CN110324729A - A kind of method, apparatus, electronic equipment and the medium of identification infringement video link - Google Patents
A kind of method, apparatus, electronic equipment and the medium of identification infringement video link Download PDFInfo
- Publication number
- CN110324729A CN110324729A CN201910650865.5A CN201910650865A CN110324729A CN 110324729 A CN110324729 A CN 110324729A CN 201910650865 A CN201910650865 A CN 201910650865A CN 110324729 A CN110324729 A CN 110324729A
- Authority
- CN
- China
- Prior art keywords
- video
- infringement
- source
- potential
- potential infringement
- 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
- H04N21/432—Content retrieval operation from a local storage medium, e.g. hard-disk
-
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- 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
- H04N21/443—OS processes, e.g. booting an STB, implementing a Java virtual machine in an STB or power management in an STB
- H04N21/4431—OS processes, e.g. booting an STB, implementing a Java virtual machine in an STB or power management in an STB characterized by the use of Application Program Interface [API] libraries
-
- 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
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
-
- 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
- H04N21/835—Generation of protective data, e.g. certificates
-
- 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
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/858—Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot
Abstract
The embodiment of the present invention provides method, apparatus, electronic equipment and the medium of a kind of identification infringement video link.The method comprise the steps that copyrighted source video is gathered around in determination；The video data of the corresponding potential infringement video of the source video is obtained from default website, the video data includes video link；By the video link, the target video file of the potential infringement video is obtained；The video frame of the video frame of the target video file and the source video is subjected to content comparison, obtain the potential infringement video whether be the source video infringement video comparing result；When the comparing result shows that the potential infringement video is the infringement video of the source video, determine the video link for infringement video link.It can solve the problem that infringement video link recognition efficiency is low in the prior art by this programme.
Description
Technical field
The present invention relates to video copy fields, method, apparatus, electronics more particularly to a kind of identification infringement video link
Equipment and medium.
Background technique
With the development of internet, the Copyright Awareness of video display industry is more and more stronger.However, although major video website is basic
Pirate infringement problem is prevented, but the pirate infringement problem on internet is still extremely serious, such as the infringement of short-sighted frequency, foreign network
Infringement, network storage infringement, the infringement of small website etc. invasion phenomenon of standing emerge one after another.Keen competition ring in current video website
Under border, in order to realize piracy infringement video quickly find, rapid strike, to protect the legal benefit of legal video place website
Benefit needs quickly and accurately to identify the infringement video link on internet.
Since many video distribution persons are in uploaded videos, video title is deliberately had modified, leads to many video title ratios
It is relatively fuzzy, therefore, in order to guarantee the accuracy of identification, in the prior art, when video link is encroached right in identification, using text analyzing
Infringement video link is identified in conjunction with the mode of manual examination and verification.
Although existing by way of manual examination and verification, the accuracy of identification infringement video link ensure that.But manually
The mode of audit takes a substantial amount of time, and causes the recognition efficiency of infringement video link low, it is difficult to meet quickly identification internet
The demand of upper infringement video link.
Summary of the invention
The embodiment of the present invention be designed to provide a kind of identification infringement method, apparatus of video link, electronic equipment and
Medium, to solve the problems, such as that infringement video link recognition efficiency is low in the prior art.Specific technical solution is as follows:
In a first aspect, the embodiment of the invention provides a kind of methods of identification infringement video link, which comprises
Copyrighted source video is gathered around in determination；
The video data of the corresponding potential infringement video of the source video, the video data packet are obtained from default website
Include video link；
By the video link, the target video file of the potential infringement video is obtained；
The video frame of the video frame of the target video file and the source video is subjected to content comparison, is obtained described latent
Infringement video whether be the source video infringement video comparing result；
When the comparing result shows that the potential infringement video is the infringement video of the source video, the view is determined
Frequency is linked as infringement video link.
Optionally, the video data further includes content description data；
Described by the video link, before the step of obtaining the target video file of the potential infringement video,
The method also includes:
Judge content description data that the video data includes and the source video content description data whether content
Correlation, if so, executing described by the video link, the step of the target video file of the acquisition potential infringement video
Suddenly.
Optionally, the video frame of the video frame by the target video file and the source video carries out content pair
Than the step of whether potential infringement video is the comparing result of infringement video of the source video obtained, comprising:
Multiframe video frame to be identified is extracted in the potential infringement video file；
According to playing sequence of the multiframe video frame to be identified in the potential infringement video file, successively judgement is every
Whether the content of one video frame to be identified matches with the video frame content of the source video file, and in content matching, record
The playing time of the video frame of the source video to match；
After judgement finishes multiframe video frame to be identified, judge whether the number of the playing time recorded is big
In the first preset threshold；
When the number of the playing time is greater than or equal to first preset threshold, and the broadcasting of first record
Moment is earlier than in the playing time of rear record, it is determined that comparing result is that the potential infringement video file is the source
The infringement video of video；Otherwise, it determines it is not invading for the source video that the comparing result, which is the potential infringement video file,
Weigh video.
Optionally, the step of the video data that the corresponding potential infringement video of the source video is obtained from default website
Suddenly, comprising:
Title and topic based on the source video retrieve the source video pair in default website by web crawlers
The potential infringement video answered, and crawl the video data of the corresponding potential infringement video of the source video.
Optionally, the web crawlers retrieves the mistake of the corresponding potential infringement video of the source video in default website
Journey, comprising:
Determine the number of all videos in default website；
When the number is less than the second preset threshold, all videos in the default website are determined as the source
The corresponding potential infringement video of video；Otherwise, using the title of the source video and topic as retrieval foundation, by described pre-
If being retrieved in website, the corresponding potential infringement video of the source video is obtained.
