CN107707940A - Video sequencing method, device, server and system - Google Patents
Video sequencing method, device, server and system Download PDFInfo
- Publication number
- CN107707940A CN107707940A CN201711009109.1A CN201711009109A CN107707940A CN 107707940 A CN107707940 A CN 107707940A CN 201711009109 A CN201711009109 A CN 201711009109A CN 107707940 A CN107707940 A CN 107707940A
- Authority
- CN
- China
- Prior art keywords
- video
- module
- sequencing
- features
- sample
- 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- 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
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/74—Browsing; Visualisation therefor
- G06F16/743—Browsing; Visualisation therefor a collection of video files or sequences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user 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)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention discloses video sequencing method, device, server and system, and this method includes：Determine server current state；According to order models corresponding to server current state selection；Obtain the video features for treating sequencing video；The ranking score of sequencing video is treated according to calculating the video features and the order models；Treat that sequencing video is ranked up to described according to the ranking score, generate video sorted lists；The video sorted lists are pushed into client to be shown.Technical scheme, currently lain fallow working condition according to server current state namely user, select corresponding order models to be ranked up video so that video sequence more conforms to user's request, improves the Experience Degree that user watches video on the client.
Description
Technical field
The present invention relates to video technique field, more particularly, to a kind of video sequencing method, device, server and is
System.
Background technology
The fast development of internet communication, done shopping by internet for user, watch video, social activity, in addition it is online it is medical,
Health care etc. both provides great convenience；And user can produce the net of many during these internet behavioral activities
Network data, these data have all reacted hobby of the user during shopping or social activity, by counting these mergings
Reason classification, many data can be provided for the collection of user behavior feature and supported, such as can provide data for personalized push
On foundation.
As internet is fast-developing, network speed lifting particularly mobile network is raised speed, and video is watched whenever and wherever possible for user
Facility is provided；However, Internet video quantity and species are various, each user is not quite similar again to the preference degree of video, is video
Push, which is ordered into, carrys out greatly difficulty.More rational video sequence disclosure satisfy that the hobby degree of user, lifting video sequence institute band
The video click volume and viewing amount come.Far can not in the prior art according to the video sortord of backstage preset rules arrangement
Meets the needs of mobile video sequence.
Therefore it provides a kind of scheme of the video auto-sequencing of rationalization is this area urgent problem to be solved.
The content of the invention
A technical problem to be solved of the embodiment of the present invention is：It is unreasonable for the list of videos sequence of user's push,
Can not meet the needs of user.
A kind of video sequencing method of the embodiment of the present invention, device, server and system.The technical scheme is as follows：
First aspect according to embodiments of the present invention, there is provided a kind of video sequencing method, including：
Determine server current state；
According to order models corresponding to server current state selection；
Obtain the video features for treating sequencing video；
The ranking score of sequencing video is treated according to calculating the video features and the order models；
Treat that sequencing video is ranked up to described according to the ranking score, generate video sorted lists；
The video sorted lists are pushed into client to be shown.
Optionally, the determination server current state, including：
The server current state is determined according to the resources occupation rate of the server；
And/or
The server current state is determined according to current time.
Optionally, the video features for treating sequencing video include at least one of following：
Video type, video scoring, video renewal time, video is in past intraday number of clicks, frequently in the past one
Number of clicks in week, video is in past intraday searching times, and searching times of the video within past one week, video is in mistake
Intraday end broadcasting time, end broadcasting time of the video within past one week are removed, video was averagely broadcast within past one week
Success rate is put, video averagely terminated playing duration within past one week；
And/or the video features of sequencing video are treated in the acquisition, including：
Obtain previously selected characteristic type；
The video features of sequencing video are treated according to obtaining the characteristic type；
And/or the video features of sequencing video are treated in the acquisition, including：
The validity of sequencing video is treated described in detection；
When described when sequencing video is effective, the video features of sequencing video are treated described in acquisition.
Optionally, methods described also includes：
Server current state when being played according to Sample video, is grouped to the Sample video；
Obtain the video features and ranking score of Sample video in each Sample video group；
The video features and ranking score are trained, obtain order models corresponding to the Sample video group.
