CN109587578A - The processing method and processing device of video clip - Google Patents
The processing method and processing device of video clip Download PDFInfo
- Publication number
- CN109587578A CN109587578A CN201811573325.3A CN201811573325A CN109587578A CN 109587578 A CN109587578 A CN 109587578A CN 201811573325 A CN201811573325 A CN 201811573325A CN 109587578 A CN109587578 A CN 109587578A
- Authority
- CN
- China
- Prior art keywords
- video
- target
- time section
- target time
- period
- 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]
- H04N21/80—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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference 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]
- H04N21/80—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
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
-
- 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
Abstract
The embodiment of the present application discloses a kind of processing method and processing device of video clip, to realize the purpose for automatically generating video clip and labelling for video clip.The described method includes: determining at least one target time section to be extracted in target video according to the corresponding comment information of each period of target video；The corresponding video clip of each target time section is intercepted from target video；And obtain corresponding first comment information of each target time section；The first comment information corresponding to each target time section is analyzed, to analyze the corresponding video tab of each target time section；The corresponding video clip of each target time section and video tab are associated, to generate the video clip for carrying video tab.The technical solution can automatically generate video clip and label for video clip, and improve the accuracy and efficiency of video clip generated and video tab.
Description
Technical field
The present invention relates to technical field of video processing more particularly to a kind of processing method and processing devices of video clip.
Background technique
In traditional video website, video clip and corresponding video clip label generally carry out people by operation personnel
Work screening, labels at editing.That is, operation personnel needs first when needing to generate short-sighted frequency and corresponding label according to long video
Long video sight is read through, then finds out wherein excellent segment, and carry out artificial editing and manually add label.
Obviously, increasing with number of videos can become more and more numerous by manually carrying out editing and adding tagged work
Weight, and since video tab belongs to artificial addition, cause the video tab generated inevitably to have the subjective colo(u)r of operation personnel.Cause
This, the video tab serious forgiveness that this mode generates is lower, and the label liked with masses inevitably disagrees.
Therefore, a kind of mode for automating, efficiently, accurately generating video clip and corresponding label is needed.
Summary of the invention
The purpose of the embodiment of the present application is to provide a kind of processing method and processing device of video clip, to realize automatically
The purpose for generating video clip and labelling for video clip.
In order to solve the above technical problems, the embodiment of the present application is achieved in that
On the one hand, the embodiment of the present application provides a kind of processing method of video clip, comprising:
According to the corresponding comment information of each period of target video, determine to be extracted at least one in the target video
A target time section；
The corresponding video clip of each target time section is intercepted from the target video；And it obtains each described
Corresponding first comment information of target time section；
Corresponding first comment information of each target time section is analyzed, when analyzing each target
Between the corresponding video tab of section；
Each corresponding video clip of target time section and the video tab are associated, to generate
Carry the video clip of the video tab.
In one embodiment, the comment information includes number of reviews；
The corresponding comment information of each period according to target video, determine in the target video it is to be extracted extremely
A few target time section, comprising:
Count the corresponding number of reviews of each period of the target video；
According to the statistical result of the number of reviews, determines and meet described in the specified quantity period conduct of preset condition
Target time section；
Wherein, the preset condition includes at least one of the following: that the number of reviews is most, the number of reviews reaches pre-
If threshold value.
In one embodiment, the statistical result according to the number of reviews determines and meets the specified of preset condition
The quantity period is as the target time section, comprising:
Using each period as horizontal axis, using each period corresponding number of reviews as the longitudinal axis, generate and institute
State the relevant curve graph of number of reviews；
The specified quantity is filtered out from the curve graph meets the period of the preset condition as the mesh
Mark the period.
In one embodiment, the comment information includes comment content；
It is described that corresponding first comment information of each target time section is analyzed, to analyze each mesh
Mark period corresponding video tab, comprising:
The multiple comment contents for meeting and presetting high similarity condition are filtered out from first comment information；Wherein, institute
Stating and presetting high similarity condition includes that similarity reaches default similarity；
Semantic analysis is carried out to the multiple comment content, is commented with obtaining the corresponding synthesis of the multiple comment content
By content；
The corresponding video tab of each target time section is determined according to each comprehensive survey content.
In one embodiment, described to determine that each target time section respectively corresponds according to each comprehensive survey content
Video tab, comprising:
In conjunction with each comprehensive survey content and the associated video information of the target video, each object time is obtained
The corresponding video tab of section；Wherein, the associated video information includes video name, at least one in Video Key word
?.
In one embodiment, the method also includes:
The video clip for carrying the video tab is pushed into client, so that described in the client terminal playing
When target video, the video clip for carrying the video tab is shown into the corresponding position in the target video.
