CN106407401A - A video recommendation method and device - Google Patents
A video recommendation method and device Download PDFInfo
- Publication number
- CN106407401A CN106407401A CN201610839166.1A CN201610839166A CN106407401A CN 106407401 A CN106407401 A CN 106407401A CN 201610839166 A CN201610839166 A CN 201610839166A CN 106407401 A CN106407401 A CN 106407401A
- Authority
- CN
- China
- Prior art keywords
- video file
- video
- similarity
- file
- characteristic information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiments of the invention provide a video recommendation method and device and a terminal apparatus. The video recommendation method comprises the steps of acquiring the feature information of video files in a to-be-recommended video file set, wherein the video files in the to-be-recommended video file set are video files meeting preset conditions; determining the degree of similarity between each video file and a target video file according to the feature information of the video files; sorting the video files according to the order of the degrees of similarity and recommending the video files to users according to the sorting result. According to the embodiments, the degrees of similarity between different video files can be compared according to the feature information of the video files to determine the order for successive play of the video files; since the specific content and the mutual correlation degrees of video files are fully considered, the mutual correlation degrees of obtained recommendation results are relatively high.
Description
Technical field
The present invention relates to network application field, more particularly to a kind of video recommendation method and device.
Background technology
Becoming increasingly popular with computer network, people carry out on the net watching the joy such as film, TV play more and more
Happy activity.Video website often recommends video to user, to increase user's stickiness.
Usually, often multi-section video, this video recommendations mode, multi-section video are recommended to user according to temperature or timeliness
Between usually not certain degree of association, but also the radio hookup of multi-section video can not be carried out.
Content of the invention
The embodiment of the present invention mainly solving the technical problems that providing a kind of video recommendation method, device and electronic equipment,
Preferably video can be recommended to user.
For solving above-mentioned technical problem, one aspect of the present invention is：A kind of video recommendation method, institute are provided
The method of stating includes：Obtain the characteristic information that video file to be recommended concentrates video file；Wherein, described video clip to be recommended
In video file be the video file meeting predetermined condition；Each described video is determined according to the characteristic information of described video file
File and the similarity of target video file；And according to the order of similarity, described video file is ranked up, and according to
Ranking results recommend described video file to user.
Wherein, the described order according to similarity is ranked up to described video file, and according to ranking results to user
The step recommending described video file includes：Order according to similarity is ranked up to described video file；According to sequence knot
Fruit determines the continuous order play of described video file；And described video is recommended to user according to the order of described continuous broadcasting
File.
Wherein, determine that each described video file is similar to target video file according to the characteristic information of described video file
Degree, specially：Characteristic information according to described video file calculates corresponding characteristic vector, and is determined according to described characteristic vector
Each described video file and the similarity of target video document characteristic vector；Wherein, described characteristic information includes following at least one
Kind：Personage's sequence, content introduction, program category.
Wherein, described target video file is the video file that currently playing video file or user select.
Wherein, described predetermined condition includes predetermined hot pixel threshold or predetermined age threshold；Described acquisition is to be recommended to be regarded
Before the characteristic information of video file that frequency file is concentrated, also include：Filter out from video library and reach described predetermined focus
Threshold value or the video file of predetermined age threshold, determine described video clip to be recommended.
For solving above-mentioned technical problem, another technical solution used in the present invention is：A kind of video recommendations are provided
Device, including：Feature acquisition module, concentrates the characteristic information of video file for obtaining video file to be recommended；Wherein, described
The video file that video file to be recommended is concentrated is the video file meeting predetermined condition；Similarity calculation module, for basis
The characteristic information of described video file determines the similarity of each described video file and target video file；And recommending module,
For the order according to similarity, described video file is ranked up, and recommends described video literary composition according to ranking results to user
Part.
Wherein, described recommending module is used for：Order according to similarity is ranked up to described video file；According to sequence
Result determines the continuous order play of described video file；And according to the order of described continuous broadcasting to user recommend described in regard
Frequency file.
Wherein, described similarity calculation module be used for according to the characteristic information of described video file calculate corresponding feature to
Amount, and the similarity of each video file and target video file is determined according to described characteristic vector；Wherein, described characteristic information bag
Include following at least one：Personage's sequence, content introduction, program category.