Optionally, methods described also includes：
The history for obtaining the client plays record；
Record is played according to the history and obtains the video sample；
And/or it is described the video features and ranking score are trained, including：
Rise (Coordinate Ascent) algorithm using coordinate to be trained the video features and ranking score；
And/or methods described also includes：
Broadcasting of the client to video in the video sorted lists is obtained to record；
According to the ranking score for playing record and adjusting video in the list of videos；
It is added to the video in the video sorted lists as Sample video in corresponding Sample video group；
Ranking score after the video features of video in the video sorted lists and adjustment regards to the sample
Order models corresponding to frequency group are trained, and obtain new order models.
Second aspect according to embodiments of the present invention, there is provided a kind of video collator, including：
Determining module, for determining server current state；
Selecting module, for the order models according to corresponding to server current state selection；
First acquisition module, the video features of sequencing video are treated for obtaining；
Computing module, for treating the sequence point of sequencing video according to the video features and order models calculating
Number；
Sort generation module, for treating that sequencing video is ranked up to described according to the ranking score, generation video row
Sequence table；
Pushing module, it is shown for the video sorted lists to be pushed into client.
Optionally, the determining module includes：First determination sub-module and/or the second determination sub-module,
First determination sub-module, for determining the current shape of the server according to the resources occupation rate of the server
State；
Second determination sub-module, for determining the server current state according to current time.
Optionally, the video features for treating sequencing video include at least one of following：
Video type, video scoring, video renewal time, video is in past intraday number of clicks, frequently in the past one
Number of clicks in week, video is in past intraday searching times, and searching times of the video within past one week, video is in mistake
Intraday end broadcasting time, end broadcasting time of the video within past one week are removed, video was averagely broadcast within past one week
Success rate is put, video averagely terminated playing duration within past one week；
And/or first acquisition module includes：First acquisition submodule and the second acquisition submodule,
First acquisition submodule, for obtaining previously selected characteristic type；
Second acquisition submodule, for treating the video features of sequencing video according to characteristic type acquisition；
And/or first acquisition module includes：Detection sub-module and the 3rd acquisition submodule,
The detection sub-module, for detecting the validity for treating sequencing video；
3rd acquisition submodule, for when sequencing video is effective, regarding for sequencing video to be treated described in acquisition when described
Frequency feature.
Optionally, described device also includes：Grouping module, the second acquisition module and training module,
The grouping module, server current state during for being played according to Sample video, enters to the Sample video
Row packet；
Second acquisition module, for obtaining the video features of Sample video and sequence point in each Sample video group
Number；
The training module, for being trained to the video features and ranking score, obtain the Sample video group
Corresponding order models.
Optionally, described device also includes：3rd acquisition module and the 4th acquisition module,
3rd acquisition module, the history for obtaining the client play record；
4th acquisition module, the video sample is obtained for playing record according to the history；
And/or the training module, for rising (Coordinate Ascent) algorithm to the video using coordinate
Feature and ranking score are trained；
And/or described device also includes：5th acquisition module, adjusting module and add module,
5th acquisition module, remember for obtaining broadcasting of the client to video in the video sorted lists
Record；
The adjusting module, for according to the ranking score for playing record and adjusting video in the list of videos；
Add module, corresponded to for the video in the video sorted lists to be added to as Sample video described in sample originally
In video group；
The training module, for the sequence after the video features of the video in the video sorted lists and adjustment
Fraction is trained to order models corresponding to the Sample video group, obtains new order models.
A kind of third aspect according to embodiments of the present invention, there is provided video sequence server, it is characterised in that including above-mentioned
Weigh the video collator described in device embodiment.
A kind of video ordering system, it is characterised in that including：Above-mentioned video sequence server and client,
The video sorted lists of generation are sent to the client by the video sequence server, and the client is to institute
Video sorted lists are stated to be shown.
Compared with prior art, technical scheme, currently lain fallow work according to server current state namely user
Make state, select corresponding order models to be ranked up video so that video sequence more conforms to user's request, improves user
The Experience Degree of video is watched on the client.
Below by drawings and examples, technical scheme is described in further detail.
Brief description of the drawings
The accompanying drawing of a part for constitution instruction describes embodiments of the invention, and is used to explain together with description
The principle of the present invention.