In one embodiment, the method also includes:
The corresponding marked content of each target time section is determined according to each video tab；
Each marked content is added respectively when on the target video, corresponding with each target time section
Between on axis, so as to show the marked content on the time axis when target video described in the client terminal playing.
On the other hand, the embodiment of the present application provides a kind of processing unit of video clip, comprising:
First determining module determines the target view for the corresponding comment information of each period according to target video
At least one target time section to be extracted in frequency；
Module is obtained, for intercepting the corresponding video clip of each target time section from the target video；
And obtain corresponding first comment information of each target time section；
Analysis module, for analyzing corresponding first comment information of each target time section, with analysis
The corresponding video tab of each target time section out；
Generation module, for by each corresponding video clip of target time section and the video tab into
Row association, to generate the video clip for carrying the video tab.
In one embodiment, the comment information includes number of reviews；
First determining module includes:
Statistic unit, for counting the corresponding number of reviews of each period of the target video；
First determination unit determines the specified number for meeting preset condition for the statistical result according to the number of reviews
A period is measured as the target time section；
Wherein, the preset condition includes at least one of the following: that the number of reviews is most, the number of reviews reaches pre-
If threshold value.
In one embodiment, the determination unit is also used to:
Using each period as horizontal axis, using each period corresponding number of reviews as the longitudinal axis, generate and institute
State the relevant curve graph of number of reviews；
The specified quantity is filtered out from the curve graph meets the period of the preset condition as the mesh
Mark the period.
In one embodiment, the comment information includes comment content；
The analysis module includes:
Screening unit meets the multiple comments for presetting high similarity condition for filtering out from first comment information
Content；It is wherein, described that preset high similarity condition include that similarity reaches default similarity；
Analytical unit, for carrying out semantic analysis to the multiple comment content, to obtain the multiple comment content pair
The comprehensive survey content answered；
Second determination unit, for determining that each target time section is corresponding according to each comprehensive survey content
Video tab.
In one embodiment, second determination unit is also used to:
In conjunction with each comprehensive survey content and the associated video information of the target video, each object time is obtained
The corresponding video tab of section；Wherein, the associated video information includes video name, at least one in Video Key word
?.
In one embodiment, described device further include:
Pushing module, for the video clip for carrying the video tab to be pushed to client, so that described
Described in client terminal playing when target video, the video clip for carrying the video tab is shown in the target video
Corresponding position.
In one embodiment, described device further include:
Second determining module, for being determined in the corresponding mark of each target time section according to each video tab
Hold；
Adding module, for each marked content to be added on the target video and each target respectively
On period corresponding time shaft, so that when target video described in the client terminal playing, on the time axis described in display
Marked content.
In another aspect, the embodiment of the present application provides a kind of processing equipment of video clip, comprising:
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage device:
According to the corresponding comment information of each period of target video, determine to be extracted at least one in the target video
A target time section；
The corresponding video clip of each target time section is intercepted from the target video；And it obtains each described
Corresponding first comment information of target time section；
Corresponding first comment information of each target time section is analyzed, when analyzing each target
Between the corresponding video tab of section；
Each corresponding video clip of target time section and the video tab are associated, to generate
Carry the video clip of the video tab.
In another aspect, the embodiment of the present application provides a kind of storage medium, for storing computer executable instructions, it is described can
It executes instruction and realizes following below scheme when executed:
According to the corresponding comment information of each period of target video, determine to be extracted at least one in the target video
A target time section；
The corresponding video clip of each target time section is intercepted from the target video；And it obtains each described
Corresponding first comment information of target time section；
Corresponding first comment information of each target time section is analyzed, when analyzing each target
Between the corresponding video tab of section；
Each corresponding video clip of target time section and the video tab are associated, to generate
Carry the video clip of the video tab.
It, can be true according to the corresponding comment information of each period of target video using the technical solution of the embodiment of the present invention
At least one target time section to be extracted in the fixed target video, and then each target time section point is intercepted from target video
Not corresponding video clip, and corresponding first comment information of each target time section is obtained, and pass through the first comment of analysis
Information obtains the corresponding video tab of each target time section, finally by the corresponding video clip of each target time section and
Video tab is associated, to generate the video clip for carrying video tab.As it can be seen that the technical solution can automatically give birth to
Label at video clip and for video clip, compared to the prior art in label using artificial interception video and manually
For mode, which saves a large amount of manpower, and it is too strong to avoid the caused label subjectivity that manually labels
Problem improves the accuracy and efficiency of video clip generated and video tab.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, in the premise of not making the creative labor property
Under, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of schematic flow chart of the processing method of video clip according to an embodiment of the invention；
Fig. 2 is the schematic graph of number of reviews in a kind of processing method of video clip according to an embodiment of the invention
Figure.
