CN109672936A - A kind of the determination method, apparatus and electronic equipment of video evaluations collection - Google Patents
A kind of the determination method, apparatus and electronic equipment of video evaluations collection Download PDFInfo
- Publication number
- CN109672936A CN109672936A CN201811603478.8A CN201811603478A CN109672936A CN 109672936 A CN109672936 A CN 109672936A CN 201811603478 A CN201811603478 A CN 201811603478A CN 109672936 A CN109672936 A CN 109672936A
- Authority
- CN
- China
- Prior art keywords
- video
- segment
- unit
- intercepted
- interception
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
Abstract
The embodiment of the invention provides a kind of determination method, apparatus of video evaluations collection and electronic equipments, the method comprise the steps that the video clip for obtaining video platform user for video to be assessed intercepts record, wherein, the video clip interception record includes initial time and the end time for being respectively intercepted video clip；According to each initial time and end time for being intercepted video clip of video clip interception record, the interception number that the constituent parts segment of different periods in the video to be assessed is intercepted is calculated；The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；According to default clustering algorithm, each unit-segment to be polymerized is polymerize sequentially in time, obtains each target video sequence；The set that each target video sequence is formed, is determined as the assessment collection of the video to be assessed.The present invention, which realizes, efficiently obtains the assessment collection of video.
Description
Technical field
The present invention relates to field of computer technology, more particularly to the determination method, apparatus and electricity of a kind of video evaluations collection
Sub- equipment.
Background technique
Video website can do various analyses to online video, analyze whether online video is liked by spectators, analysis view
The part that frequency is liked by spectators is promoted and is runed etc. to do to orient with this, the user experience of Lai Tigao video website.
Video is analyzed, it is thus necessary to determine that the assessment collection of video.In the prior art in the assessment collection for determining video,
It needs to mark after personnel manually finish watching video, score is got to video frame, the video frame that these are graded is as each video
Assessment collection.However, this mode, which needs to mark personnel, looks first at complete video, there is whole understanding to entire video, so
See video again again afterwards, score provided to each frame in video, mark the heavy workload of personnel and due to the frame number of video too
More, mark personnel can the forgetting that marks of front and in label subsequent.
As it can be seen that determining that the assessment collection efficiency of video is lower in such a way that mark personnel manually mark.Therefore, how to realize
The assessment collection of video efficiently is obtained, is still a technical problem to be solved urgently.
Summary of the invention
The determination method, apparatus and electronic equipment for being designed to provide a kind of video evaluations collection of the embodiment of the present invention, with
It realizes and efficiently obtains the assessment collection of video.Specific technical solution is as follows:
In a first aspect, the embodiment of the invention discloses a kind of determination methods of video evaluations collection, which comprises
The video clip that video platform user is obtained for video to be assessed intercepts record, wherein the video clip is cut
Taking record includes initial time and the end time for being respectively intercepted video clip；
According to each initial time and end time for being intercepted video clip of video clip interception record, meter
Calculate the interception number that the constituent parts segment of different periods in the video to be assessed is intercepted；
The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；
According to default clustering algorithm, each unit-segment to be polymerized is polymerize sequentially in time, obtains each mesh
Mark video sequence；
The set that each target video sequence is formed, is determined as the assessment collection of the video to be assessed.
Optionally, the method also includes: the default unit time is obtained, using the unit time as dividing unit, by institute
It states video logic to be assessed and is divided into multiple unit-segments.
Optionally, each initial time for being intercepted video clip according to video clip interception record and
End time calculates the interception number that the constituent parts segment of different periods in the video to be assessed is intercepted, comprising:
For it is each it is described be intercepted video clip, determine that this is intercepted packet in the initial time of video clip and end time
The constituent parts segment contained；
For each unit-segment, add up the interception number that the unit-segment is intercepted video.
Optionally, in the unit-segment chosen interception number and be not less than preset threshold, each unit piece to be polymerized is obtained
Before section, the method also includes:
The mean value that constituent parts segment is intercepted the interception number of video is calculated, using the mean value as the preset threshold.
Optionally, described according to default clustering algorithm, each unit-segment to be polymerized is gathered sequentially in time
It closes, obtains each target video sequence, comprising:
Sequentially in time, it sorts to each unit-segment to be polymerized；
Each unit-segment to be polymerized according to the core radius and density of default DBSCAN algorithm, after determining sequence
Each target video sequence formed.
Second aspect, the embodiment of the invention discloses a kind of determining device of video evaluations collection, described device includes:
Video clip interception record obtains module, the video clip for being directed to video to be assessed for obtaining video platform user
Interception record, wherein the video clip interception record includes initial time and the end time for being respectively intercepted video clip；
Unit-segment intercepts number determining module, for described being intercepted view according to each of video clip interception record
The initial time of frequency segment and end time calculate section that the constituent parts segment of different periods in the video to be assessed is intercepted
Take number；
Unit-segment determining module to be polymerized, the unit-segment for being not less than preset threshold for choosing interception number, obtains
Each unit-segment to be polymerized；
Target video sequence determining module, for according to default clustering algorithm, to each unit-segment to be polymerized according to
Time sequencing is polymerize, and each target video sequence is obtained；
Video evaluations collection determining module to be assessed, the set for forming each target video sequence, is determined as institute
State the assessment collection of video to be assessed.