Optionally, the video data further includes the ID of video uploader；Potential infringement view described in the default website
The quantity of frequency is multiple；
The method also includes:
After multiple potential infringement videos identify in the default website, each video uploader is judged
In ID, if the quantity that there is corresponding infringement link is greater than the Target id of third predetermined threshold value；
If it does, obtaining all videos that the Target id uploads from the default website by web crawlers
Video data as the video data of the corresponding new potential infringement video of the source video, and returns and passes through institute described in execution
The step of stating video link, obtaining the target video file of the potential infringement video.
Second aspect, the embodiment of the invention also provides a kind of device of identification infringement video link, described device includes:
Source video determining module gathers around copyrighted source video for determination；
First video data obtains module, for obtaining the corresponding potential infringement video of the source video from default website
Video data, the video data includes video link；
First video file obtains module, for obtaining the target of the potential infringement video by the video link
Video file；
Video contrast module, in carrying out the video frame of the video frame of the target video file and the source video
Hold comparison, obtain it is described it is potential infringement video whether be the source video infringement video comparing result；
Determining module is linked, for showing that the potential infringement video is the infringement of the source video when the comparing result
When video, determine the video link for infringement video link.
Optionally, the video data further includes content description data；Described device further includes that the second video file obtains
Module；
Second video file obtains module, for, by the video link, obtaining the potential infringement described
Before the step of target video file of video, the content description data and the source video that the video data includes are judged
Whether content is related for content description data, if so, executing described by the video link, the acquisition potential infringement video
Target video file the step of.
Optionally, the video contrast module, is specifically used for:
Multiframe video frame to be identified is extracted in the potential infringement video file；
According to playing sequence of the multiframe video frame to be identified in the potential infringement video file, successively judgement is every
Whether the content of one video frame to be identified matches with the video frame content of the source video file, and in content matching, record
The playing time of the video frame of the source video to match；
After judgement finishes multiframe video frame to be identified, judge whether the number of the playing time recorded is big
In the first preset threshold；
When the number of the playing time is greater than or equal to first preset threshold, and the broadcasting of first record
Moment is earlier than in the playing time of rear record, it is determined that comparing result is that the potential infringement video file is the source
The infringement video of video；Otherwise, it determines it is not invading for the source video that the comparing result, which is the potential infringement video file,
Weigh video.
Optionally, first video data obtains module, is specifically used for:
Title and topic based on the source video retrieve the source video pair in default website by web crawlers
The potential infringement video answered, and crawl the video data of the corresponding potential infringement video of the source video.
Optionally, the web crawlers retrieves the mistake of the corresponding potential infringement video of the source video in default website
Journey, comprising:
Determine the number of all videos in default website；
When the number is less than the second preset threshold, all videos in the default website are determined as the source
The corresponding potential infringement video of video；Otherwise, using the title of the source video and topic as retrieval foundation, by described pre-
If being retrieved in website, the corresponding potential infringement video of the source video is obtained.
Optionally, the video data further includes the ID of video uploader；Potential infringement view described in the default website
The quantity of frequency is multiple；
Described device further includes that the second video data obtains module:
Second video data obtains module, knows for the potential infringement videos multiple in the default website
After not, in the ID that judges each video uploader, if the quantity that there is corresponding infringement link is greater than third predetermined threshold value
Target id；
If it does, obtaining all videos that the Target id uploads from the default website by web crawlers
Video data as the video data of the corresponding new potential infringement video of the source video, and returns and passes through institute described in execution
The step of stating video link, obtaining the target video file of the potential infringement video.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, the electronic equipment includes processor, communication
Interface, memory and communication bus, wherein processor, communication interface, memory complete mutual lead to by communication bus
Letter；
Memory, for storing computer program；
Processor when for executing the program stored on memory, realizes method and step described in above-mentioned first aspect.
Fourth aspect, it is described computer-readable to deposit the embodiment of the invention also provides a kind of computer readable storage medium
It is stored with computer program in storage media, when the computer program is executed by processor, realizes described in above-mentioned first aspect
Method and step.
The embodiment of the present invention replaces manual examination and verification by using video comparison technology, eliminates the mistake of manual examination and verification verifying
Journey has been greatly saved the time of manual examination and verification, has improved review efficiency；It can be realized quick under the premise of guaranteeing accuracy
Identification infringement video link.
In addition, compared with the existing technology, the embodiment of the present invention is by being added the grasp mode of topic by title, and by mark
It, can in conjunction with by video uploader and/or by the grasp mode of default web video number on the basis of topic plus topic grasp mode
With get by title search obtain less than potential infringement video video data, effectively prevent leakage grab, grab video data less,
It thus can more fully identify potential infringement video link.
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, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow chart of the method for identification infringement video link provided by the embodiment of the present invention；
Fig. 2 is the flow chart of the method for the identification infringement video link of another kind provided by the embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of the device of identification infringement video link provided by the embodiment of the present invention；
Fig. 4 is the structural schematic diagram of a kind of electronic equipment provided by 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, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are acquired every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
In order to solve the problems, such as to encroach right in the prior art, video link recognition efficiency is low, and the embodiment of the invention provides one kind
Method, apparatus, electronic equipment and the medium of identification infringement video link.
A kind of method for being provided for the embodiments of the invention identification infringement video link first below is introduced.This hair
A kind of method for identification infringement video link that bright embodiment provides can be applied to electronic equipment.Specifically, the electronic equipment
It can be desktop computer, intelligent mobile terminal, portable computer etc..
Specifically, a kind of executing subject of the method for identification infringement video link can be one run in electronic equipment
The device of kind identification infringement video link.In a particular application, the device of identification infringement video link can answer to be special
With software, or the plug-in unit in existing application software, this is all reasonable.
As shown in Figure 1, a kind of method of identification infringement video link provided in an embodiment of the present invention, may include walking as follows
It is rapid:
Copyrighted source video is gathered around in S101, determination；
As the precondition of identification infringement video link, the tool that website where legal video is possessed should be determined first
Copyrighted source video.
It is understood that the content description data of source video can be obtained once it is determined that gather around copyrighted source video.