Fig. 3 is a kind of schematic block diagram of the processing unit of video clip according to an embodiment of the invention；
Fig. 4 is a kind of schematic block diagram of the processing equipment of video clip according to an embodiment of the invention.
Specific embodiment
The embodiment of the present application provides a kind of processing method and processing device of video clip, automatically generates video to realize
Segment and the purpose to label for video clip.
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality
The attached drawing in example is applied, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described implementation
Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common
The application protection all should belong in technical staff's every other embodiment obtained without creative efforts
Range.
Fig. 1 is a kind of schematic flow chart of the processing method of video clip according to an embodiment of the invention, such as Fig. 1 institute
Show, this method comprises:
S102, according to the corresponding comment information of each period of target video, determine in target video it is to be extracted at least
One target time section.
S104 intercepts the corresponding video clip of each target time section from target video；And obtain each object time
Corresponding first comment information of section.
S106, the first comment information corresponding to each target time section is analyzed, to analyze each object time
The corresponding video tab of section.
The corresponding video clip of each target time section and video tab are associated by S108, are carried with generating
The video clip of video tab.
In the present embodiment, each period of target video can be the unit interval divided in advance, and such as every 1 minute, every
10 seconds, every 30 seconds etc..To keep the video clip intercepted automatically more accurate, unit interval can be divided into the time as small as possible
Section.
Assuming that the unit interval divided in advance is 1 minute, then the step is executable are as follows: according to every 1 point of target video
Clock corresponding comment information determines target time section to be extracted in target video.When target time section can be unit
Between section, be also possible to the time set of multiple unit intervals, such as target time section is the 10th minute or is the 10th to 15
The time set of minute.
Comment information can be the barrage information in target video；It is also possible in the embedded comment region on video web-pages
Comment information；It can also be the comment information, such as the comment information on each World Jam etc. commented on platform with third party.
It, can be true according to the corresponding comment information of each period of target video using the technical solution of the embodiment of the present invention
At least one target time section to be extracted in the fixed target video, and then each target time section point is intercepted from target video
Not corresponding video clip, and corresponding first comment information of each target time section is obtained, and pass through the first comment of analysis
Information obtains the corresponding video tab of each target time section, finally by the corresponding video clip of each target time section and
Video tab is associated, to generate the video clip for carrying video tab.As it can be seen that the technical solution can automatically give birth to
Label at video clip and for video clip, compared to the prior art in label using artificial interception video and manually
For mode, which saves a large amount of manpower, and it is too strong to avoid the caused label subjectivity that manually labels
Problem improves the accuracy and efficiency of video clip generated and video tab.
The processing method of video clip provided by the above embodiment described in detail below.
In one embodiment, comment information includes number of reviews.Therefore, corresponding according to each period of target video
Comment information when determining at least one target time section to be extracted in target video, can first count each time of target video
The corresponding number of reviews of section, and then according to the statistical result of number of reviews, determine the specified quantity time for meeting preset condition
Duan Zuowei target time section.Wherein, preset condition include at least one of the following: number of reviews at most, number of reviews reach default
Threshold value.
It, can be by drawing corresponding number of reviews of each period and the curve relation figure between each period in the present embodiment
To screen target time section.Specifically, using each period as horizontal axis, using corresponding number of reviews of each period as the longitudinal axis,
Curve graph relevant to number of reviews is generated, and then determines that specified quantity meets preset condition from curve graph generated
Period as target time section.
Fig. 2 shows period each in an embodiment corresponding number of reviews and the curve graphs between each period.Such as Fig. 2
Shown, horizontal axis is each period of target video, and each period is every 1 minute in target video；The longitudinal axis is each period
Corresponding number of reviews.Assuming that need to determine in the present embodiment 3 most periods of number of reviews as target time section,
So as seen from Figure 2,3 most periods of number of reviews are respectively 3 minutes, 9 minutes and 12 minutes corresponding periods.
Accordingly, it can be determined that 3 minutes, 9 minutes and 12 minutes corresponding periods are as target time section.
In one embodiment, comment information includes comment content.It is commented to each target time section corresponding first
It is analyzed by information, it, can be first from each first comment information when analyzing the corresponding video tab of each target time section
In filter out to meet and preset multiple comment contents of high similarity condition, and then to the progress semantic analysis of multiple comment content,
To obtain the corresponding comprehensive survey content of multiple comment contents, each target time section point is then determined according to each comprehensive survey content
Not corresponding video tab.Wherein, presetting high similarity condition includes that similarity reaches default similarity.
For example, for corresponding first comment information of a target time section, commenting on content packet in film " Thunder God 3 "
Include following: " hammer is broken ", " my god！Hammer is broken ", " hammer is crumbed ", " jumping off on Ban Nacong flying saucer " etc..Pass through
Analyze these comment contents between similarity, it can be seen that " hammer is broken ", " my god！Hammer is broken " and " hammer is crumbed
" between similarity it is higher, reached default similarity, and " jumping off on Ban Nacong flying saucer " and other several comment contents
Between similarity it is lower, not up to default similarity, then can filter out, " hammer is broken ", " my god！Hammer is broken " and " hammer
Son is crumbed " these comment contents, and these comment contents filtered out are analyzed, to analyze comprehensive survey
Content, if comprehensive survey content is " hammer is broken ".
In the present embodiment, multiple comment contents of high similarity condition are preset by screening to meet, may make and filter out
Content is commented on more close to the video content of corresponding video clip, thus the accuracy of video tab determined by improving.
It, can when determining the corresponding video tab of each target time section according to each comprehensive survey content in the present embodiment
In conjunction with each comprehensive survey content and the associated video information of target video, the corresponding video mark of each target time section is obtained
Label；Wherein, associated video information include video name, in Video Key word at least one of.
For example, the corresponding comprehensive survey content of target time section is " hammer is broken ", then by by comprehensive survey content
Combine with video name, can obtain the corresponding video tab of the target time section is " Thunder God 3: hammer is broken ".
In one embodiment, the video clip for carrying video tab can be pushed to client, so that client is broadcast
When putting target video, the video clip for carrying video tab is shown into the corresponding position in target video.Wherein, corresponding position
It can be any position on the current page for playing target video, such as lower position in the broadcasting pictures of target video or the right side
Side position shows each video clip and its corresponding video tab with tabular form.
In one embodiment, the corresponding marked content of each target time section can be determined according to each video tab, and will be each
Marked content is added respectively on time shaft on target video, corresponding with each target time section, so that client terminal playing mesh
When marking video, marked content is shown on a timeline.Wherein, marked content can be in the corresponding comprehensive survey of video tab
Hold, is also possible to video tab itself, can also be the keyword etc. extracted in video tab.For example, video tab is " Thunder God
3: hammer is broken ", then marked content corresponding to the corresponding target time section of the video tab can be " hammer is broken ", therefore
Upper marked content " hammer is broken " can be added in position corresponding with target time section on the time shaft of target video, to use
When watching target video, capable of knowing each target time section from time shaft at a glance, (i.e. number of reviews is most at family
Each period) key content.
To sum up, the specific embodiment of this theme is described.Other embodiments are in the appended claims
In range.In some cases, the movement recorded in detail in the claims can execute and still in a different order
Desired result may be implemented.In addition, process depicted in the drawing not necessarily requires the particular order shown or continuous suitable
Sequence, to realize desired result.In some embodiments, multitasking and parallel processing can be advantageous.
The above are the processing methods of video clip provided by the embodiments of the present application, are based on same thinking, and the application is implemented
Example also provides a kind of processing unit of video clip.
Fig. 3 is a kind of schematic block diagram of the processing unit of video clip according to an embodiment of the invention, such as Fig. 3 institute
Show, the processing unit 300 of video clip includes:
First determining module 310 determines target video for the corresponding comment information of each period according to target video
In at least one target time section to be extracted；
Module 320 is obtained, for intercepting the corresponding video clip of each target time section from target video；And it obtains
Take corresponding first comment information of each target time section；
Analysis module 330, for analyzing corresponding first comment information of each target time section, to analyze
The corresponding video tab of each target time section；
Generation module 340, for the corresponding video clip of each target time section and video tab to be associated, with
Generate the video clip for carrying video tab.
In one embodiment, comment information includes number of reviews；
First determining module 310 includes:
Statistic unit, for counting the corresponding number of reviews of each period of target video；
First determination unit determines the specified quantity for meeting preset condition for the statistical result according to number of reviews
Period is as target time section；
Wherein, preset condition include at least one of the following: number of reviews at most, number of reviews reach preset threshold.
In one embodiment, determination unit is also used to:
Using each period as horizontal axis, using corresponding number of reviews of each period as the longitudinal axis, generate and number of reviews phase
The curve graph of pass；
Specified quantity is filtered out from curve graph meets the period of preset condition as target time section.
In one embodiment, comment information includes comment content；
Analysis module 330 includes:
Screening unit, for from filtered out in the first comment information meet preset high similarity condition multiple comments in
Hold；Wherein, presetting high similarity condition includes that similarity reaches default similarity；
Analytical unit, for carrying out semantic analysis to multiple comment contents, to obtain the corresponding synthesis of multiple comment contents
Comment on content；
Second determination unit, for determining the corresponding video mark of each target time section according to each comprehensive survey content
Label.
In one embodiment, the second determination unit is also used to:
In conjunction with each comprehensive survey content and the associated video information of target video, it is corresponding to obtain each target time section
Video tab；Wherein, associated video information include video name, in Video Key word at least one of.
In one embodiment, device 300 further include:
Pushing module, for the video clip for carrying video tab to be pushed to client, so that client terminal playing mesh
When marking video, the video clip for carrying video tab is shown into the corresponding position in target video.
In one embodiment, device 300 further include:
Second determining module, for determining the corresponding marked content of each target time section according to each video tab；
Adding module, it is on target video, corresponding with each target time section for adding respectively each marked content
On time shaft, so as to show marked content on a timeline when client terminal playing target video.
Using the device of the embodiment of the present invention, institute can be determined according to the corresponding comment information of each period of target video
At least one target time section to be extracted in target video is stated, and then it is right respectively to intercept from target video each target time section
The video clip answered, and corresponding first comment information of each target time section is obtained, and pass through the first comment information of analysis
The corresponding video tab of each target time section is obtained, finally by the corresponding video clip of each target time section and video
Label is associated, to generate the video clip for carrying video tab.As it can be seen that the technical solution can automatically generate view
Frequency segment and label for video clip, compared to the prior art in using manually intercepting video and manually labelling by the way of
For, which saves a large amount of manpower, and avoids the too strong problem of caused label subjectivity that manually labels,
Improve the accuracy and efficiency of video clip generated and video tab.
It should be understood that the processing unit of above-mentioned video clip can be previously described for realizing
The processing method of video clip, datail description therein should be described with method part above it is similar, it is cumbersome to avoid, it is not another herein
It repeats.
Based on same thinking, the embodiment of the present application also provides a kind of processing equipment of video clip, as shown in Figure 4.Depending on
The processing equipment of frequency segment can generate bigger difference because configuration or performance are different, may include one or more
Processor 401 and memory 402 can store one or more storage application programs or data in memory 402.Its
In, memory 402 can be of short duration storage or persistent storage.Be stored in memory 402 application program may include one or
More than one module (diagram is not shown), each module may include the series of computation machine in the processing equipment to video clip
Executable instruction.Further, processor 401 can be set to communicate with memory 402, in the processing equipment of video clip
The upper series of computation machine executable instruction executed in memory 402.The processing equipment of video clip can also include one or
More than one power supply 403, one or more wired or wireless network interfaces 404, one or more input and output connect
Mouth 405, one or more keyboards 406.
Specifically in the present embodiment, the processing equipment of video clip includes memory and one or more
Program, perhaps more than one program is stored in memory and one or more than one program may include one for one of them
A or more than one module, and each module may include that series of computation machine in processing equipment to video clip is executable
Instruction, and be configured to execute this or more than one program by one or more than one processor to include for carrying out
Following computer executable instructions:
According to the corresponding comment information of each period of target video, determine to be extracted at least one in the target video
A target time section；
The corresponding video clip of each target time section is intercepted from the target video；And it obtains each described
Corresponding first comment information of target time section；
Corresponding first comment information of each target time section is analyzed, when analyzing each target
Between the corresponding video tab of section；
Each corresponding video clip of target time section and the video tab are associated, to generate
Carry the video clip of the video tab.
Optionally, the comment information includes number of reviews；
Computer executable instructions when executed, can also make the processor:
Count the corresponding number of reviews of each period of the target video；
According to the statistical result of the number of reviews, determines and meet described in the specified quantity period conduct of preset condition
Target time section；
Wherein, the preset condition includes at least one of the following: that the number of reviews is most, the number of reviews reaches pre-
If threshold value.
Optionally, computer executable instructions when executed, can also make the processor:
Using each period as horizontal axis, using each period corresponding number of reviews as the longitudinal axis, generate and institute
State the relevant curve graph of number of reviews；
The specified quantity is filtered out from the curve graph meets the period of the preset condition as the mesh
Mark the period.
Optionally, the comment information includes comment content；
Computer executable instructions when executed, can also make the processor:
The multiple comment contents for meeting and presetting high similarity condition are filtered out from first comment information；Wherein, institute
Stating and presetting high similarity condition includes that similarity reaches default similarity；
Semantic analysis is carried out to the multiple comment content, is commented with obtaining the corresponding synthesis of the multiple comment content
By content；
The corresponding video tab of each target time section is determined according to each comprehensive survey content.
Optionally, computer executable instructions when executed, can also make the processor:
In conjunction with each comprehensive survey content and the associated video information of the target video, each object time is obtained
The corresponding video tab of section；Wherein, the associated video information includes video name, at least one in Video Key word
?.
Optionally, computer executable instructions when executed, can also make the processor:
The video clip for carrying the video tab is pushed into client, so that described in the client terminal playing
When target video, the video clip for carrying the video tab is shown into the corresponding position in the target video.
Optionally, computer executable instructions when executed, can also make the processor:
The corresponding marked content of each target time section is determined according to each video tab；
Each marked content is added respectively when on the target video, corresponding with each target time section
Between on axis, so as to show the marked content on the time axis when target video described in the client terminal playing.
The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one
A or multiple programs, the one or more program include instruction, which holds when by the electronic equipment including multiple application programs
When row, the electronic equipment can be made to execute the processing method of above-mentioned video clip, and be specifically used for executing:
According to the corresponding comment information of each period of target video, determine to be extracted at least one in the target video
A target time section；
The corresponding video clip of each target time section is intercepted from the target video；And it obtains each described
Corresponding first comment information of target time section；
Corresponding first comment information of each target time section is analyzed, when analyzing each target
Between the corresponding video tab of section；
Each corresponding video clip of target time section and the video tab are associated, to generate
Carry the video clip of the video tab.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
All the embodiments in this specification are described in a progressive manner, 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 system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (14)
1. a kind of processing method of video clip, which is characterized in that the described method includes:
According to the corresponding comment information of each period of target video, at least one mesh to be extracted in the target video is determined
Mark the period；
The corresponding video clip of each target time section is intercepted from the target video；And obtain each target
Period corresponding first comment information；
Corresponding first comment information of each target time section is analyzed, to analyze each target time section
Corresponding video tab；
Each corresponding video clip of target time section and the video tab are associated, carried with generating
There is the video clip of the video tab.
2. the method according to claim 1, wherein the comment information includes number of reviews；
The corresponding comment information of each period according to target video determines to be extracted at least one in the target video
A target time section, comprising:
Count the corresponding number of reviews of each period of the target video；
According to the statistical result of the number of reviews, determine the specified quantity period for meeting preset condition as the target
Period；
Wherein, the preset condition includes at least one of the following: that the number of reviews is most, the number of reviews reaches default threshold
Value.
3. according to the method described in claim 2, it is characterized in that, the statistical result according to the number of reviews, determines
Meet the specified quantity period of preset condition as the target time section, comprising:
Using each period as horizontal axis, using each period corresponding number of reviews as the longitudinal axis, generate and institute's commentary
By the relevant curve graph of quantity；
When filtering out the specified quantity from the curve graph and meeting the period of the preset condition as the target
Between section.
4. the method according to claim 1, wherein the comment information includes comment content；
It is described that corresponding first comment information of each target time section is analyzed, when analyzing each target
Between the corresponding video tab of section, comprising:
The multiple comment contents for meeting and presetting high similarity condition are filtered out from first comment information；Wherein, described pre-
If high similarity condition includes that similarity reaches default similarity；
Semantic analysis is carried out to the multiple comment content, to obtain in the corresponding comprehensive survey of the multiple comment content
Hold；
The corresponding video tab of each target time section is determined according to each comprehensive survey content.
5. according to the method described in claim 4, it is characterized in that, it is described determined according to each comprehensive survey content it is each described
The corresponding video tab of target time section, comprising:
In conjunction with each comprehensive survey content and the associated video information of the target video, each target time section point is obtained
Not corresponding video tab；Wherein, the associated video information include video name, in Video Key word at least one of.
6. the method according to claim 1, wherein the method also includes:
The video clip for carrying the video tab is pushed into client, so that target described in the client terminal playing
When video, the video clip for carrying the video tab is shown into the corresponding position in the target video.
7. according to the method described in claim 6, it is characterized in that, the method also includes:
The corresponding marked content of each target time section is determined according to each video tab；
Each marked content is added into time shaft on the target video, corresponding with each target time section respectively
On, so as to show the marked content on the time axis when target video described in the client terminal playing.
8. a kind of processing unit of video clip, which is characterized in that described device includes:
First determining module determines in the target video for the corresponding comment information of each period according to target video
At least one target time section to be extracted；
Module is obtained, for intercepting the corresponding video clip of each target time section from the target video；And it obtains
Take corresponding first comment information of each target time section；
Analysis module, it is each to analyze for analyzing corresponding first comment information of each target time section
The corresponding video tab of the target time section；
Generation module, for closing each corresponding video clip of target time section and the video tab
Connection, to generate the video clip for carrying the video tab.
9. device according to claim 8, which is characterized in that the comment information includes number of reviews；
First determining module includes:
Statistic unit, for counting the corresponding number of reviews of each period of the target video；
First determination unit determines the specified quantity for meeting preset condition for the statistical result according to the number of reviews
Period is as the target time section；
Wherein, the preset condition includes at least one of the following: that the number of reviews is most, the number of reviews reaches default threshold
Value.
10. device according to claim 9, which is characterized in that the determination unit is also used to:
Using each period as horizontal axis, using each period corresponding number of reviews as the longitudinal axis, generate and institute's commentary
By the relevant curve graph of quantity；
When filtering out the specified quantity from the curve graph and meeting the period of the preset condition as the target
Between section.