Referring to the drawings, according to following detailed description, the present invention can be more clearly understood, wherein：
Fig. 1 is the flow chart of the video sequencing method shown in the embodiment of the present invention；
Fig. 2 is the flow chart of the video sequencing method shown in another embodiment of the present invention；
Fig. 3 is the flow chart of the video sequencing method shown in another embodiment of the present invention；
Fig. 4 is the flow chart of the video sequencing method shown in another embodiment of the present invention；
Fig. 5 is the flow chart of the video sequencing method shown in another embodiment of the present invention；
Fig. 6 is the flow chart of the video sequencing method shown in another embodiment of the present invention；
Fig. 7 is the block diagram of the video collator shown in the embodiment of the present invention；
Fig. 8 is the block diagram of the determining module 701 shown in the embodiment of the present invention；
Fig. 9 is the block diagram of the first acquisition module 703 shown in the embodiment of the present invention；
Figure 10 is the block diagram of the first acquisition module 703 shown in another embodiment of the present invention；
Figure 11 is the block diagram of the video collator shown in another embodiment of the present invention；
Figure 12 is the block diagram of the video collator shown in another embodiment of the present invention；
Figure 13 is the block diagram of the video collator shown in another embodiment of the present invention.
Embodiment
The various exemplary embodiments of the present invention are described in detail now with reference to accompanying drawing.It should be noted that：Unless have in addition
Body illustrates that the unlimited system of part and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The scope of invention.
Simultaneously, it should be appreciated that for the ease of description, the size of the various pieces shown in accompanying drawing is not according to reality
Proportionate relationship draw.
The description only actually at least one exemplary embodiment is illustrative to be never used as to the present invention below
And its application or any restrictions that use.
It may be not discussed in detail for technology, method and apparatus known to person of ordinary skill in the relevant, but suitable
In the case of, the technology, method and apparatus should be considered as part for specification.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it need not be further discussed in subsequent accompanying drawing in individual accompanying drawing.
The embodiment of the present invention can apply to computer system/server, and it can be with numerous other universal or special calculating
System environments or configuration operate together.Suitable for be used together with computer system/server well-known computing system, ring
The example of border and/or configuration includes but is not limited to：Personal computer system, server computer system, thin client, thick client
Machine, hand-held or laptop devices, the system based on microprocessor, set top box, programmable consumer electronics, NetPC Network PC,
Little types Ji calculates machine Xi Tong ﹑ large computer systems and the distributed cloud computing technology environment including any of the above described system, etc..
Computer system/server can be in computer system executable instruction (such as journey performed by computer system
Sequence module) general linguistic context under describe.Generally, program module can include routine, program, target program, component, logic, number
According to structure etc., they perform specific task or realize specific abstract data type.Computer system/server can be with
Implement in distributed cloud computing environment, in distributed cloud computing environment, task is by by the long-range of communication network links
Manage what equipment performed.In distributed cloud computing environment, program module can be located at the Local or Remote meter for including storage device
In calculation system storage medium.
Fig. 1 is the flow chart of the video sequencing method shown in the embodiment of the present invention.As shown in figure 1, the video sequencing method
Applied in server, comprise the following steps：
Step S11, determine server current state；
Step S12, according to order models corresponding to the selection of server current state；
Step S13, obtain the video features for treating sequencing video；
Step S14, the ranking score for treating sequencing video is calculated according to video features and order models；
Step S15, sequencing video is treated according to ranking score and is ranked up, generate video sorted lists；
Step S16, video sorted lists are pushed to client and are shown.
Wherein, server current state includes the busy-idle condition of server, according to the busy-idle condition of server, it may be determined that
User is currently at leisure period or working hour.
In the present embodiment, currently lain fallow working condition according to server current state namely user, select corresponding sequence
Model is ranked up to video so that video sequence more conforms to user's request, improves user and watches video on the client
Experience Degree.
In another embodiment, determine server current state, including one of following at least two mode or it is following at least
The combination of two ways：
First, server current state is determined according to the resources occupation rate of server；
For example, when the resources occupation rate of server is more than or equal to 50%, determines that server is in busy, work as server
Resources occupation rate be less than 50%, determine that server is in idle.
2nd, server current state is determined according to current time.
For example, preset server idle, i.e. the user job period is：Working day, 2:00-18:00；
Server busy, i.e. user leisure the period be：0:00-2:00 and 18:00-0:00, and nonworkdays whole day.
It is the corresponding order models of video sequencing selection by determining server current state in the present embodiment so that row
Sequence result is more accurate, more meets user's request.
In another embodiment, treat the video features of sequencing video including at least one of following：
Video type, video scoring, video renewal time, video is in past intraday number of clicks, frequently in the past one
Number of clicks in week, video is in past intraday searching times, and searching times of the video within past one week, video is in mistake
Intraday end broadcasting time, end broadcasting time of the video within past one week are removed, video was averagely broadcast within past one week
Success rate is put, video averagely terminated playing duration within past one week.
In the specific implementation, for each video features, it can be used to lower character representation：
Aid_type, special edition type；
Aid_score, special edition scoring；
Aid_update_time, special edition renewal time；
Index_list_uid_cnt_td, special edition is in past intraday number of clicks；
Index_list_uid_cnt_7d, number of clicks of the special edition within past one week；
Index_search_uid_cnt_td, special edition is in past intraday searching times；
Index_search_uid_cnt_7d, searching times of the special edition within past one week；
Vv_ending_td, special edition is in past intraday end broadcasting time；
Vv_ending_7d, end broadcasting time of the special edition within past one week；
Vv_success_rate_7d, special edition averagely played success rate within past one week；
Vv_end_atime_sec_avg_7d special editions averagely terminated playing duration within past one week.
Optionally, the video features for sequence are not limited to features described above, may also comprise video playback time, video is fitted
Close age bracket etc..
In addition, also can the artificial selection video features to be used.Fig. 2 is the video row shown in another embodiment of the present invention
The flow chart of sequence method.As shown in Fig. 2 the video features for treating sequencing video are obtained, including：
Step S21, obtain previously selected characteristic type；
Step S22, the video features for treating sequencing video are obtained according to characteristic type.
In the present embodiment, it can be used to sort according to concern angle artificial selection of the temperature and user of video to video
Video features so that ranking results are more accurate, more meet user's request.
In another embodiment, the video much to fail is had in video display process, such as expired video, lost part
The video of data or second-rate video etc., if sequence pushes to client, the use of user can be greatly reduced
Experience.Therefore, before sequence, the validity of video is detected.Fig. 3 is the video sequence shown in another embodiment of the present invention
The flow chart of method.As shown in figure 3, the video features for treating sequencing video are obtained, including：
The validity of sequencing video is treated in step S31, detection；
Step S32, when when sequencing video is effective, the video features of sequencing video are treated in acquisition.
In the present embodiment, the validity for treating sequencing video is detected, can by detecting whether video can play,
Whether video quality, which meets preset requirement etc., determines whether video is effective, for the video of failure, is then pushed without sequence
To user.So, the validity of sequence rear video list is improved, user experience is more preferable.
Fig. 4 is the flow chart of the video sequencing method shown in another embodiment of the present invention.As shown in figure 4, this method is also wrapped
Include：
Step S41, server current state when being played according to Sample video, is grouped to Sample video；
Step S42, obtain the video features and ranking score of Sample video in each Sample video group；
Video features and ranking score are trained by step S43, obtain order models corresponding to Sample video group.
Wherein, coordinate can be used to rise (Coordinate Ascent) algorithm to instruct video features and ranking score
Practice.The order models are actually the corresponding relation between video features and ranking score, can show as one with multiple
The function of variable.
Ranking score can be that server side obtains according to the broadcasting record analysis of magnanimity client, also can be according to client
The video scoring option of setting obtains scoring of the user to video as ranking score.
In the present embodiment, server current state is grouped to sample data during previously according to video playback, for example, right
In film, TV play video, reproduction time is mostly server busy, i.e., user lies fallow the period；And in server idle, that is, use
Family working hour, the video of the types such as short-movie, newsflash is played mostly.Every group of video is trained respectively, obtains every group of sample
Order models corresponding to this video, to be used when subsequently being sorted to video.
Fig. 5 is the flow chart of the video sequencing method shown in another embodiment of the present invention.As shown in figure 5, in order to further
Improving the order models sequence degree of accuracy and validity, this method also includes：
Step S51, the history for obtaining client play record；
Step S52, record is played according to history and obtains video sample.
In the present embodiment, it can be broadcast for order models corresponding to the training of each client according to the history of the client
Put record and obtain video sample, carry out model training based on these video samples so that the sorted lists finally given more accord with
The hobby of the client user is closed, further improves user experience.
In addition, also can obtain history from client by periodicity for Sample video plays record to obtain, for example, often
7~15 days, the history for obtaining once the client played record, to collect stable Sample video.
Fig. 6 is the flow chart of the video sequencing method shown in another embodiment of the present invention.As shown in fig. 6, in order to further
The accurate and effective of ranking results is improved, this method also includes：
Step S61, obtain broadcasting of the client to video in video sorted lists and record；
Step S62, the ranking score for adjusting video in list of videos is recorded according to playing；
Step S63, it is added to the video in video sorted lists as Sample video in corresponding Sample video group；
Step S64, the ranking score after the video features of the video in video sorted lists and adjustment regard to sample
Order models corresponding to frequency group are trained, and obtain new order models.
In the present embodiment, according to user to sequence point corresponding to the broadcasting record adjustment video of video in sorted lists
Number, for example, ranking score is 1~100 integer, for the video of user's first choice viewing, its ranking score is increased by 10
Point；The video of viewing is selected for user second, its ranking score is increased by 8 points；For the video of the complete viewing of user, by it
Ranking score increases by 5 points；The video more than 60% is watched for user, its ranking score is increased by 3 points；Etc..Also will can use
Family selection ranking is combined with video-see degree, how much to determine ranking score increase.
So, the ranking score by user to the broadcasting record adjustment video of video in list of videos, and then to sequence
Model carries out further training study so that ranking results afterwards can more conform to the viewing hobby of user, user's body
Degree of testing is more preferable.
In another embodiment, for Sample video, can be grouped according to video type, for example, by Sample video
It is divided into film, TV, animation and variety etc., is respectively trained to obtain corresponding order models for every group of video.
Following is apparatus of the present invention embodiment, can be used for performing the inventive method embodiment.
Fig. 7 is the block diagram of the video collator shown in the embodiment of the present invention, the device can by software, hardware or
Both is implemented in combination with as some or all of of electronic equipment.As shown in fig. 7, the video collator 700, including：
Determining module 701, for determining server current state；
Selecting module 702, for the order models according to corresponding to the selection of server current state；
First acquisition module 703, the video features of sequencing video are treated for obtaining；
Computing module 704, the ranking score of sequencing video is treated for being calculated according to video features and order models；
Sort generation module 705, is ranked up for treating sequencing video according to ranking score, generates video Sorted list
Table；
Pushing module 706, it is shown for video sorted lists to be pushed into client.
Fig. 8 is the block diagram of the determining module 701 shown in the embodiment of the present invention, as shown in figure 8, optionally, determining module 701
Including：First determination sub-module 81 and/or the second determination sub-module 82,
First determination sub-module 81, for determining server current state according to the resources occupation rate of server；
Second determination sub-module 82, for determining server current state according to current time.
Optionally, treat the video features of sequencing video including at least one of following：
Video type, video scoring, video renewal time, video is in past intraday number of clicks, frequently in the past one
Number of clicks in week, video is in past intraday searching times, and searching times of the video within past one week, video is in mistake
Intraday end broadcasting time, end broadcasting time of the video within past one week are removed, video was averagely broadcast within past one week
Success rate is put, video averagely terminated playing duration within past one week.
Fig. 9 is the block diagram of the first acquisition module 703 shown in the embodiment of the present invention, as shown in figure 9, optionally, first obtains
Modulus block 703 includes：First acquisition submodule 91 and the second acquisition submodule 92,
First acquisition submodule 91, for obtaining previously selected characteristic type；
Second acquisition submodule 92, the video features of sequencing video are treated for being obtained according to characteristic type.
Figure 10 is the block diagram of the first acquisition module 703 shown in another embodiment of the present invention, and as shown in Figure 10, first obtains
Module 703 includes：The acquisition submodule 102 of detection sub-module 101 and the 3rd,
Detection sub-module 101, the validity of sequencing video is treated for detecting；
3rd acquisition submodule 102, for when when sequencing video is effective, the video features of sequencing video are treated in acquisition.
Figure 11 is the block diagram of the video collator shown in another embodiment of the present invention, as shown in figure 11, optionally, the dress
Putting 700 also includes：Grouping module 707, the second acquisition module 708 and training module 709,
Grouping module 707, server current state during for being played according to Sample video, divides Sample video
Group；
Second acquisition module 708, for obtaining the video features and ranking score of Sample video in each Sample video group；
Training module 709, for being trained video features and ranking score, obtain sorting corresponding to Sample video group
Model.
Optionally, training module 709, for rising (Coordinate Ascent) algorithm to video features using coordinate
And ranking score is trained.
Figure 12 is the block diagram of the video collator shown in another embodiment of the present invention, as shown in figure 12, optionally, the dress
Putting 700 also includes：3rd acquisition module 710 and the 4th acquisition module 711,
3rd acquisition module 710, the history for obtaining client play record；
4th acquisition module 711, video sample is obtained for playing record according to history.
Figure 13 is the block diagram of the video collator shown in another embodiment of the present invention, as shown in figure 13, optionally, the dress
Putting 700 also includes：5th acquisition module 712, adjusting module 713 and add module 714,
5th acquisition module 712, recorded for obtaining broadcasting of the client to video in video sorted lists；
Adjusting module 713, for according to the ranking score for playing video in record adjustment list of videos；
Add module 714, for being added to corresponding Sample video using the video in video sorted lists as Sample video
In group；
Training module 709, for the ranking score after the video features of the video in video sorted lists and adjustment
Order models corresponding to Sample video group are trained, obtain new order models.
The present invention also provides the video collator in a kind of video sequence server, including above-mentioned each embodiment.
The present invention also provides a kind of video ordering system, including the video sequence server in above-described embodiment and client
End,
The video sorted lists of generation are sent to the client by the video sequence server, and the client is to institute
Video sorted lists are stated to be shown.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, apparatus or computer program
Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
Although some specific embodiments of the present invention are described in detail by example, the skill of this area
Art personnel it should be understood that example above merely to illustrating, the scope being not intended to be limiting of the invention.The skill of this area
Art personnel are it should be understood that the feelings of scope and spirit of the present invention can not departed from
Under condition, above example is modified.The scope of the present invention is defined by the appended claims.
Claims (12)
- A kind of 1. video sequencing method, it is characterised in that including：Determine server current state；According to order models corresponding to server current state selection；Obtain the video features for treating sequencing video；The ranking score of sequencing video is treated according to calculating the video features and the order models；Treat that sequencing video is ranked up to described according to the ranking score, generate video sorted lists；The video sorted lists are pushed into client to be shown.
- 2. according to the method for claim 1, it is characterised in that the determination server current state, including：The server current state is determined according to the resources occupation rate of the server；And/orThe server current state is determined according to current time.
- 3. according to the method for claim 1, it is characterised in that the video features for treating sequencing video include it is following at least One：Video type, video scoring, video renewal time, video is in past intraday number of clicks, frequently within past one week Number of clicks, video is in past intraday searching times, and searching times of the video within past one week, video was in the past one End broadcasting time in it, end broadcasting time of the video within past one week, video within past one week it is average play into Power, video averagely terminated playing duration within past one week；And/orThe video features of sequencing video are treated in the acquisition, including：Obtain previously selected characteristic type；The video features of sequencing video are treated according to obtaining the characteristic type；And/or the video features of sequencing video are treated in the acquisition, including：The validity of sequencing video is treated described in detection；When described when sequencing video is effective, the video features of sequencing video are treated described in acquisition.
- 4. according to the method for claim 1, it is characterised in that methods described also includes：Server current state when being played according to Sample video, is grouped to the Sample video；Obtain the video features and ranking score of Sample video in each Sample video group；The video features and ranking score are trained, obtain order models corresponding to the Sample video group.
- 5. according to the method for claim 4, it is characterised in that methods described also includes：The history for obtaining the client plays record；Record is played according to the history and obtains the video sample；And/orIt is described that the video features and ranking score are trained, including：Rise (Coordinate Ascent) algorithm using coordinate to be trained the video features and ranking score；And/orMethods described also includes：Broadcasting of the client to video in the video sorted lists is obtained to record；According to the ranking score for playing record and adjusting video in the list of videos；It is added to the video in the video sorted lists as Sample video in corresponding Sample video group；Ranking score after the video features of video in the video sorted lists and adjustment is to the Sample video group Corresponding order models are trained, and obtain new order models.
- A kind of 6. video collator, it is characterised in that including：Determining module, for determining server current state；Selecting module, for the order models according to corresponding to server current state selection；First acquisition module, the video features of sequencing video are treated for obtaining；Computing module, for treating the ranking score of sequencing video according to the video features and order models calculating；Sort generation module, for treating that sequencing video is ranked up to described according to the ranking score, generates video Sorted list Table；Pushing module, it is shown for the video sorted lists to be pushed into client.
- 7. device according to claim 6, it is characterised in that the determining module includes：First determination sub-module and/or Second determination sub-module,First determination sub-module, for determining the server current state according to the resources occupation rate of the server；Second determination sub-module, for determining the server current state according to current time.
- 8. device according to claim 6, it is characterised in that the video features for treating sequencing video include it is following at least One：Video type, video scoring, video renewal time, video is in past intraday number of clicks, frequently within past one week Number of clicks, video is in past intraday searching times, and searching times of the video within past one week, video was in the past one End broadcasting time in it, end broadcasting time of the video within past one week, video within past one week it is average play into Power, video averagely terminated playing duration within past one week；And/orFirst acquisition module includes：First acquisition submodule and the second acquisition submodule,First acquisition submodule, for obtaining previously selected characteristic type；Second acquisition submodule, for treating the video features of sequencing video according to characteristic type acquisition；And/orFirst acquisition module includes：Detection sub-module and the 3rd acquisition submodule,The detection sub-module, for detecting the validity for treating sequencing video；3rd acquisition submodule, for when sequencing video is effective, treating that the video of sequencing video is special described in acquisition when described Sign.
- 9. device according to claim 6, it is characterised in that described device also includes：Grouping module, the second acquisition module And training module,The grouping module, server current state during for being played according to Sample video, divides the Sample video Group；Second acquisition module, for obtaining the video features and ranking score of Sample video in each Sample video group；The training module, for being trained to the video features and ranking score, it is corresponding to obtain the Sample video group Order models.
- 10. device according to claim 9, it is characterised in that described device also includes：3rd acquisition module and the 4th obtains Modulus block,3rd acquisition module, the history for obtaining the client play record；4th acquisition module, the video sample is obtained for playing record according to the history；And/orThe training module, for rising (Coordinate Ascent) algorithm to the video features and sequence using coordinate Fraction is trained；And/orDescribed device also includes：5th acquisition module, adjusting module and add module,5th acquisition module, recorded for obtaining broadcasting of the client to video in the video sorted lists；The adjusting module, for according to the ranking score for playing record and adjusting video in the list of videos；Add module, this video described in sample is corresponded to for the video in the video sorted lists to be added to as Sample video In group；The training module, for the ranking score after the video features of the video in the video sorted lists and adjustment Order models corresponding to the Sample video group are trained, obtain new order models.
- The server 11. a kind of video sorts, it is characterised in that including：Video any one of the claims 6-10 Collator.
- A kind of 12. video ordering system, it is characterised in that including：Described in the claims 11 video sequence server and Client,The video sorted lists of generation are sent to the client by the video sequence server, and the client regards to described Frequency sorted lists are shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711009109.1A CN107707940A (en) | 2017-10-25 | 2017-10-25 | Video sequencing method, device, server and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711009109.1A CN107707940A (en) | 2017-10-25 | 2017-10-25 | Video sequencing method, device, server and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107707940A true CN107707940A (en) | 2018-02-16 |
Family
ID=61183176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711009109.1A Pending CN107707940A (en) | 2017-10-25 | 2017-10-25 | Video sequencing method, device, server and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107707940A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108345696A (en) * | 2018-03-20 | 2018-07-31 | 广东欧珀移动通信有限公司 | Card sort method, device, server and storage medium |
| CN108600780A (en) * | 2018-05-07 | 2018-09-28 | 上海掌门科技有限公司 | Method for pushed information |
| CN109600434A (en) * | 2018-12-06 | 2019-04-09 | 上海博泰悦臻电子设备制造有限公司 | Vehicle radio station program listens to method, radio station APP, car networking server, system |
| CN115174997A (en) * | 2022-06-29 | 2022-10-11 | Vidaa国际控股(荷兰)公司 | Display device and medium resource recommendation method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070165638A1 (en) * | 2006-01-13 | 2007-07-19 | Cisco Technology, Inc. | System and method for routing data over an internet protocol security network |
| CN104462611A (en) * | 2015-01-05 | 2015-03-25 | 五八同城信息技术有限公司 | Modeling method, ranking method, modeling device and ranking device for information ranking model |
| CN104462573A (en) * | 2014-12-29 | 2015-03-25 | 北京奇艺世纪科技有限公司 | Method and device for displaying video retrieval results |
| CN105282565A (en) * | 2015-09-29 | 2016-01-27 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN105447045A (en) * | 2014-09-02 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Information ordering method and device and information providing method and system |
| US20160148287A1 (en) * | 2014-11-21 | 2016-05-26 | Peach Labs, Inc. | Lunch order communication |
-
2017
- 2017-10-25 CN CN201711009109.1A patent/CN107707940A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070165638A1 (en) * | 2006-01-13 | 2007-07-19 | Cisco Technology, Inc. | System and method for routing data over an internet protocol security network |
| CN105447045A (en) * | 2014-09-02 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Information ordering method and device and information providing method and system |
| US20160148287A1 (en) * | 2014-11-21 | 2016-05-26 | Peach Labs, Inc. | Lunch order communication |
| CN104462573A (en) * | 2014-12-29 | 2015-03-25 | 北京奇艺世纪科技有限公司 | Method and device for displaying video retrieval results |
| CN104462611A (en) * | 2015-01-05 | 2015-03-25 | 五八同城信息技术有限公司 | Modeling method, ranking method, modeling device and ranking device for information ranking model |
| CN105282565A (en) * | 2015-09-29 | 2016-01-27 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108345696A (en) * | 2018-03-20 | 2018-07-31 | 广东欧珀移动通信有限公司 | Card sort method, device, server and storage medium |
| CN108345696B (en) * | 2018-03-20 | 2021-03-12 | Oppo广东移动通信有限公司 | Card sorting method, device, server and storage medium |
| CN108600780A (en) * | 2018-05-07 | 2018-09-28 | 上海掌门科技有限公司 | Method for pushed information |
| CN108600780B (en) * | 2018-05-07 | 2020-10-16 | 上海掌门科技有限公司 | Method for pushing information, electronic device and computer readable medium |
| CN109600434A (en) * | 2018-12-06 | 2019-04-09 | 上海博泰悦臻电子设备制造有限公司 | Vehicle radio station program listens to method, radio station APP, car networking server, system |
| CN109600434B (en) * | 2018-12-06 | 2022-10-18 | 博泰车联网科技(上海)股份有限公司 | Vehicle-mounted radio station program listening method, radio station APP, internet of vehicles server and system |
| CN115174997A (en) * | 2022-06-29 | 2022-10-11 | Vidaa国际控股(荷兰)公司 | Display device and medium resource recommendation method |
| CN115174997B (en) * | 2022-06-29 | 2023-11-28 | Vidaa国际控股(荷兰)公司 | Display device and media asset recommendation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107515909B (en) | Video recommendation method and system | |
| CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
| CN105138624B (en) | A kind of personalized recommendation method based on online course user data | |
| CN110737859B (en) | UP master matching method and device | |
| CN107707940A (en) | Video sequencing method, device, server and system | |
| CN106528813A (en) | Multimedia recommendation method and apparatus | |
| US20130024813A1 (en) | Method, system, and means for expressing relative sentiments towards subjects and objects in an online environment | |
| CN106126524B (en) | Information pushing method and device | |
| WO2020088058A1 (en) | Information generating method and device | |
| CN107341272A (en) | A kind of method for pushing, device and electronic equipment | |
| CN106846094A (en) | A kind of method and apparatus for recommending application message based on application has been installed | |
| CN110807150A (en) | Information processing method and device, electronic equipment and computer readable storage medium | |
| CN103020845A (en) | Mobile application pushing method and system | |
| CN111090809A (en) | Topic recommendation method and device, computer equipment and storage medium | |
| CN108322317A (en) | A kind of account identification correlating method and server | |
| CN113535991B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN113742567B (en) | Recommendation method and device for multimedia resources, electronic equipment and storage medium | |
| CN107944026A (en) | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation | |
| CN108009194A (en) | A kind of books method for pushing, electronic equipment, storage medium and device | |
| CN112734142B (en) | Resource learning path planning method and device based on deep learning | |
| CN106844504A (en) | A kind of method and apparatus for sending the single mark of song | |
| CN113886633B (en) | Video recommendation, device, equipment and storage medium based on artificial intelligence | |
| CN115565680A (en) | Individualized cognitive training system of cognitive assessment result based on game behavior analysis | |
| CN110471721A (en) | Page display method and system, electronic equipment and storage medium | |
| CN114282095A (en) | Course recommendation method, device and equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |