in the art that do not have some detail, the present invention equally implements.In some instances, for
Method well known to those skilled in the art, means, element and circuit are not described in detail, in order to highlight the purport of the present invention.
Seeing Fig. 1, this figure is the flow chart of a kind of video recommendation method first embodiment that the present invention provides.Including:
Step S101, obtain the identification information of the first video.
Specifically, user can voluntarily by electric terminal to server uploaded videos, as the first video.Referred to herein
Electric terminal, include but not limited to that user can be carried out by modes such as keyboard, mouse, remote controller, touch pad, handwriting equipments
The electronic product of man-machine interaction, such as, computer, mobile phone, personal digital assistant are (English: Personal Digital
PDA), notebook, desktop computer, intelligent television etc. Assistant, is called for short:.Server can include but not limited to network master
The cloud service group etc. that machine, single network server, multiple webserver collection or multiple server are constituted.
It should be noted that above-mentioned terminal, server etc. are not limited only to above-mentioned example, those skilled in the art should be able to be much of that
Solving, other existing or that be likely to occur the from now on subscriber equipment of other form, the network equipment and second video all can be suitable for
In the present invention, say, that the present invention is not intended to subscriber equipment, the network equipment and the concrete form of the second video.
Server, after obtaining the first video, obtains the identification information of the first video.Here identification information can be
The file name of one video, size, duration, uploader account number etc., it is also possible to for uploader for the attribute definition of the first video,
It is sport category video, record flap-type video, video etc. for some personage as defined video.Such as, user A was January 1
Upload video " Xiaobao diary one ", then the identification information of this video can include upload user account number " user A ", " January time
1 day ", video name " Xiaobao diary one ", duration 35 minutes, it is also possible to mark: label 1 " documentary film ", label 2 " child's video " etc.
Field.
S102, identification information according to described first video, determine the second video of association, described first video and second
Tabulation group belonging to video and the recommendation list group belonging to described second video.
In reality, have substantial amounts of video file server end is the most stored, these videos all can be divided into
Few two or more tabulation groups.Concrete, can be according to the ID of each video, access time, broadcasting
Video is classified by the fields such as time span, title (title), label.
Therefore, it can search, by this identification information, the video that being associated with property is strong, and by the first video and pass
The second video that connection property is strong is divided into same group.
Such as, video files names can include prefix and suffix, and prefix is any character that length is more than 0, and suffix is
Chinese figure or Arabic numerals, such as, video " transformer 1 ", video " Xiaobao diary two ", " Xiaobao diary three ".
First can search announced second video that there is identical characters according to the file name of the first video, then sentence
Whether the number of disconnected identical characters is more than predetermined threshold, finally by the number of identical characters more than announced the of predetermined threshold
Two videos are divided into same group.Here it is possible to take into full account the regulation requirement that character is similar, thus increase the accuracy of coupling.
Common, identical characters can be continuous print identical characters, it is also possible to for discontinuous identical characters.Such as, " Kangxu is micro-for video
Clothes inspect note in private " and " Kangxu imperial court " there are " health " and " prosperous " two continuous print identical characters.And by this keyword, the most permissible
Judge whether the two video belongs to the video that can be associated.
For example, it is assumed that upload video V2 " Xiaobao diary two ", video V3 " cook home cooking 2 " before user A, regard
Frequently V4 " going out travel notes ", video V5 " Xiaobao diary one " and video V6 " cook home cooking 1 ", and predetermined threshold is 3, then owing to regarding
Frequently the number of the identical characters that the title of V2 and video V5 exists is 4, and therefore, the number 4 of identical characters is more than predetermined threshold 3,
Thus video V2 and video V5 can be divided into same group, in like manner, owing to video V3 is identical with what the title of video V6 existed
The number of character is 5, and the number 5 of identical characters is more than predetermined threshold 3, thus can be divided into same by video V3 and video V6
Group.
This user A uploads " Xiaobao diary three ", then may determine that " Xiaobao diary two " " Xiaobao diary one " enters with it
Row association, forms tabulation group S.Further, according to uplink time " Xiaobao diary one " uplink time the earliest, this is " little
Precious diary three " uplink time the latest, so the location order in this tabulation group is " Xiaobao diary one ", " Xiaobao diary
Two ", " Xiaobao diary three ", namely the positional value that this video uploaded " Xiaobao diary three " is in tabulation group is S (V1)
=3, " Xiaobao diary two " positional value is S (V2)=2, " Xiaobao diary one " positional value is S (V3)=1, in this tabulation group
Whole objects be S (VALL)=3.
In tabulation group, " Xiaobao diary two " is closest to the video of this " Xiaobao diary three " uploaded.Therefore,
By " Xiaobao diary two " as the second video, search recommendation list group belonging to the second video.Here recommendation list group, mainly
Formed, the video inventory recommended for batch.It is assumed that " Xiaobao diary two " has been arranged on a child
In recommendation list group P of documentary film, positional value is P (V2), and the whole objects in recommendation list group have VALLIndividual.
S103, according to the first video described in the parameter value calculation of described tabulation group and described recommendation list group for institute
State the incorporation way of the second video, described first video is incorporated into described recommendation list group.
Owing to video has numerous mode classifications, each mode is both for different crowds.Such as: playing
After one action movie, the follow-up video that can show several same or similar themes.At this moment, in recommendation list group, the most not
The video of multiple same subject can be preserved simultaneously, may be that selection each in different tabulation groups one is recommended.
In this case, it is necessary to recommend up-to-date " the Xiaobao diary three " uploaded rather than on " the Xiaobao diary two " that be transmitted through.
And after in user has watched some series video, that the most typically can recommend in series one by one when recommending is every
One video.Such as, after finishing watching " Xiaobao diary one ", then can recommend " Xiaobao diary two " and " Xiaobao diary three ".
Therefore, in order to divide this video uploaded more accurately, improve the accuracy recommended, in addition it is also necessary to according to
First video and the relevant information of the second video being associated carry out calculating and judge.Concrete judge to need in which way to
First video is incorporated in recommendation list group.Specific as follows:
According to described first video and the second video in the positional value of described tabulation group and the recommendation of the second video
List group parameter value, it is judged that described first video is inserted in described recommendation list group or described first video is replaced described
Described second video in recommendation list group.
Here some numerical value, may include that
According to described first video positional value S (V in described tabulation group1), the second video is in described category column
Positional value S (V2) in table group, whole positional value S (V of tabulation groupALL), second video position in recommendation list group
Value P (V2), whole positional value P (V of recommendation list groupALL)。
After obtaining above-mentioned numerical value, start to calculate for the incorporation way value of the first video:
Wherein, described α is the constant between 0 to 1.
As the result f (V calculated1,V2) value more than 0 time, then it is assumed that the first video should be recommended jointly with the second video, will
Described first video is inserted in described recommendation list group.Result f (the V otherwise calculated1,V2) value less than or equal to 0 time, then it is assumed that
First video can not be recommended jointly with the second video, and described first video is replaced the second video in described recommendation list group.
It addition, when determining the recommendation list group that the first video is joined the second video place, it is also desirable to take into full account
The position of the first video introduced (insertion).If the position of relevant video recommendations falls far short, or adjacent mistake the most then cannot
Reach the effect correctly recommended to user.Therefore, the recommendation list group that the first video is inserted into the second video place is being determined
Time middle, first by the on position of below equation described first video of calculating:
Wherein, described ROUND is the function that rounds up.
S104, according in described recommendation list group position recommend described first video.
After the first video is incorporated into recommendation list group, the form shown according to recommendation list group, that frequency etc. requires is right
First video therein is recommended.
The video recommendation method that the present invention provides, for the first video (video newly uploaded), belonging to the first video
Tabulation group recommendation information combine before existed video carry out classification judge, determine final first video recommendations
Mode.Thus, it is possible to improve the recommendation results of the first video newly uploaded, it is achieved the first video newly uploaded quickly is had
The recommendation of effect, Consumer's Experience is good.
A kind of video recommendation method provided for the present invention above, on this basis, the present invention also provides for a kind of video and pushes away
Recommend device.Specific as follows:
Seeing Fig. 2, this figure is the theory diagram of a kind of video recommendations device first embodiment that the present invention provides.Including:
Identification information obtaining unit 10, list group acquiring unit 20, video introduce unit 30 and video recommendations unit 40.Wherein,
Identification information obtaining unit 10 is for obtaining the identification information of the first video.
Specifically, user can voluntarily by electric terminal to server uploaded videos, as the first video.Referred to herein
Electric terminal, include but not limited to that user can be carried out by modes such as keyboard, mouse, remote controller, touch pad, handwriting equipments
The electronic product of man-machine interaction, such as, computer, mobile phone, personal digital assistant are (English: Personal Digital
PDA), notebook, desktop computer, intelligent television etc. Assistant, is called for short:.Server can include but not limited to network master
The cloud service group etc. that machine, single network server, multiple webserver collection or multiple server are constituted.
It should be noted that above-mentioned terminal, server etc. are not limited only to above-mentioned example, those skilled in the art should be able to be much of that
Solving, other existing or that be likely to occur the from now on subscriber equipment of other form, the network equipment and second video all can be suitable for
In the present invention, say, that the present invention is not intended to subscriber equipment, the network equipment and the concrete form of the second video.
Server, after obtaining the first video, obtains the identification information of the first video.Here identification information can be
The file name of one video, size, duration, uploader account number etc., it is also possible to for uploader for the attribute definition of the first video,
It is sport category video, record flap-type video, video etc. for some personage as defined video.Such as, user A was January 1
Upload video " Xiaobao diary one ", then the identification information of this video can include upload user account number " user A ", " January time
1 day ", video name " Xiaobao diary one ", duration 35 minutes, it is also possible to mark: label 1 " documentary film ", label 2 " child's video " etc.
Field.
List group acquiring unit 20, for the identification information according to described first video, determines the second video of association, institute
State the tabulation group belonging to the first video and the second video and the recommendation list group belonging to described second video.
In reality, have substantial amounts of video file server end is the most stored, these videos all can be divided into
Few two or more tabulation groups.Concrete, can be according to the ID of each video, access time, broadcasting
Video is classified by the fields such as time span, title (title), label.
Therefore, the second video retrieval subelement searches, by this identification information, the video that being associated with property is strong, and
The second strong to first video and relatedness video is divided into same group by tabulation subelement.
Such as, video files names can include prefix and suffix, and prefix is any character that length is more than 0, and suffix is
Chinese figure or Arabic numerals, such as, video " transformer 1 ", video " Xiaobao diary two ", " Xiaobao diary three ".
First can search announced second video that there is identical characters according to the file name of the first video, then sentence
Whether the number of disconnected identical characters is more than predetermined threshold, finally by the number of identical characters more than announced the of predetermined threshold
Two videos are divided into same group.Here it is possible to take into full account the regulation requirement that character is similar, thus increase the accuracy of coupling.
Common, identical characters can be continuous print identical characters, it is also possible to for discontinuous identical characters.Such as, " Kangxu is micro-for video
Clothes inspect note in private " and " Kangxu imperial court " there are " health " and " prosperous " two continuous print identical characters.And by this keyword, the most permissible
Judge whether the two video belongs to the video that can be associated.
For example, it is assumed that upload video V2 " Xiaobao diary two ", video V3 " cook home cooking 2 " before user A, regard
Frequently V4 " going out travel notes ", video V5 " Xiaobao diary one " and video V6 " cook home cooking 1 ", and predetermined threshold is 3, then owing to regarding
Frequently the number of the identical characters that the title of V2 and video V5 exists is 4, and therefore, the number 4 of identical characters is more than predetermined threshold 3,
Thus video V2 and video V5 can be divided into same group, in like manner, owing to video V3 is identical with what the title of video V6 existed
The number of character is 5, and the number 5 of identical characters is more than predetermined threshold 3, thus can be divided into same by video V3 and video V6
Group.
This user A uploads " Xiaobao diary three ", then may determine that " Xiaobao diary two " " Xiaobao diary one " enters with it
Row association, forms tabulation group S.Further, according to uplink time " Xiaobao diary one " uplink time the earliest, this is " little
Precious diary three " uplink time the latest, so the location order in this tabulation group is " Xiaobao diary one ", " Xiaobao diary
Two ", " Xiaobao diary three ", namely the positional value that this video uploaded " Xiaobao diary three " is in tabulation group is S (V1)
=3, " Xiaobao diary two " positional value is S (V2)=2, " Xiaobao diary one " positional value is S (V3)=1, in this tabulation group
Whole objects be S (VALL)=3.
In tabulation group, " Xiaobao diary two " is closest to the video of this " Xiaobao diary three " uploaded.Therefore,
By " Xiaobao diary two " as the second video, recommendation list obtain subelement and search recommendation list group belonging to the second video.
Here recommendation list group, has been formed before being mainly, the video inventory recommended for batch.It is assumed that " Xiaobao diary
Two " being arranged in recommendation list group P of child's documentary film, positional value is P (V2), complete in recommendation list group
Portion's object has VALLIndividual.
Video introduces unit 30 for according to described in the parameter value calculation of described tabulation group and described recommendation list group
Described first video, for the incorporation way of described second video, is incorporated into described recommendation list group by the first video.
Owing to video has numerous mode classifications, each mode is both for different crowds.Such as: playing
After one action movie, the follow-up video that can show several same or similar themes.At this moment, in recommendation list group, the most not
The video of multiple same subject can be preserved simultaneously, may be that selection each in different tabulation groups one is recommended.
In this case, it is necessary to recommend up-to-date " the Xiaobao diary three " uploaded rather than on " the Xiaobao diary two " that be transmitted through.
And after in user has watched some series video, that the most typically can recommend in series one by one when recommending is every
One video.Such as, after finishing watching " Xiaobao diary one ", then can recommend " Xiaobao diary two " and " Xiaobao diary three ".
Therefore, in order to divide this video uploaded more accurately, improve the accuracy recommended, in addition it is also necessary to according to
First video and the relevant information of the second video being associated carry out calculating and judge.Concrete judge to need in which way to
First video is incorporated in recommendation list group.Specific as follows:
Numerical computations subelement according to described first video and the second video at the positional value of described tabulation group and
The recommendation list group parameter value of the second video.Incorporation way judgment sub-unit judges that described first video is inserted described recommendation arranges
Described second video in described recommendation list group is replaced in table group or by described first video.
Here some numerical value, may include that
According to described first video positional value S (V in described tabulation group1), the second video is in described category column
Positional value S (V in table group2), whole positional value S (V of tabulation groupALL), second video position in recommendation list group
Value P (V2), whole positional value P (V of recommendation list groupALL)。
After obtaining above-mentioned numerical value, start to calculate for the incorporation way value of the first video:
Wherein, described α is the constant between 0 to 1.
As the result f (V calculated1,V2) value more than 0 time, then it is assumed that the first video should be recommended jointly with the second video, will
Described first video is inserted in described recommendation list group.Result f (the V otherwise calculated1,V2) value less than or equal to 0 time, then it is assumed that
First video can not be recommended jointly with the second video, and described first video is replaced the second video in described recommendation list group.
It addition, when determining the recommendation list group that the first video is joined the second video place, it is also desirable to take into full account
The position of the first video introduced (insertion).If the position of relevant video recommendations falls far short, or adjacent mistake the most then cannot
Reach the effect correctly recommended to user.Therefore, the recommendation list group that the first video is inserted into the second video place is being determined
Time middle, the on position of incorporation way judgment sub-unit use below equation described first video of calculating:
Wherein, described ROUND is the function that rounds up.
Finally, video recommendations unit 40 recommends described first video according to the position in described recommendation list group.
After the first video is incorporated into recommendation list group, the form shown according to recommendation list group, that frequency etc. requires is right
First video therein is recommended.
The video recommendations device that the present invention provides, for the first video (video newly uploaded), belonging to the first video
Tabulation group recommendation information combine before existed video carry out classification judge, determine final first video recommendations
Mode.Thus, it is possible to improve the recommendation results of the first video newly uploaded, it is achieved the first video newly uploaded quickly is had
The recommendation of effect, Consumer's Experience is good.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art, in the technical scope that the invention discloses, can readily occur in change or replace, should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with described scope of the claims.
Claims (10)
1. a video recommendation method, it is characterised in that including:
Obtain the identification information of the first video；
According to the identification information of described first video, determine belonging to the second video of association, described first video and the second video
Tabulation group and described second video belonging to recommendation list group；
Described in parameter value calculation according to described tabulation group and described recommendation list group, the first video regards for described second
The incorporation way of frequency, is incorporated into described recommendation list group by described first video；
Described first video is recommended according to the position in described recommendation list group.
Recommendation method the most according to claim 1, it is characterised in that the described identification information according to described first video,
Determine belonging to the second video of association, described first video and the tabulation group belonging to the second video and described second video
Recommendation list group, particularly as follows:
Identification information according to described first video, as keyword, is searched and is reached to specify threshold value with described keyword similarity
Video, as the second video；
Obtain described second video it has been determined that tabulation group, as described first video and the tabulation of the second video
Group；
Obtain the recommendation list group of described second video.
Recommendation method the most according to claim 1 and 2, it is characterised in that described according to described tabulation group and recommendation
Described first video, for the incorporation way of described second video, is incorporated into by the first video described in the parameter value calculation of list group
The recommendation list group belonged to described in described second video, particularly as follows:
According to described first video and the second video in the positional value of described tabulation group and the recommendation list of the second video
Group parameter value, it is judged that described first video is inserted in described recommendation list group or described first video is replaced in described recommendation
Described second video in list group.
Recommendation method the most according to claim 3, it is characterised in that according to described first video and the second video described
The positional value of tabulation group and the recommendation list group parameter value of the second video, particularly as follows:
According to described first video positional value S (V in described tabulation group1), the second video is in described tabulation group
Positional value S (V2), whole positional value S (V of tabulation groupALL), second video positional value P in recommendation list group
(V2), whole positional value P (V of recommendation list groupALL), calculating incorporation way value:
Wherein, described α is the constant between 0 to 1；
If f is (V1,V2) value more than 0 time described first video is inserted in described recommendation list group, otherwise regard described first
Frequency replaces the second video in described recommendation list group.
Recommendation method the most according to claim 4, it is characterised in that described by the first video input to described recommendation list
In group, particularly as follows:
Calculate the on position of described first video:
Described ROUND is the function that rounds up.
6. a video recommendations device, it is characterised in that including: identification information obtaining unit, list group acquiring unit, video draw
Enter unit and video recommendations unit；
Described identification information obtaining unit, for obtaining the identification information of the first video；
Described list group acquiring unit, for according to the identification information of described first video, determines the second video of association, described
Tabulation group belonging to first video and the second video and the recommendation list group belonging to described second video；
Described video introduces unit, for according to described in the parameter value calculation of described tabulation group and described recommendation list group the
Described first video, for the incorporation way of described second video, is incorporated into described recommendation list group by one video；
Described video recommendations unit, for recommending described first video according to the position in described recommendation list group.
Recommendation apparatus the most according to claim 6, it is characterised in that described list group acquiring unit, including:
Second video retrieval subelement, for the identification information according to described first video as keyword, searches and described pass
Key word similarity reaches to specify the video of threshold value, as the second video；
Tabulation subelement, for obtain described second video it has been determined that tabulation group, as described first video
Tabulation group with the second video；
Recommendation list obtains subelement, for obtaining the recommendation list group of described second video.
8. according to the recommendation apparatus described in claim 6 or 7, it is characterised in that described video introduces unit, including:
Numerical computations subelement, for according to described first video and the second video at the positional value of described tabulation group and
The recommendation list group parameter value of the second video；
Incorporation way judgment sub-unit, is used for judging to insert in described recommendation list group or by described first described first video
Video replaces described second video in described recommendation list group.
Recommendation apparatus the most according to claim 6, it is characterised in that described numerical computations subelement, particularly as follows:
According to described first video positional value S (V in described tabulation group1), the second video is in described tabulation group
Positional value S (V2), whole positional value S (V of tabulation groupALL), second video positional value P in recommendation list group
(V2), whole positional value P (V of recommendation list groupALL), calculating incorporation way value:
Wherein, described α is the constant between 0 to 1；
If f is (V1,V2) value more than 0 time described first video is inserted in described recommendation list group, otherwise regard described first
Frequency replaces the second video in described recommendation list group.
Recommendation apparatus the most according to claim 9, it is characterised in that described by the first video input to described recommend row
In table group, particularly as follows:
Calculate the on position of described first video:
Described ROUND is the function that rounds up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610624780.6A CN106162351A (en) | 2016-08-02 | 2016-08-02 | A kind of video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610624780.6A CN106162351A (en) | 2016-08-02 | 2016-08-02 | A kind of video recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106162351A true CN106162351A (en) | 2016-11-23 |
Family
ID=57328530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610624780.6A Pending CN106162351A (en) | 2016-08-02 | 2016-08-02 | A kind of video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106162351A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604081A (en) * | 2016-12-30 | 2017-04-26 | Tcl集团股份有限公司 | Method and device for generating video recommendation pool |
| CN108769955A (en) * | 2018-05-16 | 2018-11-06 | 深圳市路上自驾有限公司 | Intelligent hand account notebook system, device and apparatus control method |
| CN109241301A (en) * | 2018-08-31 | 2019-01-18 | 北京优酷科技有限公司 | Resource recommendation method and device |
| WO2020007083A1 (en) * | 2018-07-04 | 2020-01-09 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing information associated with video, electronic device, and storage medium |
| WO2020037886A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳创维－Rgb电子有限公司 | Video associating method and device and computer readable storage medium |
| CN113242459A (en) * | 2021-07-13 | 2021-08-10 | 武汉斗鱼鱼乐网络科技有限公司 | New video exposure method, device, medium and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144499A1 (en) * | 2003-12-02 | 2005-06-30 | Sony Corporation | Information processor, information processing method and computer program |
| CN101990119A (en) * | 2009-08-03 | 2011-03-23 | 鸿富锦精密工业（深圳）有限公司 | Music video server and music video personalized setting method thereof |
| CN103164405A (en) * | 2011-12-08 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Generation method for relevant video data bank, recommendation method and recommendation system for relevant videos |
| CN104038790A (en) * | 2014-06-30 | 2014-09-10 | 北京奇艺世纪科技有限公司 | Video playing list updating method and system |
| CN105404698A (en) * | 2015-12-31 | 2016-03-16 | 海信集团有限公司 | Education video recommendation method and device |
-
2016
- 2016-08-02 CN CN201610624780.6A patent/CN106162351A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144499A1 (en) * | 2003-12-02 | 2005-06-30 | Sony Corporation | Information processor, information processing method and computer program |
| CN101990119A (en) * | 2009-08-03 | 2011-03-23 | 鸿富锦精密工业（深圳）有限公司 | Music video server and music video personalized setting method thereof |
| CN103164405A (en) * | 2011-12-08 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Generation method for relevant video data bank, recommendation method and recommendation system for relevant videos |
| CN104038790A (en) * | 2014-06-30 | 2014-09-10 | 北京奇艺世纪科技有限公司 | Video playing list updating method and system |
| CN105404698A (en) * | 2015-12-31 | 2016-03-16 | 海信集团有限公司 | Education video recommendation method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604081A (en) * | 2016-12-30 | 2017-04-26 | Tcl集团股份有限公司 | Method and device for generating video recommendation pool |
| CN108769955A (en) * | 2018-05-16 | 2018-11-06 | 深圳市路上自驾有限公司 | Intelligent hand account notebook system, device and apparatus control method |
| WO2020007083A1 (en) * | 2018-07-04 | 2020-01-09 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing information associated with video, electronic device, and storage medium |
| CN110691256A (en) * | 2018-07-04 | 2020-01-14 | 北京字节跳动网络技术有限公司 | Video associated information processing method and device, server and storage medium |
| US11250267B2 (en) | 2018-07-04 | 2022-02-15 | Beijing Bytedance Network Technology Co., Ltd. | Method and apparatus for processing information associated with video, electronic device, and storage medium |
| WO2020037886A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳创维－Rgb电子有限公司 | Video associating method and device and computer readable storage medium |
| CN109241301A (en) * | 2018-08-31 | 2019-01-18 | 北京优酷科技有限公司 | Resource recommendation method and device |
| CN113242459A (en) * | 2021-07-13 | 2021-08-10 | 武汉斗鱼鱼乐网络科技有限公司 | New video exposure method, device, medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106162351A (en) | A kind of video recommendation method and device | |
| CN104199896B (en) | The video similarity of feature based classification is determined and video recommendation method | |
| US8589434B2 (en) | Recommendations based on topic clusters | |
| KR101471940B1 (en) | Apparatus, System, Method and Computer Readable Recording Media Storing the Program for Related Recommendation of TV Program Contents and Web Contents | |
| US10387915B2 (en) | Digital magazine recommendations by topic | |
| CN106131601A (en) | Video recommendation method and device | |
| US20130290306A1 (en) | Recommendation engine | |
| CN109982155B (en) | Playlist recommendation method and system | |
| EP2568395A1 (en) | Method and apparatus for automatic generation of recommendations | |
| CN107704560B (en) | Information recommendation method, device and equipment | |
| CN103942257B (en) | Video search method and device | |
| US10019419B2 (en) | Method, server, browser, and system for recommending text information | |
| JP6291145B2 (en) | Information processing apparatus, information processing method, program, and storage medium | |
| CN103984740A (en) | Combination label based search page display method and system | |
| CN112507163B (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| CN109753601A (en) | Recommendation information clicking rate determines method, apparatus and electronic equipment | |
| CN109168047A (en) | Video recommendation method, device, server and storage medium | |
| CN105915956A (en) | Video content recommendation method, device, server and system | |
| CN112579913B (en) | Video recommendation method, device, equipment and computer readable storage medium | |
| CN107105349A (en) | A kind of video recommendation method | |
| JP5386660B1 (en) | Information processing apparatus, information processing method, and information processing program | |
| JP2010262534A (en) | Content information distribution device, method, and computer program | |
| CN111914079A (en) | Topic recommendation method and system based on user tags | |
| CN105630950A (en) | Guidance type search method and system | |
| CN111291217A (en) | Content recommendation method and device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100080 A 5 C, block A, China International Steel Plaza, 8 Haidian Avenue, Haidian District, Beijing. Applicant after: Youku network technology (Beijing) Co., Ltd. Address before: 100080 A 5 C, block A, China International Steel Plaza, 8 Haidian Avenue, Haidian District, Beijing. Applicant before: 1Verge Inc. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161123 |