11. device according to claim 8, which is characterized in that the comment information includes comment content；
The analysis module includes:
Screening unit, for from filtered out in first comment information meet preset high similarity condition multiple comments in
Hold；It is wherein, described that preset high similarity condition include that similarity reaches default similarity；
Analytical unit, it is corresponding to obtain the multiple comment content for carrying out semantic analysis to the multiple comment content
The comprehensive survey content；
Second determination unit, for determining the corresponding video of each target time section according to each comprehensive survey content
Label.
12. device according to claim 11, which is characterized in that second determination unit is also used to:
In conjunction with each comprehensive survey content and the associated video information of the target video, each target time section point is obtained
Not corresponding video tab；Wherein, the associated video information include video name, in Video Key word at least one of.
13. device according to claim 8, which is characterized in that described device further include:
Pushing module, for the video clip for carrying the video tab to be pushed to client, so that the client
When end plays the target video, the video clip for carrying the video tab is shown into pair in the target video
Answer position.
14. device according to claim 13, which is characterized in that described device further include:
Second determining module, for determining the corresponding marked content of each target time section according to each video tab；
Adding module, for each marked content to be added on the target video and each object time respectively
On the corresponding time shaft of section, so as to show the mark on the time axis when target video described in the client terminal playing
Content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811573325.3A CN109587578A (en) | 2018-12-21 | 2018-12-21 | The processing method and processing device of video clip |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811573325.3A CN109587578A (en) | 2018-12-21 | 2018-12-21 | The processing method and processing device of video clip |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109587578A true CN109587578A (en) | 2019-04-05 |
Family
ID=65930576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811573325.3A Pending CN109587578A (en) | 2018-12-21 | 2018-12-21 | The processing method and processing device of video clip |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109587578A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110856013A (en) * | 2019-11-19 | 2020-02-28 | 珠海格力电器股份有限公司 | Method, system and storage medium for identifying key segments in video |
| CN111010619A (en) * | 2019-12-05 | 2020-04-14 | 北京奇艺世纪科技有限公司 | Method, apparatus, computer device and storage medium for processing short video data |
| CN111490929A (en) * | 2020-03-27 | 2020-08-04 | 威比网络科技(上海)有限公司 | Video clip pushing method and device, electronic equipment and storage medium |
| CN111556326A (en) * | 2020-03-27 | 2020-08-18 | 威比网络科技(上海)有限公司 | Public class video clip pushing method and device, electronic equipment and storage medium |
| CN111581433A (en) * | 2020-05-18 | 2020-08-25 | Oppo广东移动通信有限公司 | Video processing method and device, electronic equipment and computer readable medium |
| WO2021160141A1 (en) * | 2020-02-11 | 2021-08-19 | 北京字节跳动网络技术有限公司 | Video processing method and apparatus, readable medium and electronic device |
| CN115022659A (en) * | 2022-05-31 | 2022-09-06 | 广州虎牙科技有限公司 | Live video processing method and system and live device |
| CN115767204A (en) * | 2022-11-10 | 2023-03-07 | 北京奇艺世纪科技有限公司 | Video processing method, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130311388A1 (en) * | 2011-06-10 | 2013-11-21 | Lucas J. Myslinski | Method of and system for fact checking flagged comments |
| CN104994425A (en) * | 2015-06-30 | 2015-10-21 | 北京奇艺世纪科技有限公司 | Video labeling method and device |
| US20160080295A1 (en) * | 2014-03-12 | 2016-03-17 | Stephen Davies | System and Method for Voice Networking |
| CN105787049A (en) * | 2016-02-26 | 2016-07-20 | 浙江大学 | Network video hotspot event finding method based on multi-source information fusion analysis |
| CN105847993A (en) * | 2016-04-19 | 2016-08-10 | 乐视控股（北京）有限公司 | Method and device for sharing video clip |
| CN106095804A (en) * | 2016-05-30 | 2016-11-09 | 维沃移动通信有限公司 | The processing method of a kind of video segment, localization method and terminal |
| CN107801106A (en) * | 2017-10-24 | 2018-03-13 | 维沃移动通信有限公司 | A kind of video segment intercept method and electronic equipment |
| CN108108353A (en) * | 2017-12-19 | 2018-06-01 | 北京邮电大学 | A kind of video semantic annotation method, apparatus and electronic equipment based on barrage |
-
2018
- 2018-12-21 CN CN201811573325.3A patent/CN109587578A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130311388A1 (en) * | 2011-06-10 | 2013-11-21 | Lucas J. Myslinski | Method of and system for fact checking flagged comments |
| US20160080295A1 (en) * | 2014-03-12 | 2016-03-17 | Stephen Davies | System and Method for Voice Networking |
| CN104994425A (en) * | 2015-06-30 | 2015-10-21 | 北京奇艺世纪科技有限公司 | Video labeling method and device |
| CN105787049A (en) * | 2016-02-26 | 2016-07-20 | 浙江大学 | Network video hotspot event finding method based on multi-source information fusion analysis |
| CN105847993A (en) * | 2016-04-19 | 2016-08-10 | 乐视控股（北京）有限公司 | Method and device for sharing video clip |
| CN106095804A (en) * | 2016-05-30 | 2016-11-09 | 维沃移动通信有限公司 | The processing method of a kind of video segment, localization method and terminal |
| CN107801106A (en) * | 2017-10-24 | 2018-03-13 | 维沃移动通信有限公司 | A kind of video segment intercept method and electronic equipment |
| CN108108353A (en) * | 2017-12-19 | 2018-06-01 | 北京邮电大学 | A kind of video semantic annotation method, apparatus and electronic equipment based on barrage |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110856013A (en) * | 2019-11-19 | 2020-02-28 | 珠海格力电器股份有限公司 | Method, system and storage medium for identifying key segments in video |
| CN111010619A (en) * | 2019-12-05 | 2020-04-14 | 北京奇艺世纪科技有限公司 | Method, apparatus, computer device and storage medium for processing short video data |
| WO2021160141A1 (en) * | 2020-02-11 | 2021-08-19 | 北京字节跳动网络技术有限公司 | Video processing method and apparatus, readable medium and electronic device |
| CN111490929A (en) * | 2020-03-27 | 2020-08-04 | 威比网络科技(上海)有限公司 | Video clip pushing method and device, electronic equipment and storage medium |
| CN111556326A (en) * | 2020-03-27 | 2020-08-18 | 威比网络科技(上海)有限公司 | Public class video clip pushing method and device, electronic equipment and storage medium |
| CN111490929B (en) * | 2020-03-27 | 2022-07-15 | 深圳市企鹅网络科技有限公司 | Video clip pushing method and device, electronic equipment and storage medium |
| CN111581433A (en) * | 2020-05-18 | 2020-08-25 | Oppo广东移动通信有限公司 | Video processing method and device, electronic equipment and computer readable medium |
| CN111581433B (en) * | 2020-05-18 | 2023-10-10 | Oppo广东移动通信有限公司 | Video processing method, device, electronic equipment and computer readable medium |
| CN115022659A (en) * | 2022-05-31 | 2022-09-06 | 广州虎牙科技有限公司 | Live video processing method and system and live device |
| CN115767204A (en) * | 2022-11-10 | 2023-03-07 | 北京奇艺世纪科技有限公司 | Video processing method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109587578A (en) | The processing method and processing device of video clip | |
| US9728230B2 (en) | Techniques to bias video thumbnail selection using frequently viewed segments | |
| US11190821B2 (en) | Methods and apparatus for alerting users to media events of interest using social media analysis | |
| US20200374306A1 (en) | Network traffic anomaly detection method, apparatus, computer device and storage medium | |
| CN111050205B (en) | Video clip acquisition method, device, equipment and storage medium | |
| US8577996B2 (en) | Method and apparatus for tracing users of online video web sites | |
| CN107493467B (en) | A kind of video quality evaluation method and device | |
| US20180014156A1 (en) | Content request by location | |
| CN110175291B (en) | Hand trip recommendation method, storage medium, equipment and system based on similarity calculation | |
| US8396874B2 (en) | System and method for using topic messages to understand media relating to an event | |
| US20090100456A1 (en) | Method and apparatus for monitoring online video | |
| CN105930363B (en) | HTML5 webpage-based user behavior analysis method and device | |
| CN109657138A (en) | A kind of video recommendation method, device, electronic equipment and storage medium | |
| CN109040796A (en) | The calculation method of contents fragment temperature, the playback method of video content and device | |
| CN105872837A (en) | User recommendation method and device | |
| CN104504084A (en) | Method and device for determining user retention rate | |
| CN106604050A (en) | Direct broadcast video assessment method and device | |
| CN104488277A (en) | Methods and apparatus to monitor media presentations | |
| CN104270654B (en) | Internet video plays monitoring method and device | |
| CN106021449A (en) | Searching method and device for mobile terminal and mobile terminal | |
| CN107578263A (en) | A kind of detection method, device and the electronic equipment of advertisement abnormal access | |
| CN105183925A (en) | Content association recommending method and content association recommending device | |
| KR20190101374A (en) | Network traffic preparation system for high speed analysis | |
| CN105260393A (en) | Information pushing method and device and electronic equipment | |
| CN111523920A (en) | Information pushing method and device and terminal equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190405 |