Illustratively, the content description data of source video may include source video title, source video brief introduction, source video role, source video
One of performer, topic, bridge section or it is a variety of certainly not limitation and this.Wherein, topic refer to user's hot discussion about
The main contents such as theme, the central idea of source video.The comment information that can be added by collecting user in advance to source video, obtains
To the topic of the source video.Specifically, since topic collection is calculated according to the comment of user, barrage, it can
With by the way that the higher word of those frequencys to be collected, so that topic is obtained, such as in " prolonging auspiciousness strategy ", by the way that the frequency is higher
" Bai Yueguang ", the words such as " cp after Supreme Being " are collected to obtain topic.Comment information is user during watching source video, root
According to oneself cognition to source video impression, the evaluation that source video is made.Comment information is stored in the database of website, can
The comment information is directly extracted from the database in website, which can also be crawled from website by reptile instrument,
Can also disclosed in the website is downloaded in other websites comment information.Wherein, bridge section refers in the source video by verbal description
Classical plot or wonderful.
S102 obtains the video data of the corresponding potential infringement video of the source video, the video from default website
Data include video link；
The implementation that the video data of the corresponding potential infringement video of the source video is obtained from default website exists
It is a variety of.It illustratively, in one possible implementation, can be based on the title of source video, by web crawlers, in default net
The corresponding potential infringement video of the source video is retrieved in standing, and crawls the video of the corresponding potential infringement video of the source video
Data.
It is understood that default website is previously selected targeted website, it can be various video portal websites.Source view
Frequently corresponding potential infringement video refers to the infringement video that may invade source video copyright.
S103 obtains the target video file of the potential infringement video by the video link；
Wherein, by the video link, there are many modes for obtaining the target video file of the potential infringement video.
Illustratively, in one implementation, corresponding potential for a small amount of source video obtained from default website
The video data of infringement video, can directly pass through the video link, obtain the target video file of the potential infringement video.
Wherein, " a small amount of " can be judged that the threshold value may be set according to actual conditions by setting threshold value, not limited herein
It is fixed, such as: the threshold value can be 10,20,30,100,200 etc..Specifically, the quantity when acquired video data is small
When the threshold value, then it is assumed that the video counts of the corresponding potential infringement video of a small amount of source video obtained from default website occur
According to scene.
Illustratively, in another implementation, it is contemplated that the video of magnanimity may be got from default website
Data, in order to reduce the subsequent number of videos for obtaining target video file and mitigate the video content pair to target video file
The pressure of ratio, increase the content description data and the source video that judge potential infringement video content description data whether content phase
The screening step of pass only when it is relevant just carries out the target video file and the subsequent video comparison that obtain potential infringement video
The step of.In this implementation, the video data further includes content description data, the specific steps of which are as follows:
Described by the video link, before the step of obtaining the target video file of the potential infringement video,
Judging content description data that the video data includes, whether content is related to the content description data of the source video, if
It is to execute described the step of passing through the video link, obtaining the target video file of the potential infringement video.
Wherein, content description data included by video data include at least it is potential infringement video video title and/or
Video profile is not limited thereto certainly, can also include user name, User Page etc..
Wherein, the content description data of the content description data that video data includes and the source video whether content phase
It closes, can be judged by text analyzing, specific: the content description data included by the video data is video title
When, if the participle and the content description data of the source video of the video title in the content description data of the video data
In any participle in all participles match；Alternatively, when the content description data included by the video data is video profile,
If the content description data of the participle and the video data of the video profile in the content description data of the video data
In any participle in all participles match；Then think the interior of content description data that video data includes and the source video
It is related to hold description data content.
Wherein, there are many modes for obtaining the target video file of potential infringement video, for example, can pass through web crawlers
Tool or the application programming interfaces API of opening download the target video file, etc. of potential infringement video, the embodiment of the present invention pair
This is without restriction.
The video frame of the video frame of the target video file and the source video is carried out content comparison, obtained by S104
It is described it is potential infringement video whether be the source video infringement video comparing result；
Wherein, the video frame of the video frame of the target video file and the source video is subjected to content comparison, obtained
Whether the potential infringement video is that there are a variety of for the specific implementation of comparing result of infringement video of the source video.
It illustratively, in one implementation, can be by judging video frame to be identified and source video file video frame
Number is matched, obtains comparing result, specific comparison process is as follows:
Multiframe video frame to be identified is extracted in the potential infringement video file；
Judge whether the content of each video frame to be identified matches with the video frame content of the source video file, and inside
When holding matching, the number of the video frame of the source video to match is counted；
When the number of the video frame of matched source video is greater than or equal to first preset threshold, it is determined that comparison knot
Fruit is the infringement video that the potential infringement video file is the source video；Otherwise, it determines the comparing result is described latent
In the infringement video that infringement video file is not the source video.
Illustratively, in another implementation, it is contemplated that the potential infringement video user experience that random ordering plays is poor, difficult
To obtain wide-scale distribution, increase judge it is potential infringement video broadcasting timing whether the consistent step of broadcasting timing with source video
Suddenly, the potential infringement video file only is assert when the broadcasting timing of potential infringement video is consistent with the broadcasting timing of source video
It is the infringement video of source video.The specific comparison process of this implementation is as follows:
Multiframe video frame to be identified is extracted in the potential infringement video file；
According to playing sequence of the multiframe video frame to be identified in the potential infringement video file, successively judgement is every
Whether the content of one video frame to be identified matches with the video frame content of the source video file, and in content matching, record
The playing time of the video frame of the source video to match；
After judgement finishes multiframe video frame to be identified, judge whether the number of the playing time recorded is big
In the first preset threshold；
When the number of the playing time is greater than or equal to first preset threshold, and the broadcasting of first record
Moment is earlier than in the playing time of rear record, it is determined that comparing result is that the potential infringement video file is the source
The infringement video of video；Otherwise, it determines it is not invading for the source video that the comparing result, which is the potential infringement video file,
Weigh video.
Wherein, the first preset threshold flexibly determines according to the actual situation.For example, short-sighted frequency can take lesser numerical value, such as
5,8,10 etc..Long video (referring generally to the video more than half an hour, based on movie and television play) can take biggish numerical value, such as 15,
30 etc..
Illustratively, it takes the first preset threshold to be set as 5, above-mentioned comparison process is illustrated.
The source video file for being 30min for one section of playing duration, if the video frame for the source video that matches is 6, phase
The playing time of the video frame for the source video that matches that should be recorded be 6, be successively 2min, 3min, 5min, 10min, 15min,
22min。
At this point, since the number of playing time is greater than the first preset threshold, and the playing time of first record is located at
Before the playing time recorded afterwards, it can determine that comparing result is the infringement video that potential infringement video file is source video.
If the number of the playing time of record is more than or equal to the first preset threshold, but the playing time of first record is late
In the playing time in rear record, as in above-mentioned example, if the playing time of record be successively 2min, 10min, 5min, 3min,
15min, 22min can then determine that comparing result is the infringement video that potential infringement video file is not source video.
It should be noted that in practical applications, uniquely determined due to having copyrighted source video, and for wait know
Other potential infringement video then can be varied, under the premise of guaranteeing to compare accuracy, in order to reduce comparison data amount, reduces
Pressure when data processing, optionally, can the relatively more extraction of video frame to source video, to the video frame of potential infringement video
Relatively rarely extract.For example, each video frame of extractable source video.Between can waiting the potential infringement video file downloaded
Every extraction multiframe, such as 1 frame picture of extraction per second, 1 minute video extraction, a 60 frame picture.
In addition, it is necessary to explanation, judge each video frame to be identified content whether the view with the source video file
The matching of frequency content frame, can be used conventional images matching algorithm, the embodiment of the present invention is to this process without repeating.
The technical solution of embodiment in order to better understand the present invention, below with reference to Ffmpeg video frequency tool and Deep
Video Analytics system is introduced and how to be compared target video file with source video, to obtain the potential infringement
Video whether be the source video infringement video comparing result.Wherein, FFmpeg be it is a set of can be used to record, convert number
Word tone frequency, video, and it can be translated into the open source computer program of stream, Ffmpeg is provided as the most common video tool
It records, the total solution of conversion and fluidisation audio-video.Deep Video Analytics is one from video and figure
Platform as indexing and extracting information uses the object indexing detected each using deep learning detection and recognizer
Frame/image.
Illustratively, a kind of implementation is as follows:
Firstly, source video is input to Deep Video Analytics system by the device of identification infringement video link, build
Vertical source video index；
Then, the device of identification infringement video link is using Ffmpeg video frequency tool to the mesh of the potential infringement video of acquisition
It marks video file and extracts video frame according to playing sequence, to obtain multiframe video frame to be identified；
Wherein it is possible to preset time interval, a picture is carried out to video at regular intervals and is extracted, for extracting
The quantity of picture can be adjusted according to the actual situation setting.
Then, it is to be identified to input multiframe in Deep Video Analytics system for the device of identification infringement video link
Video frame scans for, and regards when passing through Deep Video Analytics systematic search to the source that matches with video frame to be identified
When the video frame of frequency, relative position index of the video frame of the source video in source video, i.e. playing time are recorded；
If at least N frame video frame to be identified, which can retrieve, matches in Deep Video Analytics system
N frame source video video frame, and the relative position index of first record is earlier than in the relative position of rear record
Index then can determine that potential infringement video file is the infringement video of source video.
By taking 10 frames video frame to be identified as an example, the corresponding source of each video frame frameX (X=1,2 ..., 10) to be identified is remembered
The relative position indexX (X=1,2 ..., 10) of the video frame of video, relative position according to source video playing sequence it is constant can
It indicates are as follows:
In the presence of by it is potential infringement video file playing sequence arrangement 10 frames video frame frame1 to be identified,
Frame2 ..., frame10, after retrieving in Deep Video Analytics system, the relative position of record meets
index1<index2<…<index10。
S105 is determined when the comparing result shows that the potential infringement video is the infringement video of the source video
The video link is infringement video link.
It is understood that can determine potential invade when potential infringement video is identified as the infringement video of source video
Power video corresponds to the video link in video data, which is just infringement video link.
The embodiment of the present invention replaces manual examination and verification by using video comparison technology, eliminates the mistake of manual examination and verification verifying
Journey has been greatly saved the time of manual examination and verification, has improved review efficiency；It can be realized quick under the premise of guaranteeing accuracy
Identification infringement video link.
In order to grab infringement video link comprehensively as much as possible, the legitimate interests of website where protecting legal video.This hair
Bright embodiment can be by being added the grasp mode of topic by title, and on the basis of adding topic grasp mode by title, knot
Close and press video uploader and/or the grasp mode by default web video number, get by title search obtain less than it is latent
In the video data of infringement video, the video data of the more potential infringement videos of crawl is laid for identification infringement video link
Solid foundation.
Based on this kind of roadmap, as shown in Fig. 2, the embodiment of the present invention also provides another identification infringement video link
Method, the method may include following steps:
Copyrighted source video is gathered around in S201, determination；
S202, title and topic based on the source video are retrieved the source in default website and are regarded by web crawlers
Frequently corresponding potential infringement video, and crawl the video data of the corresponding potential infringement video of the source video；The video counts
According to including video link；
Wherein, web crawlers retrieves the specific of the process of the corresponding potential infringement video of the source video in default website
There are a variety of for implementation.
Illustratively, in one implementation, web crawlers is directly using the title of the source video and topic as inspection
Rope foundation obtains the corresponding potential infringement video of the source video by being retrieved in the default website.
Illustratively, in another embodiment, web crawlers first determines the number of all videos in default website；When
When the number is less than the second preset threshold, it is corresponding that all videos in the default website are determined as the source video
Potential infringement video；Otherwise, using the title of the source video and topic as retrieval foundation, by the default website into
Row retrieval, obtains the corresponding potential infringement video of the source video.
It is understood that the second preset threshold can be set according to actual needs.Illustratively, which can
Think 30, at this point, when web crawlers determines the number of all videos in default website less than 30, then by the institute in default website
There is video to be determined as the corresponding potential infringement video of the source video.
It should be noted that the present embodiment method is by analyzing video number in default website, it is less to video number
Website carries out full dose crawl, i.e., all videos of website less to video number all grab, it is therefore prevented that leakage grabs, grabs video less
Data, the website that can encroach right to the low cost of similar individual workship carry out the identification without dead angle, thus potential more fully to identify
Infringement video link lay a good foundation.
S203 obtains the target video file of the potential infringement video by the video link；
The video frame of the video frame of the target video file and the source video is carried out content comparison, obtained by S204
It is described it is potential infringement video whether be the source video infringement video comparing result；
S205 is determined when the comparing result shows that the potential infringement video is the infringement video of the source video
The video link is infringement video link.
In the present embodiment, S201, S203-S205 can in above-described embodiment the step of S101, S103-S105 it is identical,
This will not be repeated here.
It should be noted that when the video data of the corresponding potential infringement video of source video further includes video uploader
ID；And the quantity of potential infringement video described in default website is when being multiple；
The video counts for all videos that the Target id uploads can be obtained from the default website by web crawlers
According to as the video data of the corresponding new potential infringement video of the source video, and then executing and described pass through the video link
The step of connecing, obtaining the target video file of the potential infringement video.
According to the different modes for obtaining having infringement link information source in video uploader ID, the above process is implemented
Mode there are many.
Illustratively, in one implementation, the ID of each video uploader is obtained by the information such as reporting, complaining
In, if the quantity that there is corresponding infringement link is greater than the Target id of third predetermined threshold value；
If it does, can directly pass through web crawlers, all of the Target id upload are obtained from the default website
The video data of video passes through institute described in execution as the video data of the corresponding new potential infringement video of the source video
The step of stating video link, obtaining the target video file of the potential infringement video.
Illustratively, in another implementation, multiple potential infringement videos are known in the default website
After not, in the ID that judges each video uploader, if the quantity that there is corresponding infringement link is greater than third predetermined threshold value
Target id；
If it does, obtaining all videos that the Target id uploads from the default website by web crawlers
Video data as the video data of the corresponding new potential infringement video of the source video, and returns and passes through institute described in execution
The step of stating video link, obtaining the target video file of the potential infringement video.
Wherein, the numerical value of third predetermined threshold value is set according to actual needs, such as takes 3 or 5, etc..
It is understood that if a certain video uploader uploads the infringement link more than third predetermined threshold value quantity,
It is believed that the video uploader is emphasis infringement suspicion person.By grabbing the video data of all videos of video uploader, and
It continues through subsequent text analyzing and video comparison carries out targetedly infringement video link identification, can accomplish that some is put
Arrow, to obtain the effect got twice the result with half the effort.
The embodiment of the present invention grabs the basis of the video data of potential infringement video in the prior art according to source video title
On, by increase by title add topic and by video uploader, by the grasp mode of default web video number, can obtain
Get by title search obtain less than potential infringement video video data, it is therefore prevented that leakage grab, grab video data, thus energy less
Enough potential infringement video links of more fully identification.By measuring and calculating, with only by title search compared with, the embodiment of the present invention passes through
Introduce by title add topic and by video uploader, by the grasp mode of default web video number, more than enough can grab
57% video data containing potential infringement link.
As shown in figure 3, corresponding to above method embodiment, the embodiment of the invention also provides a kind of identification infringement video links
The device connect, comprising:
Source video determining module 301 gathers around copyrighted source video for determination；
First video data obtains module 302, for obtaining the corresponding potential infringement of the source video from default website
The video data of video, the video data include video link；
First video file obtains module 303, by the video link, obtains the target view of the potential infringement video
Frequency file；
Video contrast module 304, for by the video frame of the video frame of the target video file and the source video into
Row content comparison, obtain it is described it is potential infringement video whether be the source video infringement video comparing result；
Determining module 305 is linked, for showing that the potential infringement video is the source video when the comparing result
When infringement video, determine the video link for infringement video link.
Optionally, the video data further includes content description data；Described device further includes that the second video file obtains
Module；
Second video file obtains module, for, by the video link, obtaining the potential infringement described
Before the step of target video file of video, the content description data and the source video that the video data includes are judged
Whether content is related for content description data, if so, executing described by the video link, the acquisition potential infringement video
Target video file the step of.
Optionally, the video contrast module 304, is specifically used for:
Multiframe video frame to be identified is extracted in the potential infringement video file；
According to playing sequence of the multiframe video frame to be identified in the potential infringement video file, successively judgement is every
Whether the content of one video frame to be identified matches with the video frame content of the source video file, and in content matching, record
The playing time of the video frame of the source video to match；
After judgement finishes multiframe video frame to be identified, judge whether the number of the playing time recorded is big
In the first preset threshold；
When the number of the playing time is greater than or equal to first preset threshold, and the broadcasting of first record
Moment is earlier than in the playing time of rear record, it is determined that comparing result is that the potential infringement video file is the source
The infringement video of video；Otherwise, it determines it is not invading for the source video that the comparing result, which is the potential infringement video file,
Weigh video.
Optionally, the first video data obtains module 302, is specifically used for:
Title and topic based on the source video retrieve the source video pair in default website by web crawlers
The potential infringement video answered, and crawl the video data of the corresponding potential infringement video of the source video.
Optionally, the web crawlers retrieves the mistake of the corresponding potential infringement video of the source video in default website
Journey, comprising:
Determine the number of all videos in default website；
When the number is less than the second preset threshold, all videos in the default website are determined as the source
The corresponding potential infringement video of video；Otherwise, using the title of the source video and topic as retrieval foundation, by described pre-
If being retrieved in website, the corresponding potential infringement video of the source video is obtained.
Optionally, the video data further includes the ID of video uploader；Potential infringement view described in the default website
The quantity of frequency is multiple；
Described device further includes that the second video data obtains module:
Second video data obtains module, knows for the potential infringement videos multiple in the default website
After not, in the ID that judges each video uploader, if the quantity that there is corresponding infringement link is greater than third predetermined threshold value
Target id；
If it does, obtaining all videos that the Target id uploads from the default website by web crawlers
Video data as the video data of the corresponding new potential infringement video of the source video, and returns and passes through institute described in execution
The step of stating video link, obtaining the target video file of the potential infringement video.
In another embodiment provided by the invention, a kind of electronic equipment is additionally provided, as shown in figure 4, the electronics is set
Standby includes processor 401, communication interface 402, memory 403 and communication bus 404, wherein processor 401, communication interface
402, memory 403 completes mutual communication by communication bus 404；
Memory 403, for storing computer program；
Processor 401 when for executing the program stored on memory, realizes identification provided by the embodiment of the present invention
The method of infringement video link.
The communication bus 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 can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor 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), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components.
In another embodiment provided by the invention, a kind of computer readable storage medium, the computer are additionally provided
It is stored with computer program in readable storage medium storing program for executing, when the computer program is executed by processor, realizes the embodiment of the present invention
The method of provided identification infringement video link.
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.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present invention.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The 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, the 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.The 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.The 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 the 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 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 foregoing is merely illustrative of the preferred embodiments of the present invention, is 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 (14)
1. a kind of method of identification infringement video link characterized by comprising
Copyrighted source video is gathered around in determination；
The video data of the corresponding potential infringement video of the source video is obtained from default website, the video data includes view
Frequency links；
By the video link, the target video file of the potential infringement video is obtained；
The video frame of the video frame of the target video file and the source video is subjected to content comparison, obtains described potential invade
Power video whether be the source video infringement video comparing result；
When the comparing result shows that the potential infringement video is the infringement video of the source video, the video link is determined
It is connected in infringement video link.
2. the method according to claim 1, wherein the video data further includes content description data；
It is described before the step of obtaining the target video file of the potential infringement video described by the video link
Method further include:
Judging content description data that the video data includes, whether content is related to the content description data of the source video,
If so, executing described the step of passing through the video link, obtaining the target video file of the potential infringement video.
3. method according to claim 1 or 2, which is characterized in that the video frame by the target video file with
The video frame of the source video carries out content comparison, obtain the potential infringement video whether be the source video infringement video
Comparing result the step of, comprising:
Multiframe video frame to be identified is extracted in the potential infringement video file；
According to multiframe video frame to be identified it is described it is potential infringement video file in playing sequence, successively judge it is each to
Whether the content of identification video frame matches with the video frame content of the source video file, and in content matching, records phase
The playing time of the video frame for the source video matched；
After judgement finishes multiframe video frame to be identified, judge whether the number of the playing time recorded is greater than the
One preset threshold；
When the number of the playing time is greater than or equal to first preset threshold, and the playing time of first record
Earlier than in the playing time of rear record, it is determined that comparing result is that the potential infringement video file is the source video
Infringement video；Otherwise, it determines the comparing result is the infringement view that the potential infringement video file is not the source video
Frequently.
4. method according to claim 1 or 2, which is characterized in that described to obtain the source video pair from default website
The step of video data for the potential infringement video answered, comprising:
Title and topic based on the source video, by web crawlers, it is corresponding in default website to retrieve the source video
Potential infringement video, and crawl the video data of the corresponding potential infringement video of the source video.
5. according to the method described in claim 4, it is characterized in that, the web crawlers retrieves the source view in default website
Frequently the process of corresponding potential infringement video, comprising:
Determine the number of all videos in default website；
When the number is less than the second preset threshold, all videos in the default website are determined as the source video
Corresponding potential infringement video；Otherwise, using the title of the source video and topic as retrieval foundation, by the default net
It is retrieved in standing, obtains the corresponding potential infringement video of the source video.
6. according to the method described in claim 4, it is characterized in that, the video data further includes the ID of video uploader；Institute
It is multiple for stating the quantity of potential infringement video described in default website；
The method also includes:
After multiple potential infringement videos identify in the default website, the ID of each video uploader is judged
In, if the quantity that there is corresponding infringement link is greater than the Target id of third predetermined threshold value；
If it does, obtaining the video for all videos that the Target id uploads from the default website by web crawlers
Data, as the video data of the corresponding new potential infringement video of the source video, and it is described by the view to return to execution
The step of frequency links, and obtains the target video file of the potential infringement video.
7. a kind of device of identification infringement video link characterized by comprising
Source video determining module gathers around copyrighted source video for determination；
First video data obtains module, for obtaining the view of the corresponding potential infringement video of the source video from default website
Frequency evidence, the video data include video link；
First video file obtains module, for obtaining the target video of the potential infringement video by the video link
File；
Video contrast module, for the video frame of the video frame of the target video file and the source video to be carried out content pair
Than, obtain it is described it is potential infringement video whether be the source video infringement video comparing result；
Determining module is linked, for showing that the potential infringement video is the infringement video of the source video when the comparing result
When, determine the video link for infringement video link.
8. device according to claim 7, which is characterized in that the video data further includes content description data；It is described
Device further includes that the second video file obtains module；
Second video file obtains module, for, by the video link, obtaining the potential infringement video described
Target video file the step of before, judge the content of content description data that the video data includes and the source video
Describing data, whether content is related, if so, obtaining the mesh of the potential infringement video by the video link described in executing
The step of marking video file.
9. device according to claim 7 or 8, which is characterized in that the video contrast module is specifically used for:
Multiframe video frame to be identified is extracted in the potential infringement video file；
According to multiframe video frame to be identified it is described it is potential infringement video file in playing sequence, successively judge it is each to
Whether the content of identification video frame matches with the video frame content of the source video file, and in content matching, records phase
The playing time of the video frame for the source video matched；
After judgement finishes multiframe video frame to be identified, judge whether the number of the playing time recorded is greater than the
One preset threshold；
When the number of the playing time is greater than or equal to first preset threshold, and the playing time of first record
Earlier than in the playing time of rear record, it is determined that comparing result is that the potential infringement video file is the source video
Infringement video；Otherwise, it determines the comparing result is the infringement view that the potential infringement video file is not the source video
Frequently.
10. device according to claim 7 or 8, which is characterized in that first video data obtains module, specific to use
In:
Title and topic based on the source video, by web crawlers, it is corresponding in default website to retrieve the source video
Potential infringement video, and crawl the video data of the corresponding potential infringement video of the source video.
11. device according to claim 10, which is characterized in that the web crawlers retrieves the source in default website
The process of the corresponding potential infringement video of video, comprising:
Determine the number of all videos in default website；
When the number is less than the second preset threshold, all videos in the default website are determined as the source video
Corresponding potential infringement video；Otherwise, using the title of the source video and topic as retrieval foundation, by the default net
It is retrieved in standing, obtains the corresponding potential infringement video of the source video.
12. device according to claim 10, which is characterized in that the video data further includes the ID of video uploader；
The quantity of potential infringement video is multiple described in the default website；
Described device further includes that the second video data obtains module:
Second video data obtains module, has identified for the potential infringement videos multiple in the default website
In Bi Hou, the ID for judging each video uploader, if the quantity that there is corresponding infringement link is greater than the mesh of third predetermined threshold value
Mark ID；
If it does, obtaining the video for all videos that the Target id uploads from the default website by web crawlers
Data, as the video data of the corresponding new potential infringement video of the source video, and it is described by the view to return to execution
The step of frequency links, and obtains the target video file of the potential infringement video.
13. a kind of electronic equipment, it is characterised in that: the electronic equipment includes that processor, communication interface, memory and communication are total
Line, 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, realizes any method and step of claim 1 to 6.
14. a kind of computer readable storage medium, it is characterised in that: be stored with computer in the computer readable storage medium
Program when the computer program is executed by processor, realizes any method and step of claim 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910650865.5A CN110324729B (en) | 2019-07-18 | 2019-07-18 | Method, device, electronic equipment and medium for identifying infringement video link |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910650865.5A CN110324729B (en) | 2019-07-18 | 2019-07-18 | Method, device, electronic equipment and medium for identifying infringement video link |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110324729A true CN110324729A (en) | 2019-10-11 |
| CN110324729B CN110324729B (en) | 2021-08-27 |
Family
ID=68123980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910650865.5A Active CN110324729B (en) | 2019-07-18 | 2019-07-18 | Method, device, electronic equipment and medium for identifying infringement video link |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110324729B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111182364A (en) * | 2019-12-27 | 2020-05-19 | 杭州趣维科技有限公司 | Short video copyright detection method and system |
| CN111274450A (en) * | 2020-02-21 | 2020-06-12 | 沃民高新科技（北京）股份有限公司 | Video identification method |
| CN111314736A (en) * | 2020-03-19 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Video copyright analysis method and device, electronic equipment and storage medium |
| CN111708988A (en) * | 2020-05-15 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Infringement video identification method and device, electronic equipment and storage medium |
| CN111738171A (en) * | 2020-06-24 | 2020-10-02 | 北京奇艺世纪科技有限公司 | Video clip detection method and device, electronic equipment and storage medium |
| CN111950360A (en) * | 2020-07-06 | 2020-11-17 | 北京奇艺世纪科技有限公司 | Method and device for identifying infringing user |
| CN112203141A (en) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | Video-on-demand content identification method, device, equipment and system and smart television |
| CN112688931A (en) * | 2020-12-21 | 2021-04-20 | 杭州当虹科技股份有限公司 | Method for acquiring video playing webpage evidence obtaining content by using RecordRTC |
| CN112788363A (en) * | 2020-12-30 | 2021-05-11 | 北京奇艺世纪科技有限公司 | Method for identifying infringement video, device for identifying infringement video and electronic equipment |
| CN113076961A (en) * | 2021-05-12 | 2021-07-06 | 北京奇艺世纪科技有限公司 | Image feature library updating method, image detection method and device |
| CN115640422A (en) * | 2022-11-29 | 2023-01-24 | 苏州琅日晴传媒科技有限公司 | Network media video data analysis and supervision system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120177296A1 (en) * | 2011-01-07 | 2012-07-12 | Alcatel-Lucent Usa Inc. | Method and apparatus for comparing videos |
| CN102802090A (en) * | 2011-05-27 | 2012-11-28 | 未序网络科技（上海）有限公司 | Video copyright protection method and system |
| CN104143055A (en) * | 2014-08-16 | 2014-11-12 | 合一网络技术(北京)有限公司 | Pirated video monitoring method and system |
| EP2811416A1 (en) * | 2013-06-06 | 2014-12-10 | Vestel Elektronik Sanayi ve Ticaret A.S. | An identification method |
| CN105681899A (en) * | 2015-12-31 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Method and device for detecting similar video and pirated video |
| US20160236083A1 (en) * | 2002-12-10 | 2016-08-18 | Sony Interactive Entertainment America Llc | System and Method for Compressing Video Frames or Portions Thereof Based on Feedback Information from a Client Device |
| CN107169004A (en) * | 2017-03-31 | 2017-09-15 | 北京奇艺世纪科技有限公司 | A kind of property data base update method and device |
| CN107832384A (en) * | 2017-10-28 | 2018-03-23 | 北京安妮全版权科技发展有限公司 | Infringement detection method, device, storage medium and electronic equipment |
| CN108881947A (en) * | 2017-05-15 | 2018-11-23 | 阿里巴巴集团控股有限公司 | A kind of infringement detection method and device of live stream |
-
2019
- 2019-07-18 CN CN201910650865.5A patent/CN110324729B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160236083A1 (en) * | 2002-12-10 | 2016-08-18 | Sony Interactive Entertainment America Llc | System and Method for Compressing Video Frames or Portions Thereof Based on Feedback Information from a Client Device |
| US20120177296A1 (en) * | 2011-01-07 | 2012-07-12 | Alcatel-Lucent Usa Inc. | Method and apparatus for comparing videos |
| CN102802090A (en) * | 2011-05-27 | 2012-11-28 | 未序网络科技（上海）有限公司 | Video copyright protection method and system |
| EP2811416A1 (en) * | 2013-06-06 | 2014-12-10 | Vestel Elektronik Sanayi ve Ticaret A.S. | An identification method |
| CN104143055A (en) * | 2014-08-16 | 2014-11-12 | 合一网络技术(北京)有限公司 | Pirated video monitoring method and system |
| CN105681899A (en) * | 2015-12-31 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Method and device for detecting similar video and pirated video |
| CN107169004A (en) * | 2017-03-31 | 2017-09-15 | 北京奇艺世纪科技有限公司 | A kind of property data base update method and device |
| CN108881947A (en) * | 2017-05-15 | 2018-11-23 | 阿里巴巴集团控股有限公司 | A kind of infringement detection method and device of live stream |
| CN107832384A (en) * | 2017-10-28 | 2018-03-23 | 北京安妮全版权科技发展有限公司 | Infringement detection method, device, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 贾克斌: "基于时序特征的视频相似性匹配算法", 《北京工业大学学报》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111182364A (en) * | 2019-12-27 | 2020-05-19 | 杭州趣维科技有限公司 | Short video copyright detection method and system |
| CN111274450A (en) * | 2020-02-21 | 2020-06-12 | 沃民高新科技（北京）股份有限公司 | Video identification method |
| CN111314736A (en) * | 2020-03-19 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Video copyright analysis method and device, electronic equipment and storage medium |
| CN111708988B (en) * | 2020-05-15 | 2023-05-30 | 北京奇艺世纪科技有限公司 | Infringement video identification method and device, electronic equipment and storage medium |
| CN111708988A (en) * | 2020-05-15 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Infringement video identification method and device, electronic equipment and storage medium |
| CN111738171A (en) * | 2020-06-24 | 2020-10-02 | 北京奇艺世纪科技有限公司 | Video clip detection method and device, electronic equipment and storage medium |
| CN111738171B (en) * | 2020-06-24 | 2023-12-08 | 北京奇艺世纪科技有限公司 | Video clip detection method and device, electronic equipment and storage medium |
| CN111950360B (en) * | 2020-07-06 | 2023-08-18 | 北京奇艺世纪科技有限公司 | Method and device for identifying infringement user |
| CN111950360A (en) * | 2020-07-06 | 2020-11-17 | 北京奇艺世纪科技有限公司 | Method and device for identifying infringing user |
| CN112203141A (en) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | Video-on-demand content identification method, device, equipment and system and smart television |
| CN112688931A (en) * | 2020-12-21 | 2021-04-20 | 杭州当虹科技股份有限公司 | Method for acquiring video playing webpage evidence obtaining content by using RecordRTC |
| CN112788363A (en) * | 2020-12-30 | 2021-05-11 | 北京奇艺世纪科技有限公司 | Method for identifying infringement video, device for identifying infringement video and electronic equipment |
| CN113076961A (en) * | 2021-05-12 | 2021-07-06 | 北京奇艺世纪科技有限公司 | Image feature library updating method, image detection method and device |
| CN113076961B (en) * | 2021-05-12 | 2023-09-05 | 北京奇艺世纪科技有限公司 | Image feature library updating method, image detection method and device |
| CN115640422A (en) * | 2022-11-29 | 2023-01-24 | 苏州琅日晴传媒科技有限公司 | Network media video data analysis and supervision system |
| CN115640422B (en) * | 2022-11-29 | 2023-12-22 | 深圳有影传媒有限公司 | Network media video data analysis and supervision system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110324729B (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110324729A (en) | A kind of method, apparatus, electronic equipment and the medium of identification infringement video link | |
| Reed et al. | Identifying https-protected netflix videos in real-time | |
| US9785757B2 (en) | System for identifying content of digital data | |
| CN104615760B (en) | Fishing website recognition methods and system | |
| TWI482045B (en) | System, method and computer-readable medium for detecting the source of media content with application to business rules | |
| CN108898415A (en) | A kind of the flow index of correlation prediction technique and device of video collection of drama | |
| CN109104421B (en) | Website content tampering detection method, device, equipment and readable storage medium | |
| KR20190042984A (en) | System for monitoring digital works distribution | |
| CN113407886A (en) | Network crime platform identification method, system, device and computer storage medium | |
| TW202201969A (en) | Apparatus and method for filtering harmful video file | |
| CN107784551A (en) | Stock public sentiment data processing method, device, computer equipment and storage medium | |
| CN111539929A (en) | Copyright detection method and device and electronic equipment | |
| CN101493871A (en) | Information processing system, information processing apparatus, information processing program and recording medium | |
| CN110796053B (en) | Video detection method and device, electronic equipment and computer readable storage medium | |
| CN110198490B (en) | Live video theme classification method and device and electronic equipment | |
| CN111083469A (en) | Video quality determination method and device, electronic equipment and readable storage medium | |
| CN105611331B (en) | A kind of video pushing method and system based on smart television | |
| CN113076961A (en) | Image feature library updating method, image detection method and device | |
| CN108882024B (en) | Video playing method and device and electronic equipment | |
| CN108038233B (en) | Method and device for collecting articles, electronic equipment and storage medium | |
| KR20210072610A (en) | Monitoring service apparatus and method for preventing copyright infringement of news photograph | |
| US11714847B2 (en) | Methods and apparatus to detect unconfined view media | |
| CN104899320A (en) | Webpage repair method, terminal, server and system | |
| CN114638304A (en) | Training method of image recognition model, image recognition method and device | |
| CN113886273A (en) | Performance test method, device, test equipment and medium of application program |
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 |