Wherein, described predetermined condition includes predetermined hot pixel threshold or predetermined age threshold；Described device also includes regarding
Frequency acquisition module, for filtering out the video literary composition reaching described predetermined hot pixel threshold or predetermined age threshold from video library
Part, determines described video clip to be recommended.
For solving above-mentioned technical problem, another technical solution used in the present invention is：A kind of electronic equipment, bag are provided
Include：At least one processor；And, the memorizer being connected with least one processor communication described；Wherein, described memorizer is deposited
Containing can be by the instruction of at least one computing device described, and described instruction is by least one computing device described, so that institute
State at least one processor to be able to carry out：Obtain the characteristic information of each video file that video file to be recommended is concentrated；Wherein,
The video file that described video file to be recommended is concentrated is the video file meeting predetermined condition；According to each video file described
Characteristic information determine the similarity of each described video file and target video file；And according to similarity order to each institute
State video file to be ranked up, and recommend described video file according to ranking results to user.
Wherein, the described order according to similarity is ranked up to each described video file, and according to ranking results to
Described video file is recommended at family, including：Order according to similarity is ranked up to each described video file；According to ranking results
Determine the continuous order play of described video file；And described video literary composition is recommended to user according to the order of described continuous broadcasting
Part.
The embodiment of the present invention according to the similarity between the characteristic information analysis different video file of video file, to determine
The continuous order play of these video files, due to having taken into full account particular content and the association journey each other of video file
Degree, the interrelated degree of the recommendation results obtaining is higher.
Brief description
Fig. 1 is the video recommendation method flow chart in the embodiment of the present invention；
Fig. 2 is the video recommendation method flow chart in another embodiment of the present invention；
Fig. 3 is that in the embodiment of the present invention, the order according to similarity is ranked up to each video file, and according to sequence knot
Fruit recommends the method flow diagram of video file to user；
Fig. 4 is the structural representation of the video recommendations device in the embodiment of the present invention；
Fig. 5 is the structural representation of the video recommendations device in another embodiment of the present invention；
Fig. 6 is the hardware architecture diagram of the electronic equipment of execution video recommendation method provided in an embodiment of the present invention.
Specific embodiment
For the ease of understanding the present invention, below in conjunction with the accompanying drawings and specific embodiment, the present invention will be described in more detail.
Unless otherwise defined, all of technology that this specification is used and scientific terminology are led with the technology belonging to the present invention
The implication that the technical staff in domain is generally understood that is identical.The term being used in the description of the invention in this specification is simply
The purpose of description specific embodiment, is not intended to limit the present invention.The term "and/or" that this specification is used includes one
The arbitrary and all of combination of individual or multiple related Listed Items.
It should be noted that the executive agent of video recommendation method provided in an embodiment of the present invention can be terminal, for example,
Intelligent television, smart mobile phone, panel computer, notebook computer, desktop computer etc. or server.
It is further to note that hereafter all illustrating taking video recommendations as a example.It will be apparent to those skilled in the art that
" video " hereinafter could alternatively be other any one multimedia files such as voice, picture, document.
Refering to Fig. 1, it is the schematic flow sheet of the video recommendation method in the embodiment of the present invention.The method includes：
Step S10：Obtain the characteristic information of the video file that video file to be recommended is concentrated.
Wherein, each video file that this video file to be recommended is concentrated is the video file meeting predetermined condition.
Specifically, " video clip to be recommended " can be terminal select from video information storehouse meet predetermined condition
The set that constitutes of part or all of video file.Wherein " video information storehouse " can be that terminal is periodically or periodically or tactile
Send out what property ground obtained to network equipment, or network equipment periodically or periodically or triggering property ground pushes to terminal
Video information (including the mark of video, the brief introduction of video, label of video etc.).
Further, " video clip to be recommended " can also be that the satisfaction that server is selected from video information storehouse is pre-
The set that the part or all of video file of fixed condition is constituted.
Step S11：Determine that each video file is similar to target video file according to the characteristic information of described video file
Degree.
Specifically, described characteristic information can be multiple dimensions, covers the personage of video file, type, plot, content
Etc. many information.Video file that described target video file can be selected for currently playing video file, user and
In user's history data, viewing time is the longest or watches one of frequency highest video file, does not specifically limit here
Fixed.During the similarity of described target video file and target video file, can be believed according to the feature of some dimension
Breath determines the similarity of each video file and target video file, and this dimension can be the dimension that user pays close attention to target video file most
Degree or arbitrary dimension；Can also according to the characteristic information Integrated comparative of multiple dimensions, so that it is determined that each video file with
The similarity of target video file.
Step S12：Order according to similarity is ranked up to each video file, and is recommended to user according to ranking results
Video file.
Specifically, the similarity according to video file and target video file, arranges to each video file from high to low
Sequence, to generate recommendation results.For example, calculated the people information of each video file that video file to be recommended concentrates with
The similarity of the people information of target video, is then ranked up from high to low according to similarity, to generate qualified pushing away
Recommend result.Wherein, this target video can be video that currently playing video, user select etc..
Video recommendation method in the present embodiment, between the characteristic information analysis different video file of video file
Similarity, to determine the continuous order play of these video files, due to taken into full account video file particular content and
Correlation degree each other, the interrelated degree of the recommendation results obtaining is higher.
Another embodiment of the present invention provides a kind of video recommendation method, the explanation to each step in above-described embodiment
Equally applicable in the present embodiment, the method includes：
Step S21：Obtain the characteristic information of the video file that video file to be recommended is concentrated.
Wherein, the video file that this video file to be recommended is concentrated is the video file meeting predetermined condition.
Alternatively, this predetermined condition includes predetermined hot pixel threshold or predetermined age threshold, as shown in Fig. 2 in step
Before S21, the method can also include step S20：Filter out from video library (video information storehouse) and reach described predetermined heat
Point threshold value or predetermined age threshold, to determine this video clip to be recommended.
After video information storehouse updates, re-execute step S20, to retrieve this video clip to be recommended.
Alternatively, " characteristic information of video file " includes following at least one：Personage's sequence, content introduction, program class
Type.Other information can also be comprised when certainly implementing.
Step S22：Determine that each video file is similar to target video file according to the characteristic information of each video file
Degree.
Alternatively, step S22 is specially：Characteristic information according to described video file calculates corresponding characteristic vector, and
Determine the similarity of each video file and target video file according to characteristic vector.
When characteristic information sorts for personage, specially：First determine personage's dimension of video file, then obtain personage's dimension
In the corresponding sequence of each personage, then calculate the basic weight of personage.Generally, personage's dimension of video file can include this and regards
Performer involved by frequency file, role, director, welcome guest, host etc., personage's dimension of different video file may be different.This
The content included by personage's dimension is not specifically limited in embodiment.Performer's sequence under personage's dimension and a certain personage's dimension,
Generally can obtain from the metamessage of video.
When characteristic information is for content introduction, the story of a play or opera of this video can be introduced it is also possible to referred to as story introduction, content is simple
Jie, main contents, diversity story of a play or opera etc., the present embodiment does not limit the concrete form of content introduction.The content introduction of video file leads to
Often can obtain from the metamessage of video.
When characteristic information is for program category, " comedy, ancient costume, war, love, city ... " etc., video can be included
The program category of file generally can obtain from the metamessage of video.
As described above, determine the similarity of each video file and target video file according to the characteristic information of video file
When, the characteristic information of this employing is same type of characteristic information.In other embodiments, the characteristic information of this employing also may be used
To be different types of characteristic information, for example, when content introduction and program category are contrasted, there is same characteristic features information
(e.g., comedy) is as a reference information determining similarity.
Step S23：Order according to similarity is ranked up to each video file, and is recommended to user according to ranking results
Video file.
Alternatively, as shown in figure 3, step S23 includes：
Step S12a, the order according to similarity is ranked up to each video file.
Specifically, the similarity of video file and the target video file concentrated according to video file to be recommended, from height to
Low video file in video clip to be recommended is ranked up.
Step S12b, determines the continuous order play of video file according to ranking results.
Specifically, generate, according to ranking results, the video file list continuously automatically play.
Step S12c, recommends video file according to the continuous order play to user.
Specifically, video file list as above is pushed to client, and select this video file list in client
In first or n-th video file when playing out, then automatically play after the broadcasting completing this video file continuous,
Next video file.
Specifically, according to similarity order from big to small, the video file in video clip to be recommended can be entered
Row sequence, and choose the video file of the forward predetermined number of sequence, so that it is determined that these video files chosen continuously are broadcast
The order put.
Further, recommend video to user, specifically can include：In the complete target video of terminal plays, or playing
During, in the relevant position of user interface, show these video files according to the continuous order play.
Video recommendation method in the present embodiment, between the characteristic information analysis different video file of video file
Similarity, to determine the continuous order play of these video files, due to taken into full account video file particular content and
Correlation degree each other, the interrelated degree of the recommendation results obtaining is higher.
Refering to Fig. 4, it is the structural representation of the video recommendations device of the embodiment of the present invention.This device 40 includes feature and obtains
Module 41, similarity calculation module 42 and recommending module 43.
This feature acquisition module 41 is used for obtaining the characteristic information of the video file that video file to be recommended is concentrated.Wherein,
Each video file that this video file to be recommended is concentrated is the video file meeting predetermined condition.
Specifically, " video clip to be recommended " can be the satisfaction that terminal or server are selected from video information storehouse
The set that the part or all of video file of predetermined condition is constituted.Wherein " video information storehouse " can be terminal periodically or the cycle
Property ground or triggering property ground obtain to network equipment, or network equipment periodically or periodically or triggering property ground to
The information (mark of inclusion video, the brief introduction of video, label of video etc.) of the video that terminal pushes.
Alternatively, this predetermined condition includes predetermined hot pixel threshold or predetermined age threshold, as shown in figure 5, also including
Video acquiring module 51, reaches described predetermined hot pixel threshold or predetermined for filtering out from video library (video information storehouse)
The video file of age threshold, to determine this video clip to be recommended.
" characteristic information of video file " includes following at least one：Personage's sequence, content introduction, program category.Certainly
Other information can also be comprised when implementing.
This similarity calculation module 42 is used for determining each video file and target according to the characteristic information of described video file
The similarity of video file.
Alternatively, described target video file can be selected for currently playing video file, user video file and
In user's history data, viewing time is the longest or watches one of frequency highest video file, does not specifically limit here
Fixed.
Alternatively, when characteristic information sorts for personage, this similarity calculation module 42 is specifically：Embodiment first determines and regards
Personage's dimension of frequency file, then obtain the corresponding sequence of each personage in personage's dimension, then calculate the basic weight of personage.Logical
Often, personage's dimension of video can include performer involved by this video file, role, director, welcome guest, host etc., different
Personage's dimension of video file may be different.The content included by personage's dimension is not specifically limited in the present embodiment.Personage's dimension
Performer's sequence with a certain personage's dimension, generally can obtain from the metamessage of video.
When characteristic information is for content introduction, the story of a play or opera of this video can be introduced it is also possible to referred to as story introduction, content is simple
Jie, main contents, diversity story of a play or opera etc., the present embodiment does not limit the concrete form of content introduction.The content introduction of video file leads to
Often can obtain from the metamessage of video.
When characteristic information is for program category, " comedy, ancient costume, war, love, city ... " etc., video can be included
The program category of file generally can obtain from the metamessage of video.
Alternatively, the characteristic information that this similarity calculation module 42 is used for according to described video file calculates characteristic vector,
And the similarity of each described video file is determined according to described characteristic vector.
This recommending module 43 be used for according to the order of similarity, each video file is ranked up, and according to ranking results to
User recommends video file.
Alternatively, this recommending module 43 is used for：Order according to similarity is ranked up to each video file, according to sequence
Result determines the continuous order play of video file, and recommends video file according to the continuous order play to user.
Alternatively, this recommending module 43 can be according to similarity order from big to small, in video clip to be recommended
Video file be ranked up, and choose the video file of the forward predetermined number of sequence, so that it is determined that these chosen regard
The continuous order play of frequency file.
Further, this recommending module 43 can be also used for target video complete in terminal plays, or in the process play
In, in the relevant position of user interface, show these video files according to the continuous order play.
Video recommendations device in the present embodiment, between the characteristic information analysis different video file of video file
Similarity, to determine the continuous order play of these video files, due to taken into full account video file particular content and
Correlation degree each other, the interrelated degree of the recommendation results obtaining is higher.
Refer to Fig. 6, be that the hardware configuration of the electronic equipment of execution video recommendation method provided in an embodiment of the present invention shows
It is intended to,
Electronic equipment 60 includes：One or more processors 61 and memorizer 62, in Fig. 6 with a processor 61 be
Example.
Processor 61 and memorizer 62 can be connected by bus or other modes, to be connected as by bus in Fig. 6
Example.
Memorizer 62, as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
The corresponding program of video recommendation method in sequence, non-volatile computer executable program and module, the such as embodiment of the present invention
Instruction/module (for example, the feature acquisition module 41 shown in accompanying drawing 4, similarity calculation module 42 and recommending module 43).Processor
61 pass through to run the non-volatile software program being stored in memorizer 62, instruction and module, thus execute server is each
Plant application of function and data processing, that is, realize said method embodiment video recommendation method.
Memorizer 62 can include storing program area and storage data field, wherein, storing program area can storage program area,
Application program required at least one function；Storage data field can store according to video recommendations device using the number being created
According to etc..Additionally, memorizer 62 can include high-speed random access memory, nonvolatile memory can also be included, for example extremely
A few disk memory, flush memory device or other non-volatile solid state memory parts.In certain embodiments, memorizer
62 optional include the memorizer remotely located with respect to processor 61, these remote memories can by network connection to video
Recommendation apparatus.The example of above-mentioned network includes but is not limited to the Internet, intranet, LAN, mobile radio communication and its group
Close.
One or more of module stores in described memorizer 62, when by one or more of processors 61
During execution, execute the video recommendation method in above-mentioned any means embodiment, for example, execute the method in Fig. 1 described above
Step S10 is to step S12, the method and step S20 in Fig. 2 to step S23, the method and step S12a in Fig. 3 to step S12c, reality
Module 41-43 in existing Fig. 4 and the function of realizing module 51-54 in Fig. 5.
The said goods can perform the method that the embodiment of the present invention is provided, and possesses the corresponding functional module of execution method and has
Beneficial effect.The not ins and outs of detailed description in the present embodiment, can be found in the method that the embodiment of the present application is provided.
The electronic equipment of the embodiment of the present application exists in a variety of forms, including but not limited to:
(1) mobile communication equipment:The feature of this kind equipment is that possess mobile communication function, and to provide speech, data
Communicate as main target.This Terminal Type includes:Smart mobile phone (such as iPhone), multimedia handset, feature mobile phone, and low
End mobile phone etc..
(2) super mobile personal computer equipment:This kind equipment belongs to the category of personal computer, has calculating and processes work(
Can, typically also possess mobile Internet access characteristic.This Terminal Type includes:PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device:This kind equipment can show and play content of multimedia.This kind equipment includes:Audio frequency,
Video player (such as iPod), handheld device, e-book, and intelligent toy and portable car-mounted navigator.
(4) server:There is provided the equipment of the service of calculating, it is total that the composition of server includes processor, hard disk, internal memory, system
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, is therefore processing energy
The aspects such as power, stability, reliability, safety, extensibility, manageability require higher.
(5) other have the electronic installation of data interaction function.
Embodiments provide a kind of non-volatile computer readable storage medium storing program for executing, described computer-readable storage medium
Matter is stored with computer executable instructions, and this computer executable instructions is executed by one or more processors, such as in Fig. 6
One processor 61, can make said one or multiple processor can perform the video recommendations side in above-mentioned any means embodiment
Method, for example, to step S12, the method and step S20 in Fig. 2 is to step for the method and step S10 in execution Fig. 1 described above
Method and step S12a in S23, Fig. 3, to step S12c, realizes module 41-43 in Fig. 4 and realizes module 51-54 in Fig. 5
Function.
Embodiments provide a kind of computer program, when computer program is performed, realize above-mentioned
Music timing player method in meaning embodiment of the method, for example, the method and step S10 in execution Fig. 1 described above is to step
Method and step S20 in S12, Fig. 2, to step S23, the method and step S12a in Fig. 3 to step S12c, realizes the module in Fig. 4
41-43 and the function of realizing module 51-54 in Fig. 5.
Device embodiment described above is only that schematically the wherein said unit illustrating as separating component can
To be or to may not be physically separate, as the part that unit shows can be or may not be physics list
Unit, you can with positioned at a place, or can also be distributed on multiple NEs.Can be selected it according to the actual needs
In the purpose to realize this embodiment scheme for some or all of module.
Through the above description of the embodiments, those of ordinary skill in the art can be understood that each embodiment
Can realize by the mode of software plus general hardware platform naturally it is also possible to pass through hardware.Those of ordinary skill in the art can
The all or part of flow process realized in above-described embodiment method with understanding can be by computer program to instruct the hard of correlation
Completing, described program can be stored in a computer read/write memory medium part, and this program is upon execution, it may include as above
State the flow process of the embodiment of each method.Wherein, described storage medium can be magnetic disc, CD, read-only memory (Read-
Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
Finally it should be noted that：Above example only in order to the technical scheme of the application to be described, is not intended to limit；At this
Under the thinking of application, can also be combined between the technical characteristic in above example or different embodiment, step is permissible
Realized with random order, and there are many other changes of the different aspect of the application as above, in order to simple and clear, they do not have
Have and provide in details；Although being described in detail to the application with reference to the foregoing embodiments, the ordinary skill people of this area
Member should be understood：It still can be modified to the technical scheme described in foregoing embodiments, or to wherein part skill
Art feature carries out equivalent；And these modifications or replacement, do not make the essence of appropriate technical solution depart from each reality of the application
Apply the scope of a technical scheme.
It should be noted that giving the preferred embodiment of the present invention in the description of the present invention and its accompanying drawing, but,
The present invention can realize the embodiment however it is not limited to described by this specification by many different forms, these embodiments
Not as the extra restriction to present invention, the purpose providing these embodiments is to make the understanding to the disclosure
More thoroughly comprehensive.And, above-mentioned each technical characteristic continues to be mutually combined, form the various embodiments not being enumerated above, all
It is considered as the scope of description of the invention record；Further, for those of ordinary skills, can be according to the above description
Improved or converted, and all these modifications and variations all should be belonged to the protection domain of claims of the present invention.
Claims (10)
1. a kind of video recommendation method is it is characterised in that methods described includes：
Obtain the characteristic information that video file to be recommended concentrates video file；Wherein, what described video file to be recommended was concentrated regards
Frequency file is the video file meeting predetermined condition；
Determine the similarity of each described video file and target video file according to the characteristic information of described video file；And
Order according to similarity is ranked up to described video file, and recommends described video literary composition according to ranking results to user
Part.
2. video recommendation method according to claim 1 is it is characterised in that the described order according to similarity regards to described
Frequency file is ranked up, and recommends described video file according to ranking results to user, including：
Order according to similarity is ranked up to described video file；
Determine the continuous order play of described video file according to ranking results；And
Order according to described continuous broadcasting recommends described video file to user.
3. video recommendation method according to claim 1 is it is characterised in that true according to the characteristic information of described video file
Fixed each described video file and the similarity of target video file, specially：
Characteristic information according to described video file calculates characteristic vector, and determines each described video literary composition according to described characteristic vector
Part and the similarity of target video document characteristic vector；Wherein, described characteristic information includes following at least one：Personage's sequence,
Content introduction, program category.
4. the video recommendation method according to claim 1-3 any one is it is characterised in that described target video file is
The video file that currently playing video file or user select.
5. video recommendation method according to claim 1 is it is characterised in that described predetermined condition includes predetermined focus threshold
Value or predetermined age threshold；
Described obtain the characteristic information of video file that video file to be recommended is concentrated before, also include：
Filter out the video file reaching described predetermined hot pixel threshold or predetermined age threshold from video library, determine described
Video clip to be recommended.
6. a kind of video recommendations device is it is characterised in that include：
Feature acquisition module, concentrates the characteristic information of video file for obtaining video file to be recommended；Wherein, described to be recommended
The video file that video file is concentrated is the video file meeting predetermined condition；
Similarity calculation module, for determining each described video file and target video according to the characteristic information of described video file
The similarity of file；And
Recommending module, is ranked up to described video file for the order according to similarity, and according to ranking results to user
Recommend described video file.
7. device according to claim 6 is it is characterised in that described recommending module is used for：
Order according to similarity is ranked up to described video file；
Determine the continuous order play of described video file according to ranking results；And
Order according to described continuous broadcasting recommends described video file to user.
8. device according to claim 6 is it is characterised in that described similarity calculation module is used for according to described video literary composition
The characteristic information of part calculates corresponding characteristic vector, and determines each video file and target video file according to described characteristic vector
Similarity；Wherein, described characteristic information includes following at least one：Personage's sequence, content introduction, program category.
9. the device according to claim 6-8 any one is it is characterised in that described target video file is currently playing
Video file or the video file selected of user.
10. device according to claim 6 is it is characterised in that described predetermined condition includes predetermined hot pixel threshold or pre-
Fixed age threshold；Described device also includes video acquiring module, reaches described predetermined heat for filtering out from video library
Point threshold value or the video file of predetermined age threshold, determine described video clip to be recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610839166.1A CN106407401A (en) | 2016-09-21 | 2016-09-21 | A video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610839166.1A CN106407401A (en) | 2016-09-21 | 2016-09-21 | A video recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106407401A true CN106407401A (en) | 2017-02-15 |
Family
ID=57997948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610839166.1A Pending CN106407401A (en) | 2016-09-21 | 2016-09-21 | A video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407401A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577740A (en) * | 2017-08-28 | 2018-01-12 | 阿里巴巴集团控股有限公司 | The method and apparatus for determining next broadcasting content |
| CN108307240A (en) * | 2018-02-12 | 2018-07-20 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN108681601A (en) * | 2018-05-21 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of video sharing |
| CN109446379A (en) * | 2018-10-31 | 2019-03-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
| CN109618196A (en) * | 2018-12-20 | 2019-04-12 | 未来电视有限公司 | A kind of single method, apparatus of video volume, electronic equipment and storage medium |
| CN109672721A (en) * | 2018-10-23 | 2019-04-23 | 平安科技（深圳）有限公司 | Pushing method for media files, device, server-side and computer readable storage medium |
| CN110198460A (en) * | 2018-03-30 | 2019-09-03 | 腾讯科技（深圳）有限公司 | Choosing method and device, storage medium, the electronic device of media information |
| CN110446065A (en) * | 2019-08-02 | 2019-11-12 | 腾讯科技（武汉）有限公司 | A kind of video recalls method, apparatus and storage medium |
| CN110839167A (en) * | 2018-08-16 | 2020-02-25 | Tcl集团股份有限公司 | Video recommendation method and device and terminal equipment |
| CN110858914A (en) * | 2018-08-23 | 2020-03-03 | 北京优酷科技有限公司 | Video material recommendation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013089924A1 (en) * | 2011-12-14 | 2013-06-20 | Google Inc. | Video recommendation based on video co-occurrence statistics |
| CN105095431A (en) * | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for pushing videos based on behavior information of user |
| CN105404698A (en) * | 2015-12-31 | 2016-03-16 | 海信集团有限公司 | Education video recommendation method and device |
| CN105843857A (en) * | 2016-03-16 | 2016-08-10 | 合网络技术（北京）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 |
-
2016
- 2016-09-21 CN CN201610839166.1A patent/CN106407401A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013089924A1 (en) * | 2011-12-14 | 2013-06-20 | Google Inc. | Video recommendation based on video co-occurrence statistics |
| CN105095431A (en) * | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for pushing videos based on behavior information of user |
| CN105404698A (en) * | 2015-12-31 | 2016-03-16 | 海信集团有限公司 | Education video recommendation method and device |
| CN105843857A (en) * | 2016-03-16 | 2016-08-10 | 合网络技术（北京）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 |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577740A (en) * | 2017-08-28 | 2018-01-12 | 阿里巴巴集团控股有限公司 | The method and apparatus for determining next broadcasting content |
| CN108307240A (en) * | 2018-02-12 | 2018-07-20 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN108307240B (en) * | 2018-02-12 | 2019-10-22 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN110198460A (en) * | 2018-03-30 | 2019-09-03 | 腾讯科技（深圳）有限公司 | Choosing method and device, storage medium, the electronic device of media information |
| CN108681601A (en) * | 2018-05-21 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of video sharing |
| CN108681601B (en) * | 2018-05-21 | 2020-12-11 | 北京奇艺世纪科技有限公司 | Video sharing method and device and electronic equipment |
| CN110839167A (en) * | 2018-08-16 | 2020-02-25 | Tcl集团股份有限公司 | Video recommendation method and device and terminal equipment |
| CN110839167B (en) * | 2018-08-16 | 2021-05-28 | Tcl科技集团股份有限公司 | Video recommendation method and device and terminal equipment |
| CN110858914A (en) * | 2018-08-23 | 2020-03-03 | 北京优酷科技有限公司 | Video material recommendation method and device |
| CN110858914B (en) * | 2018-08-23 | 2021-11-26 | 阿里巴巴（中国）有限公司 | Video material recommendation method and device |
| CN109672721A (en) * | 2018-10-23 | 2019-04-23 | 平安科技（深圳）有限公司 | Pushing method for media files, device, server-side and computer readable storage medium |
| CN109672721B (en) * | 2018-10-23 | 2022-07-08 | 平安科技（深圳）有限公司 | Media file pushing method and device, server and computer readable storage medium |
| CN109446379A (en) * | 2018-10-31 | 2019-03-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
| CN109618196A (en) * | 2018-12-20 | 2019-04-12 | 未来电视有限公司 | A kind of single method, apparatus of video volume, electronic equipment and storage medium |
| CN110446065A (en) * | 2019-08-02 | 2019-11-12 | 腾讯科技（武汉）有限公司 | A kind of video recalls method, apparatus and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407401A (en) | A video recommendation method and device | |
| CN109819284B (en) | Short video recommendation method and device, computer equipment and storage medium | |
| US9659278B2 (en) | Methods, systems, and computer program products for displaying tag words for selection by users engaged in social tagging of content | |
| US20170169018A1 (en) | Method and Electronic Device for Recommending Media Data | |
| US8813060B2 (en) | Context aware application model for connected devices | |
| WO2017177630A1 (en) | Method and device for recommending personalized information | |
| CN107038044A (en) | The discrete loading method of game resource and system based on Unity3D | |
| US20150039608A1 (en) | Media content rankings for discovery of novel content | |
| US20170264973A1 (en) | Video playing method and electronic device | |
| CN107291352A (en) | Application program is redirected in a kind of word read method and its device | |
| CN105812941A (en) | Video playing method and device and electronic equipment | |
| CN104954872B (en) | video downloading method, video playing device, mobile terminal and storage medium | |
| US20170171334A1 (en) | Single-account multiple-preference recommendation method for video website and electronic device | |
| CN103617196B (en) | Recommend method, browser, server and the system of network address | |
| CN106294564A (en) | A kind of video recommendation method and device | |
| US10086294B2 (en) | Game service method and system | |
| CN104808889A (en) | Page switching method and electronic equipment | |
| CN106250182A (en) | File processing method and device and electronic equipment | |
| CN109791501B (en) | System and method for reducing download requirements | |
| CN106407434A (en) | Video pushing method and system | |
| CN109033285A (en) | Information-pushing method and device | |
| CN111125314A (en) | Display method of book query page, electronic device and computer storage medium | |
| CN107968963A (en) | The method and apparatus for showing local video front cover | |
| CN103457944A (en) | Method and device for pushing information and server | |
| CN103399879B (en) | The interested entity preparation method and device of daily record are searched for based on user |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170215 |