Optionally, described device further include:
Unit-segment determining module is specifically used for obtaining the default unit time, will using the unit time as dividing unit
The video logic to be assessed is divided into multiple unit-segments.
Optionally, the unit-segment intercepts number determining module, comprising:
Unit-segment determines submodule, for for it is each it is described be intercepted video clip, determine that this is intercepted video clip
Initial time and the constituent parts segment that includes in the end time；
Unit-segment interception number determines submodule, for being directed to each unit-segment, adds up the unit-segment and is cut
Take the interception number of video.
Optionally, described device further include:
Preset threshold determining module, the mean value for being intercepted the interception number of video for calculating constituent parts segment, will be described
Mean value is as the preset threshold.
Optionally, the target video sequence determining module, comprising:
Unit-segment sorting sub-module to be polymerized, for sequentially in time, sorting to each unit-segment to be polymerized；
Target video sequence determines submodule, for the core radius and density according to default DBSCAN algorithm, determines
Each target video sequence that each unit-segment to be polymerized after sequence is formed.
The third aspect, the embodiment of the invention discloses a kind of electronic equipment, including processor, communication interface, memory and
Communication bus, wherein processor, communication interface, memory complete mutual communication by communication bus；
Memory, for storing computer program；
Processor, when for executing the program stored on memory, in the determination method of realizing above-mentioned video evaluations collection
Any method and step.
Another aspect, the embodiment of the invention discloses a kind of computer readable storage medium, the computer-readable storage
Dielectric memory contains computer program, when the computer program is executed by processor, realizes the determination of above-mentioned video evaluations collection
Any method and step in method.
The embodiment of the invention also provides a kind of computer program products comprising instruction, when it runs on computers
When, realize any method and step in the determination method of above-mentioned video evaluations collection.
In a kind of determination method, apparatus of video evaluations collection provided in an embodiment of the present invention and electronic equipment, view is obtained
Frequency platform user intercepts record for the video clip of video to be assessed；It intercepts and records according to video clip, calculate view to be assessed
The interception number that constituent parts segment is intercepted in frequency；Choose interception number be not less than preset threshold unit-segment, obtain respectively to
Polymeric unit segment；According to default clustering algorithm, each unit-segment to be polymerized is polymerize sequentially in time, obtains each mesh
Mark video sequence；The set that each target video sequence is formed, is determined as the assessment collection of video to be assessed.Base of the embodiment of the present invention
In user interception video clip obtain video to be assessed assessment collection method, do not need manually mark can determine that it is to be evaluated
The assessment collection for estimating video saves the time compared to the mode manually marked, realizes and efficiently obtains the assessment collection of video.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described.
Fig. 1 is a kind of determination method flow diagram of video evaluations collection of the embodiment of the present invention；
Fig. 2 is the interception time that constituent parts segment is intercepted in a kind of determination method of video evaluations collection of the embodiment of the present invention
Number determines method flow diagram；
Fig. 3 is the interception time that constituent parts segment is intercepted in a kind of determination method of video evaluations collection of the embodiment of the present invention
Number display diagram；
Fig. 4 is that target video sequence determines method flow in a kind of determination method of video evaluations collection of the embodiment of the present invention
Figure；
Fig. 5 is that target video sequence determines method figure in a kind of determination method of video evaluations collection of the embodiment of the present invention；
Fig. 6 is a kind of determination apparatus structure schematic diagram of video evaluations collection of the embodiment of the present invention；
Fig. 7 is a kind of electronic equipment structural schematic diagram of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description.
Video website can accumulate the data of many user's viewings, such as played data, dragging number after runing a period of time
According to, barrage data etc., video website can fit curve using these data, show that video is liked by analyzing curve
Variation tendency.Specifically, under the reason of video website be can analyze at curve ascendant trend and peak, and analysis curve
The reason of drop and low ebb, and then make targeted decision.It is promoted it can be seen from the above, to make precisely effective orientation, it is bent
The tendency calculating of line will accurately, and how accurately the suggestion otherwise provided is invalid, and then how to be assessed the curve of calculating,
The accuracy rate of calculated curve, and objective accuracy rate is obtained, need to obtain objective assessment collection.
There are also a kind of artificial mask methods by Discrete in the prior art, with the mark of opposite reduction mark personnel
Form this.Specific method is that mark personnel mark out wonderful after finishing watching entire video, as long as mark personnel mark out view
Certain impressive several segment in frequency but also can solve not the problem of can not only having alleviated video specifically a certain frame is forgotten
The problem of providing specific value well does not need to provide specific excellent numerical value as long as marking out segment, the segment obtained in this way that
Do not need around here to separate it is specific which is more excellent, be par each other, be all wonderful, as long as handle when assessing
Model result discretization obtains segment and assesses.
Although this method greatly reduces mark difficulty, but there is still a need for mark personnel's marks, and wonderful is very subjective,
The result that different mark personnel mark out is different, and the result objectivity obtained in this way cannot be guaranteed.
As the above analysis, the assessment collection effect of video is determined in such a way that mark personnel manually mark in the prior art
Rate is lower.
In order to solve the technical issues of manually marking determining video evaluations collection low efficiency in the prior art, the embodiment of the present invention
Disclose determination, device, electronic equipment and the storage medium of a kind of video evaluations collection.Detailed process is as follows:
In a first aspect, the embodiment of the invention discloses a kind of determination methods of video evaluations collection, as shown in Figure 1.Fig. 1 is this
A kind of determination method flow diagram of video evaluations collection of inventive embodiments, the above method include:
S101, the video clip for obtaining video platform user for video to be assessed intercept record, wherein above-mentioned piece of video
Section interception record includes initial time and the end time for being respectively intercepted video clip.
The executing subject of the embodiment of the present invention can be the back-end server of video platform.In this step, video platform is obtained
User intercepts record for the video clip of video to be assessed, and video clip interception, which at least records, is respectively intercepted video clip
Initial time and end time.
This step can are as follows: in the database or log for saving video platform data, obtains the view for being directed to video to be assessed
Frequency segment interception record, the video clip interception record include at least respectively be intercepted video clip initial time and at the end of
Between.
S102, according to above-mentioned video clip interception record each above-mentioned initial time for being intercepted video clip and at the end of
Between, calculate the interception number that the constituent parts segment of different periods in above-mentioned video to be assessed is intercepted.
In this step, video to be assessed can be divided into multiple unit-segments, when being each intercepted the starting of video clip
Between and the end time in it is corresponding include the video to be assessed one or more unit-segments.And then it above-mentioned can be intercepted according to each
The initial time of video clip and end time calculate the interception that the constituent parts segment of different periods in video to be assessed is intercepted
Number.Interception number can react user to the favorable rating of the unit-segment, and as the interception number can indicate the unit-segment
Video frame excellent degree.
In this step, the interception number that the constituent parts segment of different periods in above-mentioned video to be assessed is intercepted is calculated, it can
Are as follows: video to be assessed is divided into multiple unit-segments, and will respectively be intercepted video clip and divide to multiple unit-segments, into
And the constituent parts segment of statistics available video different periods to be assessed is intercepted the number of video clip, obtains in video to be assessed not
The interception number quilt being intercepted with the constituent parts segment of period.
In addition, also the initial time for being respectively intercepted video clip and end time can be placed on together in the embodiment of the present invention
In one reference axis, minimum initial time and maximum end time are made into target time section, which are divided into multiple units
Segment, and then the constituent parts segment of statistics available different periods is intercepted the number of video clip, obtains different in video to be assessed
The interception number quilt that the constituent parts segment of period is intercepted.
Optionally, when executing S102, the default unit time can be first obtained, it, will using the above-mentioned unit time as dividing unit
Above-mentioned video logic to be assessed is divided into multiple unit-segments.
For example, the default unit time is second, millisecond, then the unit time can be second, millisecond.It can be by view to be assessed in this step
Frequency logical partitioning is multiple unit-segments.For example, collection TV play A to be assessed is 60 minutes, can segment in seconds, will
One collection TV play A is divided into multiple unit-segments.
This step can segment in seconds, video to be assessed is divided into multiple unit-segments.For each unit piece
Section, adds up the corresponding interception number for being intercepted video clip of the unit-segment, finally obtains constituent parts in the video to be assessed
Segment is intercepted the interception number of video.
S103 chooses the unit-segment that interception number is not less than preset threshold, obtains each unit-segment to be polymerized.
The excellent degree that estimation video is realized in this step needs to obtain the excellent higher video evaluations collection of degree, therefore,
In order to reduce calculation amount in this step, preset threshold can be set by implementing personnel, and then screen interception number and be not less than default threshold
The unit-segment of value.
In this step, the unit-segment that interception number is not less than preset threshold can be directly selected, each unit to be polymerized is obtained
Segment.Alternatively, deleting the unit-segment that interception number is lower than preset threshold in all unit-segments, obtaining each to be polymerized
Unit-segment.
Optionally, selecting video frame frequency number is obtained not less than the unit-segment of preset threshold to poly- before above-mentioned S103
Before closing unit-segment, the above method further include:
The mean value for calculating the interception number that constituent parts segment is intercepted, using above-mentioned mean value as above-mentioned preset threshold.
In this step, in order to which suitable preset threshold is arranged, the equal of the interception number that constituent parts segment is intercepted can be calculated
Value, using above-mentioned mean value as above-mentioned preset threshold.
S104 polymerize each above-mentioned unit-segment to be polymerized sequentially in time, obtains according to default clustering algorithm
Each target video sequence.
In this step, by presetting clustering algorithm, to each unit-segment to be polymerized obtained in S103, sequentially in time
Gathered, each target video sequence after being polymerize.
Wherein, default clustering algorithm can be DBSCAN algorithm.It is described in detail in specific clustering algorithm following embodiment.
S105, the set that each above-mentioned target video sequence is formed, is determined as the assessment collection of above-mentioned video to be assessed.
In a kind of determination method of video evaluations collection provided in an embodiment of the present invention, obtain video platform user be directed to
The video clip for assessing video intercepts record；It intercepts and records according to video clip, calculate constituent parts segment quilt in video to be assessed
The interception number of interception；The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；According to
Default clustering algorithm, polymerize each unit-segment to be polymerized sequentially in time, obtains each target video sequence；By each mesh
The set that video sequence is formed is marked, the assessment collection of video to be assessed is determined as.The video that the embodiment of the present invention is intercepted based on user
The method that segment obtains the assessment collection of video to be assessed, does not need manually to mark the assessment collection that can determine that video to be assessed,
Compared to the mode manually marked, the time is saved, realizes and efficiently obtains the assessment collection of video.
Optionally, in a kind of embodiment of the determination method of video evaluations collection of the invention, according to upper in above-mentioned S102
Each above-mentioned initial time for being intercepted video clip and the end time for stating video clip interception record, calculate above-mentioned view to be assessed
The interception number that the constituent parts segment of different periods is intercepted in frequency, can be as shown in Figure 2.Fig. 2 is one kind of the embodiment of the present invention
The interception number that constituent parts segment is intercepted in the determination method of video evaluations collection determines that method flow diagram, the above method include:
S201, for it is each it is above-mentioned be intercepted video clip, determine this be intercepted the initial time of video clip and at the end of
The interior constituent parts segment for including.
Video to be assessed for one finds out video clip interception record, includes each in video clip interception record
It is intercepted video clip, each interception segment has the start/stop time on the corresponding video playing item.In this step, determine each
It is intercepted the constituent parts segment for including in the initial time and end time of video clip.For example, the view that unit-segment is one second
Frequency segment.
S202 adds up the interception number that the unit-segment is intercepted video for each above-mentioned unit-segment.
For constituent parts segment, the interception number that the unit-segment is intercepted video is counted, is obtained in video to be assessed not
The interception number being intercepted with the constituent parts segment of period.For example, a kind of video evaluations collection of the embodiment of the present invention shown in Fig. 3
Determination method in the interception number display diagram that is intercepted of constituent parts segment.Abscissa indicates video frame, ordinate table in the Fig. 3
Show interception number.Each column-shape strip indicates that the unit-segment is intercepted the interception number of video, and interception number can react the unit
The video highlight degree of segment.The interception number of the as unit-segment is more, then the video of the unit-segment is more excellent.
It is intercepted the interception number of video by obtained constituent parts segment, different periods in the video to be assessed can be obtained
Constituent parts segment excellent value sequence.Such as { 2:10,3:12,4:9,8:10 }, the excellent value for being expressed as the 2nd second is the 10, the 3rd
Second, excellent value was 12, and so on.
As it can be seen that through the embodiment of the present invention, record can be intercepted based on video clip of the user to video to be assessed, obtain to
The video clip for assessing each unit-segment of video intercepts number, and the video highlight of each unit-segment is reflected by intercepting number
Degree, solves the problems, such as that handmarking determines the excellent degree low efficiency of video frame.
Optionally, in a kind of embodiment of the determination method of video evaluations collection of the present invention, according to default in above-mentioned S104
Clustering algorithm polymerize each above-mentioned unit-segment to be polymerized sequentially in time, obtains each target video sequence, can be such as figure
Shown in 4.Fig. 4 is that target video sequence determines method flow in a kind of determination method of video evaluations collection of the embodiment of the present invention
Figure, comprising:
S401 sequentially in time sorts to each above-mentioned unit-segment to be polymerized.
S402, it is each above-mentioned to be polymerized after determining sequence according to the core radius and density in default DBSCAN algorithm
Continuous each target video sequence that unit-segment is formed.
The DBSCAN algorithm sample set connected by density reachability relation export maximal density, the cluster the inside of this DBSCAN
There can be one or more kernel object.If only one kernel object, in cluster, other non-core object samples are all
In witnessing in coverage for this core；If there is multiple cores object, then the neighborhood of any one kernel object in cluster
In centainly have an other kernel object, otherwise the two kernel objects can not density it is reachable.The neighborhood of these kernel objects
In all sample the DBSCAN clustering cluster that is combined into of collection.
In the embodiment of the present invention, using the above-mentioned characteristic of DBSCAN algorithm, to each unit-segment to be polymerized after sequence into
Row cluster is clustered by each unit-segment to be polymerized according to kernel object, core radius to obtain reachable one or more of density
A continuous target video sequence.
It specifically can be as shown in figure 5, Fig. 5 be target video in a kind of determination method of video evaluations collection of the embodiment of the present invention
Sequence determines method figure.
The abscissa of Fig. 5 indicates video frame, and ordinate indicates that interception number, each column-shape strip indicate that the unit-segment is cut
The interception number of video is taken, interception number can react the video highlight degree of the unit-segment.Wherein, it is removed from column-shape strip single
Bit slice section intercepts the unit-segment that number is lower than preset threshold, obtains each unit-segment to be polymerized according to time sequence, will be to poly-
Closing unit-segment is excellent frame, while the corresponding video frame of these unit-segments of cleaning is denoted as non-excellent frame.
After eliminating non-excellent frame in excellent frame sequence after cleaning, excellent frame sequence becomes discontinuously, but by
There is continuity in video, if most of all very excellent at one, only intermediate a few frames are not excellent frames, and mutual phase
Then it is believed that the frame is also excellent frame away from very little, they can form an excellent sequence.Here the parameter of DBSCAN algorithm is set
Be set to core radius be 3, density 0.5, if meaning a certain frame or so 3 seconds and having in totally 7 seconds, 50% or more excellent frame (is here
Have 3 frames or more), although then having non-excellent frame in the continuous fragment of this 7 frame composition is also the excellent sequence clustered out.Such as Fig. 5 institute
Show, 1040 in figure at the left side have the excellent frame of 2 frames, there is the excellent frame of 1 frame on the right, in addition oneself itself is an excellent frame, front and back 3 seconds
There is the excellent frame of 4 frames in totally 7 seconds, this segment can form an excellent sequence, which is this hair
The target video sequence of bright embodiment.
Finally, the set that each target video sequence is formed, is determined as the assessment collection of video to be assessed of the embodiment of the present invention.
As it can be seen that video evaluations collection through the embodiment of the present invention determines method, do not need manually to mark can determine that
The assessment collection of assessment video saves the time compared to the mode manually marked, realizes and efficiently obtains the assessment of video
Collection.And it is based on user data, has obtained more objective assessment result.
Second aspect, the embodiment of the invention discloses a kind of determining devices of video evaluations collection, as shown in Figure 6.
Fig. 6 is a kind of determination apparatus structure schematic diagram of video evaluations collection of the embodiment of the present invention, and above-mentioned apparatus includes:
Video clip interception record obtains module 601, the video for being directed to video to be assessed for obtaining video platform user
Segment interception record, wherein above-mentioned video clip interception record include respectively be intercepted video clip initial time and at the end of
Between；
Unit-segment intercepts number determining module 602, for each above-mentioned being cut according to above-mentioned video clip interception record
Initial time and the end time of video clip are taken, the constituent parts segment for calculating different periods in above-mentioned video to be assessed is intercepted
Interception number；
Unit-segment determining module 603 to be polymerized, the unit-segment for being not less than preset threshold for choosing interception number, obtains
To each unit-segment to be polymerized；
Target video sequence determining module 604, for being pressed to each above-mentioned unit-segment to be polymerized according to default clustering algorithm
It is polymerize according to time sequencing, obtains each target video sequence；
Video evaluations collection determining module 605 to be assessed, the set for forming each above-mentioned target video sequence, is determined as
The assessment collection of above-mentioned video to be assessed.
In a kind of determining device of video evaluations collection provided in an embodiment of the present invention, obtain video platform user be directed to
The video clip for assessing video intercepts record；It intercepts and records according to video clip, calculate constituent parts segment quilt in video to be assessed
The interception number of interception；The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；According to
Default clustering algorithm, polymerize each unit-segment to be polymerized sequentially in time, obtains each target video sequence；By each mesh
The set that video sequence is formed is marked, the assessment collection of video to be assessed is determined as.The video that the embodiment of the present invention is intercepted based on user
The method that segment obtains the assessment collection of video to be assessed, does not need manually to mark the assessment collection that can determine that video to be assessed,
Compared to the mode manually marked, the time is saved, realizes and efficiently obtains the assessment collection of video.
Optionally, in a kind of embodiment of the determining device of video evaluations collection of the present invention, above-mentioned apparatus further include:
Unit-segment determining module is specifically used for obtaining the default unit time, will using the above-mentioned unit time as dividing unit
Above-mentioned video logic to be assessed is divided into multiple unit-segments.
Optionally, in a kind of embodiment of the determining device of video evaluations collection of the present invention, above-mentioned unit-segment interception time
Number determining module 602, comprising:
Unit-segment determines submodule, for for it is each it is above-mentioned be intercepted video clip, determine that this is intercepted video clip
Initial time and the constituent parts segment that includes in the end time；
Unit-segment interception number determines submodule, for being directed to each above-mentioned unit-segment, adds up the unit-segment and is cut
Take the interception number of video.
Optionally, in a kind of embodiment of the determining device of video evaluations collection of the present invention, above-mentioned apparatus further include:
Preset threshold determining module, the mean value for being intercepted the interception number of video for calculating constituent parts segment, will be above-mentioned
Mean value is as above-mentioned preset threshold.
Optionally, in a kind of embodiment of the determining device of video evaluations collection of the present invention, above-mentioned target video sequence is true
Cover half block 604, comprising:
Unit-segment sorting sub-module to be polymerized, for sequentially in time, sorting to each above-mentioned unit-segment to be polymerized；
Target video sequence determines submodule, for the core radius and density according to default DBSCAN algorithm, determines
Each target video sequence that each above-mentioned unit-segment to be polymerized after sequence is formed.
The third aspect, the embodiment of the invention discloses a kind of electronic equipment, as shown in Figure 7.Fig. 7 is the embodiment of the present invention
A kind of electronic equipment structural schematic diagram, including processor 701, communication interface 702, memory 703 and communication bus 704, wherein
Processor 701, communication interface 702, memory 703 complete mutual communication by communication bus 704；
Memory 703, for storing computer program；
Processor 701 when for executing the program stored on memory 703, realizes following methods step:
The video clip that video platform user is obtained for video to be assessed intercepts record, wherein above-mentioned video clip is cut
Taking record includes initial time and the end time for being respectively intercepted video clip；
Each above-mentioned initial time for being intercepted video clip and end time according to above-mentioned video clip interception record, meter
It counts in stating the interception number that the constituent parts segment of different periods in video to be assessed is intercepted；
The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；
According to default clustering algorithm, each above-mentioned unit-segment to be polymerized is polymerize sequentially in time, obtains each mesh
Mark video sequence；
The set that each above-mentioned target video sequence is formed, is determined as the assessment collection of above-mentioned video to be assessed.
The communication bus 704 that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral
Component Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus 704 can be divided into address bus, data/address bus, control bus etc..For
Convenient for indicating, only indicated with a thick line in figure, it is not intended that an only bus or a type of bus.
Communication interface 702 is for the communication between above-mentioned electronic equipment and other equipment.
Memory 703 may include random access memory (Random Access Memory, RAM), also may include
Nonvolatile memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory
703 can also be that at least one is located remotely from the storage device of aforementioned processor 701.
Above-mentioned processor 701 can be general processor, including central processing unit (Central Processing
Unit, CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital
Signal Processing, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components.
In a kind of electronic equipment provided in an embodiment of the present invention, the view that video platform user is directed to video to be assessed is obtained
Frequency segment interception record；It intercepts and records according to video clip, calculate the interception time that constituent parts segment is intercepted in video to be assessed
Number；The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；It is calculated according to default cluster
Method polymerize each unit-segment to be polymerized sequentially in time, obtains each target video sequence；By each target video sequence
The set of formation is determined as the assessment collection of video to be assessed.The embodiment of the present invention based on the video clip that user intercepts obtain to
The method for assessing the assessment collection of video, does not need manually to mark the assessment collection that can determine that video to be assessed, compared to artificial
The mode of mark, saves the time, realizes and efficiently obtains the assessment collection of video.
Another aspect, the embodiment of the invention discloses a kind of computer readable storage medium, above-mentioned computer-readable storage
Dielectric memory contains computer program, when above-mentioned computer program is executed by processor, realizes the determination of above-mentioned video evaluations collection
Any above-mentioned method and step in method.
In a kind of computer readable storage medium provided in an embodiment of the present invention, video platform user is obtained for be evaluated
Estimate the video clip interception record of video；It intercepts and records according to video clip, calculate constituent parts segment in video to be assessed and cut
The interception number taken；The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；According to pre-
If clustering algorithm, each unit-segment to be polymerized is polymerize sequentially in time, obtains each target video sequence；By each target
The set that video sequence is formed, is determined as the assessment collection of video to be assessed.The piece of video that the embodiment of the present invention is intercepted based on user
The method that section obtains the assessment collection of video to be assessed, does not need manually to mark the assessment collection that can determine that video to be assessed, phase
Compared with the mode manually marked, the time is saved, realizes and efficiently obtains the assessment collection of video.
The embodiment of the invention also provides a kind of computer program products comprising instruction, when it runs on computers
When, realize any above-mentioned method and step in the determination method of above-mentioned video evaluations collection.
In a kind of computer program product comprising instruction provided in an embodiment of the present invention, video platform user needle is obtained
Record is intercepted to the video clip of video to be assessed；It intercepts and records according to video clip, calculate constituent parts piece in video to be assessed
The interception number that section is intercepted；The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；
According to default clustering algorithm, each unit-segment to be polymerized is polymerize sequentially in time, obtains each target video sequence；It will
The set that each target video sequence is formed, is determined as the assessment collection of video to be assessed.The embodiment of the present invention is intercepted based on user
The method that video clip obtains the assessment collection of video to be assessed, does not need manually to mark the assessment that can determine that video to be assessed
Collection, compared to the mode manually marked, saves the time, realizes and efficiently obtains the assessment collection of video.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.Above-mentioned computer program
Product includes one or more computer instructions.When loading on computers and executing above-mentioned computer program instructions, all or
Partly generate the process or function above-mentioned according to the embodiment of the present invention.Above-mentioned computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.Above-mentioned computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, above-mentioned computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.Above-mentioned computer readable storage medium can be any usable medium that computer can access or
It is comprising data storage devices such as one or more usable mediums integrated server, data centers.Above-mentioned usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid State Disk (SSD)) etc..
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including above-mentioned element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device and
For electronic equipment embodiment, since it is substantially similar to the method embodiment, so be described relatively simple, related place referring to
The part of embodiment of the method illustrates.
It above are only presently preferred embodiments of the present invention above, be not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (11)
1. a kind of determination method of video evaluations collection, which is characterized in that the described method includes:
The video clip that video platform user is obtained for video to be assessed intercepts record, wherein the video clip interception note
Record includes initial time and the end time for being respectively intercepted video clip；
According to each initial time and end time for being intercepted video clip of video clip interception record, institute is calculated
State the interception number that the constituent parts segment of different periods in video to be assessed is intercepted；
The unit-segment that interception number is not less than preset threshold is chosen, each unit-segment to be polymerized is obtained；
According to default clustering algorithm, each unit-segment to be polymerized is polymerize sequentially in time, obtains each target view
Frequency sequence；
The set that each target video sequence is formed, is determined as the assessment collection of the video to be assessed.
2. the method according to claim 1, wherein the method also includes: the default unit time is obtained, with institute
Stating the unit time is dividing unit, and the video logic to be assessed is divided into multiple unit-segments.
3. the method according to claim 1, wherein described according to each described of video clip interception record
It is intercepted initial time and the end time of video clip, calculates the constituent parts segment quilt of different periods in the video to be assessed
The interception number of interception, comprising:
For it is each it is described be intercepted video clip, determining that this is intercepted in the initial time and end time of video clip includes
Constituent parts segment；
For each unit-segment, add up the interception number that the unit-segment is intercepted video.
4. the method according to claim 1, wherein in the list chosen interception number and be not less than preset threshold
Bit slice section, before obtaining each unit-segment to be polymerized, the method also includes:
The mean value that constituent parts segment is intercepted the interception number of video is calculated, using the mean value as the preset threshold.
5. the method according to claim 1, wherein described according to default clustering algorithm, to each described to be polymerized
Unit-segment is polymerize sequentially in time, obtains each target video sequence, comprising:
Sequentially in time, it sorts to each unit-segment to be polymerized；
According to the core radius and density of default DBSCAN algorithm, each unit-segment to be polymerized after determining sequence is formed
Each target video sequence.
6. a kind of determining device of video evaluations collection, which is characterized in that described device includes:
Video clip interception record obtains module, intercepts for obtaining video platform user for the video clip of video to be assessed
Record, wherein the video clip interception record includes initial time and the end time for being respectively intercepted video clip；
Unit-segment intercepts number determining module, for described being intercepted piece of video according to each of video clip interception record
The initial time of section and end time calculate the interception time that the constituent parts segment of different periods in the video to be assessed is intercepted
Number；
Unit-segment determining module to be polymerized, for choose interception number be not less than preset threshold unit-segment, obtain respectively to
Polymeric unit segment；
Target video sequence determining module is used for according to default clustering algorithm, to each unit-segment to be polymerized according to the time
Sequence is polymerize, and each target video sequence is obtained；
Video evaluations collection determining module to be assessed, the set for forming each target video sequence, be determined as it is described to
Assess the assessment collection of video.
7. device according to claim 6, which is characterized in that described device further include:
Unit-segment determining module is specifically used for obtaining the default unit time, will be described using the unit time as dividing unit
Video logic to be assessed is divided into multiple unit-segments.
8. device according to claim 6, which is characterized in that the unit-segment intercepts number determining module, comprising:
Unit-segment determines submodule, for for it is each it is described be intercepted video clip, determine that this is intercepted rising for video clip
The constituent parts segment for including in time beginning and end time；
Unit-segment interception number determines submodule, for being directed to each unit-segment, adds up the unit-segment and is intercepted view
The interception number of frequency.
9. device according to claim 6, which is characterized in that described device further include:
Preset threshold determining module, the mean value for being intercepted the interception number of video for calculating constituent parts segment, by the mean value
As the preset threshold.
10. device according to claim 6, which is characterized in that the target video sequence determining module, comprising:
Unit-segment sorting sub-module to be polymerized, for sequentially in time, sorting to each unit-segment to be polymerized；
Target video sequence determines submodule, for the core radius and density according to default DBSCAN algorithm, determines sequence
Each target video sequence that each unit-segment to be polymerized afterwards is formed.
11. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein processing
Device, communication interface, memory complete mutual communication by communication bus；
Memory, for storing computer program；
Processor when for executing the program stored on memory, realizes any method and step of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603478.8A CN109672936B (en) | 2018-12-26 | 2018-12-26 | Method and device for determining video evaluation set and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603478.8A CN109672936B (en) | 2018-12-26 | 2018-12-26 | Method and device for determining video evaluation set and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109672936A true CN109672936A (en) | 2019-04-23 |
| CN109672936B CN109672936B (en) | 2021-10-26 |
Family
ID=66146781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811603478.8A Active CN109672936B (en) | 2018-12-26 | 2018-12-26 | Method and device for determining video evaluation set and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109672936B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110099308A (en) * | 2019-05-15 | 2019-08-06 | 浙江传媒学院 | A kind of audio/video program temperature section Fast Segmentation and extracting method |
| CN110139158A (en) * | 2019-06-21 | 2019-08-16 | 上海摩象网络科技有限公司 | The generation method of video and sub-video, device, electronic equipment |
| CN110381391A (en) * | 2019-07-11 | 2019-10-25 | 北京字节跳动网络技术有限公司 | Video rapid section method, apparatus and electronic equipment |
| WO2021212659A1 (en) * | 2020-04-24 | 2021-10-28 | 平安国际智慧城市科技股份有限公司 | Video data processing method and apparatus, and computer device and storage medium |
| CN114040250A (en) * | 2022-01-10 | 2022-02-11 | 深圳市麦谷科技有限公司 | Video frame capturing method and device, electronic equipment and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345853A (en) * | 2008-08-07 | 2009-01-14 | 深圳市迅雷网络技术有限公司 | Method and system for acquiring video resource cutting time point |
| JP2012039284A (en) * | 2010-08-05 | 2012-02-23 | Mitsubishi Electric Corp | Moving image compression apparatus, moving image distribution system, moving image compression program, recording medium, and moving image compression method |
| CN104284216A (en) * | 2014-10-23 | 2015-01-14 | Tcl集团股份有限公司 | Method and system for generating video highlight clip |
| CN104410920A (en) * | 2014-12-31 | 2015-03-11 | 合一网络技术(北京)有限公司 | Video segment playback amount-based method for labeling highlights |
| CN105191337A (en) * | 2013-03-05 | 2015-12-23 | 英国电讯有限公司 | Provision of video data |
| CN106170104A (en) * | 2016-07-01 | 2016-11-30 | 广州华多网络科技有限公司 | Determination method, device and the server of video highlight fragment |
| CN106503029A (en) * | 2015-09-08 | 2017-03-15 | 纳宝株式会社 | Extract and provide the method for excellent image, system and recording medium in video content |
| US20180013983A1 (en) * | 2009-11-30 | 2018-01-11 | International Business Machines Corporation | Identifying popular network video segments |
| CN108307230A (en) * | 2018-02-07 | 2018-07-20 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of video highlight segment |
| CN108830212A (en) * | 2018-06-12 | 2018-11-16 | 北京大学深圳研究生院 | A kind of video behavior time shaft detection method |
| CN108924576A (en) * | 2018-07-10 | 2018-11-30 | 武汉斗鱼网络科技有限公司 | A kind of video labeling method, device, equipment and medium |
-
2018
- 2018-12-26 CN CN201811603478.8A patent/CN109672936B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345853A (en) * | 2008-08-07 | 2009-01-14 | 深圳市迅雷网络技术有限公司 | Method and system for acquiring video resource cutting time point |
| US20180013983A1 (en) * | 2009-11-30 | 2018-01-11 | International Business Machines Corporation | Identifying popular network video segments |
| JP2012039284A (en) * | 2010-08-05 | 2012-02-23 | Mitsubishi Electric Corp | Moving image compression apparatus, moving image distribution system, moving image compression program, recording medium, and moving image compression method |
| CN105191337A (en) * | 2013-03-05 | 2015-12-23 | 英国电讯有限公司 | Provision of video data |
| CN104284216A (en) * | 2014-10-23 | 2015-01-14 | Tcl集团股份有限公司 | Method and system for generating video highlight clip |
| CN104410920A (en) * | 2014-12-31 | 2015-03-11 | 合一网络技术(北京)有限公司 | Video segment playback amount-based method for labeling highlights |
| CN106503029A (en) * | 2015-09-08 | 2017-03-15 | 纳宝株式会社 | Extract and provide the method for excellent image, system and recording medium in video content |
| CN106170104A (en) * | 2016-07-01 | 2016-11-30 | 广州华多网络科技有限公司 | Determination method, device and the server of video highlight fragment |
| CN108307230A (en) * | 2018-02-07 | 2018-07-20 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of video highlight segment |
| CN108830212A (en) * | 2018-06-12 | 2018-11-16 | 北京大学深圳研究生院 | A kind of video behavior time shaft detection method |
| CN108924576A (en) * | 2018-07-10 | 2018-11-30 | 武汉斗鱼网络科技有限公司 | A kind of video labeling method, device, equipment and medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110099308A (en) * | 2019-05-15 | 2019-08-06 | 浙江传媒学院 | A kind of audio/video program temperature section Fast Segmentation and extracting method |
| CN110099308B (en) * | 2019-05-15 | 2022-06-10 | 浙江传媒学院 | Method for quickly segmenting and extracting hot interval of audio/video program |
| CN110139158A (en) * | 2019-06-21 | 2019-08-16 | 上海摩象网络科技有限公司 | The generation method of video and sub-video, device, electronic equipment |
| CN110139158B (en) * | 2019-06-21 | 2021-04-02 | 上海摩象网络科技有限公司 | Video and sub-video generation method and device, and electronic equipment |
| CN110381391A (en) * | 2019-07-11 | 2019-10-25 | 北京字节跳动网络技术有限公司 | Video rapid section method, apparatus and electronic equipment |
| CN110381391B (en) * | 2019-07-11 | 2021-11-09 | 北京字节跳动网络技术有限公司 | Video fast slicing method and device and electronic equipment |
| WO2021212659A1 (en) * | 2020-04-24 | 2021-10-28 | 平安国际智慧城市科技股份有限公司 | Video data processing method and apparatus, and computer device and storage medium |
| CN114040250A (en) * | 2022-01-10 | 2022-02-11 | 深圳市麦谷科技有限公司 | Video frame capturing method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109672936B (en) | 2021-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109672936A (en) | A kind of the determination method, apparatus and electronic equipment of video evaluations collection | |
| CN103458456B (en) | User behavior detection methods based on mobile terminal Wi-Fi data and device | |
| JP6479999B2 (en) | News list update method and apparatus | |
| CN106022505A (en) | Method and device of predicting user off-grid | |
| CN109685144B (en) | Method and device for evaluating video model and electronic equipment | |
| WO2017113677A1 (en) | User behavior data processing method and system | |
| US20150371163A1 (en) | Churn prediction in a broadband network | |
| CN109947812A (en) | Consecutive miss value fill method, data analysis set-up, terminal and storage medium | |
| CN109756352B (en) | Method and device for determining network quality and storage medium | |
| CN109495291B (en) | Calling abnormity positioning method and device and server | |
| CN103402142A (en) | Program list pushing method and device | |
| US20160132798A1 (en) | Service-level agreement analysis | |
| CN108520440B (en) | Method for determining total consumption stock demand of reading user, electronic equipment and computer storage medium | |
| WO2014206131A1 (en) | Method and apparatus for report generation | |
| CN109508405B (en) | Method and device for determining recommended video, electronic equipment and storage medium | |
| US20170245010A1 (en) | Video playing detection method and apparatus | |
| CN107678932A (en) | Application performance analysis method and device | |
| CN105429792B (en) | User behavior flow acquisition methods and device, user behavior analysis method and system | |
| WO2017156994A1 (en) | Multimedia resource quality assessment method and apparatus | |
| CN110909005B (en) | Model feature analysis method, device, equipment and medium | |
| CN111858245A (en) | Abnormal data analysis method and device, electronic equipment and storage medium | |
| CN110222790A (en) | Method for identifying ID, device and server | |
| CN105162643B (en) | The method, apparatus and computing device that flow is estimated | |
| CN110059083A (en) | A kind of data evaluation method, apparatus and electronic equipment | |
| CN113673822A (en) | Elastic scheduling method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |