CN111860367A - Video repetition identification method, electronic device and computer-readable storage medium - Google Patents

Abstract

The application provides a video repeatability identification method, video repeatability identification equipment and a computer readable storage medium. This application is through video identification information generation based on video fingerprint, video identification information is used for only sign the video, then right the video fingerprint splits, obtains a plurality of fingerprint sections, and then will a plurality of fingerprint sections correspond and add to in the different video frames of video, like this, can follow and draw the fingerprint section concatenation from the different video frames of video and obtain complete video fingerprint to can discern the video that the content is repeated based on the video fingerprint of every video, and, can avoid because the video follow-up broadcast of the great influence video of the data bulk of interpolation when adding complete video fingerprint in each video frame.

Description

Video repetition identification method, electronic device and computer-readable storage medium

【Technical field】

The present application relates to video processing technology, and in particular, to a video repetition identification method, an electronic device, and a computer-readable storage medium.

【Background technique】

At present, with the development of audio and video technology and self-media technology, various video websites and self-media platforms continue to emerge. Video manufacturers and users will generate a large number of videos with rich and diverse content every day, covering movies, TV series, animation, variety shows, life, music, etc. These videos will be uploaded to various video websites and self-media platforms for users to watch.

In the prior art, various videos, especially short videos, are easily downloaded by some users from a certain video website or self-media platform and then uploaded to other video websites or self-media platforms, or after simple modification of the downloaded video. Upload to video platforms and self-media platforms. In this way, video platforms and self-media platforms actually repeatedly include videos with the same content, wasting storage resources; in addition, when recommending videos to users, it is easy to recommend multiple videos with the same content to users, causing users to repeat Playing videos of the same content degrades the user experience.

[Content of the invention]

Aspects of the present application provide a video duplication identification method, electronic device, and computer-readable storage medium for identifying a video with duplicate content.

In one aspect of the present application, a method for recognizing video repetition is provided, comprising:

Generate a video fingerprint of the video based on the video identification information of the video, and the video identification information is used to uniquely identify the video;

Splitting the video fingerprint to obtain a plurality of fingerprint segments;

The plurality of fingerprint segments are correspondingly added to different video frames of the video.

Another aspect of the present application provides another video repetition identification method, comprising:

Extracting fingerprint segments from multiple video frames of the video respectively to obtain multiple fingerprint segments;

Splicing the extracted fingerprint segments to obtain a video fingerprint of the video; the video fingerprint is generated based on the video identification information of the video, and the video identification information is used to uniquely identify the video;

Based on the video fingerprint, it is identified whether there are other videos that duplicate the content of the video.

Another aspect of the present application provides an electronic device, the electronic device comprising:

one or more processors;

storage means for storing one or more programs,

When executed by the one or more processors, the one or more programs cause the one or more processors to implement the video repetition identification provided by the above aspect.

Another aspect of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, realizes the video repetition identification provided in the above-mentioned aspect.

As can be seen from the above technical solutions, in some embodiments of the present application, a video fingerprint of the video is generated based on the video identification information of the video, and then the video fingerprint is split to obtain multiple fingerprint segments, and then the multiple fingerprint segments are obtained. The fingerprint segments are correspondingly added to different video frames of the video. In this way, fingerprint segments can be extracted from different video frames and spliced to obtain a complete video fingerprint, so that videos with repeated content can be identified based on the video fingerprint of each video; Adding the fingerprint segments to different video frames of the video can avoid the subsequent playback of the video being affected due to the large amount of data added when a complete video fingerprint is added to each video frame.

It can be seen from the above technical solutions that in other embodiments of the present application, fingerprint segments can be extracted from multiple video frames of a video respectively to obtain multiple fingerprint segments, and then the extracted multiple fingerprint segments are spliced to obtain As for the video fingerprint of the video, since the video fingerprint is generated based on the video identification information of the video, whether there is another video that duplicates the content of the video is identified based on the video fingerprint. In this way, videos with repeated content can be identified based on the video fingerprint of each video; and, since the video fingerprint of one video is divided into multiple fingerprint segments and added to different video frames of the video, it is possible to avoid adding the content in each video frame. When a complete video fingerprint is used, the subsequent playback of the video is affected due to the large amount of data added.

In addition, by adopting the technical solution provided by the present application, since it is possible to identify whether there are videos with duplicate content based on video fingerprints, it is possible to avoid video platforms and self-media platforms from repeatedly recording videos with the same content, saving storage resources and maintenance resources.

In addition, by adopting the technical solution provided by the present application, since it is possible to identify whether there is a video with repeated content based on the video fingerprint, it is possible to avoid recommending multiple videos with the same content to the user when recommending a video to the user, and prevent the user from playing the same content repeatedly. video can effectively improve the user experience.

【Description of drawings】

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that are required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are from the present application. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

1 is a schematic flowchart of a method for recognizing video repetition provided by an embodiment of the present application;

FIG. 2 is a schematic diagram of adding a plurality of fingerprint segments to different video frames correspondingly in an embodiment of the application;

FIG. 3 is a schematic flowchart of splitting the video fingerprint to obtain a plurality of fingerprint segments according to an embodiment of the application;

FIG. 4 is a schematic diagram of a format of a fingerprint segment in an embodiment of the application;

5 is a schematic diagram of adding a fingerprint macroblock to a video frame according to an embodiment of the application;

6 is a schematic flowchart of a method for recognizing video repetition provided by another embodiment of the present application;

FIG. 7 is a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present application.

【Detailed ways】

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

It should be noted that the terminals involved in the embodiments of the present application may include but are not limited to mobile phones, personal digital assistants (Personal Digital Assistants, PDAs), wireless handheld devices, tablet computers (Tablet Computers), and personal computers (Personal Computers, PCs). ), MP3 players, MP4 players, wearable devices (eg, smart glasses, smart watches, smart bracelets, etc.), etc.

In addition, the term "and/or" in this article is only an association relationship to describe the associated objects, indicating that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, There are three cases of B alone. In addition, the character "/" in this document generally indicates that the related objects are an "or" relationship.

As mentioned in the Background Art, various videos, especially short videos, are easily downloaded by some users from a certain video website or self-media platform and then uploaded to other video websites or self-media platforms, or simply modify the downloaded videos. After uploading to the video platform and self-media platform, the video platform and self-media platform actually repeatedly recorded videos with the same content, wasting storage resources; Videos are recommended to users, causing users to repeatedly play videos with the same content, which reduces user experience.

Therefore, there is an urgent need to provide a video duplication identification method for identifying different videos with repeated content.

FIG. 1 is a schematic flowchart of a method for recognizing video repetition according to an embodiment of the present application, as shown in FIG. 1 .

101. Generate a video fingerprint of the video based on the video identification information of the video.

Wherein, the video identification information is used to uniquely identify the video.

Optionally, in some of these implementations, the video identification information may include, but is not limited to, any one or more of the following: frame data within a preset playback time range at the beginning of the video or the beginning of the video. The frame data of the preset number of frames, the frame data of the preset playback time range at the end of the video or the frame data of the preset number of frames at the end of the video, the name of the video, the producer of the video, the the production date of the said video, etc. The embodiments of the present application do not limit the specific content composition of the video identification information.

Optionally, in some of the implementation manners, the video identification information of the video may be calculated based on a preset hash algorithm to obtain the video fingerprint. The hash algorithm may be any hash algorithm, such as the MD5 algorithm, etc. The embodiment of the present application does not limit the specific hash algorithm used.

Since the video identification information is used to uniquely identify a video, a video fingerprint is generated based on the video identification information. In this way, each generated video fingerprint can uniquely correspond to a video. By comparing whether the video fingerprints are the same, it can be determined whether the corresponding video comes from to the same video, so that it can be identified whether the video content is repeated or not.

102. Split the video fingerprint to obtain multiple fingerprint segments.

103. Correspondingly add the plurality of fingerprint segments to different video frames of the video.

As shown in FIG. 2 , it is a schematic diagram of correspondingly adding multiple fingerprint segments to different video frames in an embodiment of the present application.

It should be noted that, part or all of the execution bodies of 101 to 103 may be applications located in the terminal, or may also be functional units such as plug-ins or software development kits (Software Development Kit, SDK) in the application setting the terminal, or It may also be an application located in a network-side server, which is not particularly limited in this embodiment of the present application.

It can be understood that the application may be a local program (nativeApp) installed on the terminal, or may also be a web page program (webApp) of a browser on the terminal, which is not limited in this embodiment of the present application.

In this way, fingerprint segments can be extracted from different video frames and spliced to obtain a complete video fingerprint, so that videos with repeated content can be identified based on the video fingerprint of each video; Adding the fingerprint segments to different video frames of the video can avoid the subsequent playback of the video being affected due to the large amount of data added when a complete video fingerprint is added to each video frame.

In addition, since it is possible to identify whether there are videos with duplicate content based on video fingerprints, it is possible to avoid video platforms and self-media platforms from repeatedly recording videos with the same content, saving storage resources and maintenance resources.

In addition, since it can identify whether there is a video with duplicate content based on the video fingerprint, it can avoid recommending multiple videos with the same content to the user when recommending a video to the user, and avoid the user from repeatedly playing the video with the same content, which can effectively improve the user experience.

FIG. 3 is a schematic flowchart of splitting the video fingerprint to obtain multiple fingerprint segments according to an embodiment of the present application. As shown in FIG. 3, based on the embodiment shown in FIG. 1, 102 may include:

301. Split the video fingerprint into multiple parts to obtain multiple fingerprint data.

302. Assign a fingerprint segment position to the fingerprint data according to the positions of the plurality of fingerprint data in the video fingerprint, respectively.

303. Encapsulate each fingerprint data in the plurality of fingerprint data, the corresponding fingerprint segment position, and the total number of fingerprint segments into one fingerprint segment to obtain multiple fingerprint segments.

The position of the fingerprint segment is used to represent the position of the corresponding fingerprint data in the video fingerprint, and the total number of fingerprint segments is used to represent the number of fingerprint data obtained by splitting the video fingerprint. For example, assuming that a video fingerprint is split into 10 fingerprint data, the total number of fingerprint segments is 10; fingerprint segment positions 1 to 10 are sequentially assigned to each fingerprint data according to the positions of the 10 fingerprint data in the fingerprint data.

Based on this embodiment, each fingerprint segment may include three parts of data: fingerprint segment position (index), total number of fingerprint segments, and fingerprint data. As shown in FIG. 4 , it is a schematic diagram of a format of a fingerprint segment in an embodiment of the present application. The order of the three parts of data included in each fingerprint segment can be adjusted, and is not limited to the order of the embodiment shown in FIG. 4 .

Based on this embodiment, in addition to the fingerprint data, each fingerprint segment may also include the location of the fingerprint segment and the total number of fingerprint segments. Then it can be determined whether all the fingerprint segments corresponding to the fingerprint data in a video fingerprint are read according to the total number of fingerprint segments. After reading all the fingerprint segments corresponding to the fingerprint data in a video fingerprint, the fingerprint segment in each fingerprint segment can be position, the fingerprint data in each fingerprint segment is spliced according to its position sequence in the video fingerprint, so as to obtain a complete video fingerprint.

The embodiments of the present application may be applicable to video coding standards and videos of any format. In a specific implementation, when each fingerprint segment is added to a video frame, the fingerprint segment may be added to any reserved information segment in the video frame, or may be added to the back of the video frame data. No restrictions.

For example, in the H.264/AVC video coding standard, the original code stream (bare stream) is composed of Network Abstract Layer Unit (NALU) one after another, and the entire system framework is divided into two levels: video Coding layer (Video Coding Layer, VCL) and network abstraction layer network abstraction layer (Network AbstractLayer, NAL). Wherein, an original NALU usually consists of three parts: a start code (StartCode), a NALU header (NALU Header) and a NALU payload (NALU Payload), wherein the NALU payload is the main body of the NALU. The main body of the NALU includes slice headers and on-chip data, 1 frame=n slices (slices), 1 slice=n macroblocks (MB), and 1 macroblock=16×16 yuv data. Among them, the macroblock is the main bearer of video information. An encoded image is usually divided into multiple macroblocks, which contain the luminance and chrominance information of each pixel. The main task of video decoding is to provide an efficient way to convert the code stream from the to obtain the pixel array in the macroblock. Wherein, each video frame contains a macroblock with a reserved block (residual block or coded residual), and the fingerprint segment can be added to the reserved block, or the fingerprint segment can be added to the rear of the NALU main body.

Optionally, in the video repetition identification method of another embodiment, on the basis of the embodiment shown in FIG. 1 , after step 102 , alpha (α) channel conversion may be performed on the plurality of fingerprint segments respectively, Convert the alpha channel of the plurality of fingerprint segments to a transparent background color. Correspondingly, in 103, the plurality of fingerprint segments converted from the alpha channel may be correspondingly added to the macroblocks that carry the skip run identifier in different video frames of the video. The skip run flag is used to indicate that the corresponding macroblock will not be played by the player.

Optionally, in the video repeatability identification method of another embodiment, on the basis of the embodiment shown in FIG. 1 , after 102 , each of the fingerprint segments in the plurality of fingerprint segments can also be separately identified. Perform alpha channel conversion, and convert the alpha channel of each fingerprint segment into a transparent background color; then, generate a fingerprint macroblock based on each fingerprint segment converted from the alpha channel, and add skip to the fingerprint macroblock run ID. The skip run flag is used to indicate that the corresponding macroblock will not be played by the player. Correspondingly, in 103, a plurality of fingerprint macroblocks with skip run identifiers added may be correspondingly added to different video frames of the video.

Based on this embodiment, the alpha channel of the fingerprint segment is converted into a transparent background color, so that the information in the fingerprint segment does not participate in video rendering during the subsequent video playback process, and does not change the screen displayed by the overall video; The macroblock of the segment carries the skip run flag and will not be played by the player, so it will not affect the video playback effect.

As shown in FIG. 5 , it is a schematic diagram of adding fingerprint macroblocks to a video frame. In this implementation, an original video frame includes a frame header and frame data, the fingerprint data is encapsulated into a fingerprint segment, and then α channel conversion is performed to generate a fingerprint macroblock, and then a skip run flag is added (not shown in FIG. 5 ), Then, the fingerprint macroblock added with the skip run logo is combined with the frame data, and the obtained video frame includes the frame header and the mixed frame data obtained by combining the fingerprint macroblock and the frame data.

Optionally, in some of the implementation manners, in 103, the multiple fingerprint segments may be sequentially added to multiple consecutive different video frames; or, the multiple fingerprint segments may also be randomly added to multiple In different video frames, this embodiment of the present application does not limit.

Among them, when multiple fingerprint segments are sequentially added to multiple consecutive different video frames, the fingerprint segment data can be read frame by frame subsequently, which helps to improve the efficiency of reading the fingerprint segment data, thereby improving the overall recognition efficiency of repeated videos. .

Optionally, in some of the implementation manners, in 103, the multiple fingerprint segments may be added to different video segments of the video respectively, and the multiple fingerprint segments are correspondingly added in the video segment. in different video frames.

For example, in an optional example, the plurality of fingerprint segments may be added to each video frame of the video in sequence, so that even if the video is intercepted by other users, a certain segment or the header of the video is removed. The complete fingerprint segment included in the video fingerprint can still be extracted from other video frames, so as to realize the repetitive identification of the video.

Optionally, in the video repeatability identification method of another embodiment, on the basis of the embodiment shown in FIG. 1 , it may further include: encapsulating the video fingerprint with the preset fingerprint segment position and the total number of fingerprint segments, Obtaining a complete fingerprint, wherein the preset fingerprint segment position is used to indicate that the complete fingerprint includes complete video fingerprint data, the total number of fingerprint segments is 1, and then at least one fingerprint segment is not added in the video The full fingerprint is added to the video frame of .

For example, in an optional example, a complete fingerprint can be added every several frames in the video, so as to avoid the damage of the fingerprint segment during the video transmission process, or the loss of intermediate frames when other users modify the video, resulting in failure to A complete video fingerprint is obtained by splicing, and based on the complete fingerprint, the repetitive identification of the video can be realized independently.

Optionally, on the basis of the above embodiment, the video fingerprint is encapsulated with the preset fingerprint segment position and the total number of fingerprint segments, and after obtaining a complete fingerprint, alpha channel conversion can also be performed on the complete fingerprint, and the The alpha channel of the complete fingerprint is converted into a transparent background color; then, a fingerprint macroblock is generated based on the complete fingerprint converted from the alpha channel, and a skip run identifier is added to the fingerprint macroblock, and the skip run identifier is used to represent the corresponding fingerprint macro. Chunks will not be played by the player. Correspondingly, the fingerprint macroblock to which the skip run identifier is added may be respectively added to at least one video frame in the video to which the fingerprint segment is not added.

Alternatively, on the basis of the above-mentioned embodiment, after encapsulating the video fingerprint with the preset fingerprint segment position and the total number of fingerprint segments, and obtaining a complete fingerprint, the complete fingerprint can also be converted by alpha channel to convert the complete fingerprint Convert the alpha channel to a transparent background color. Correspondingly, the complete fingerprint converted by the alpha channel is added to the macroblock that carries the skip run mark in at least one video frame without adding the fingerprint segment in the video, and the skip run mark is used to represent the corresponding macroblock. will not be played by the player.

Based on this embodiment, converting the alpha channel of the complete fingerprint to a transparent background color can prevent the information in the complete fingerprint from participating in video rendering during the subsequent video playback, and will not change the picture displayed by the overall video; The macroblock of the fingerprint carries the skip run logo and will not be played by the player, so it will not affect the video playback effect.

FIG. 6 is a schematic flowchart of a video repetition identification method provided by another embodiment of the present application, as shown in FIG. 6 .

601. Extract fingerprint segments from multiple video frames of a video, respectively, to obtain multiple fingerprint segments.

602. Splicing the extracted fingerprint segments to obtain a video fingerprint of the video.

The video fingerprint is generated based on video identification information of the video, and the video identification information is used to uniquely identify the video.

Optionally, in some of these implementations, the video identification information may include, but is not limited to, any one or more of the following: frame data within a preset playback time range at the beginning of the video or the beginning of the video. The frame data of the preset number of frames, the frame data of the preset playback time range at the end of the video or the frame data of the preset number of frames at the end of the video, the name of the video, the producer of the video, the the production date of the said video, etc. The embodiments of the present application do not limit the specific content composition of the video identification information.

603. Based on the video fingerprint, identify whether there are other videos that duplicate the content of the video.

In a specific implementation, the video fingerprint may be compared with the video fingerprints of other videos, and it is determined whether there are other videos that duplicate the content of the video according to whether there are other videos with the same video fingerprint.

It should be noted that, some or all of the execution bodies of 601 to 603 may be applications located in the terminal (eg, players), or may also be plug-ins or software development kits (Software Development Kit, SDK) in the application setting the terminal, etc. A functional unit, or may also be an application located in a network-side server (eg, a video platform, a self-media platform), which is not particularly limited in this embodiment of the present application.

It can be understood that the application may be a local program (nativeApp) installed on the terminal, or may also be a web page program (webApp) of a browser on the terminal, which is not limited in this embodiment of the present application.

In this way, videos with repeated content can be identified based on the video fingerprint of each video; and, since the video fingerprint of one video is divided into multiple fingerprint segments and added to different video frames of the video, it is possible to avoid adding the content in each video frame. When a complete video fingerprint is used, the subsequent playback of the video is affected due to the large amount of data added.

In addition, by adopting the technical solution provided by the present application, since it is possible to identify whether there are videos with duplicate content based on video fingerprints, it is possible to avoid video platforms and self-media platforms from repeatedly recording videos with the same content, saving storage resources and maintenance resources.

In addition, by adopting the technical solution provided by the present application, since it is possible to identify whether there is a video with repeated content based on the video fingerprint, it is possible to avoid recommending multiple videos with the same content to the user when recommending a video to the user, and prevent the user from playing the same content repeatedly. video can effectively improve the user experience.

Optionally, in some of the implementation manners, in 601 , fingerprint segments may be extracted from macroblocks carrying skiprun identifiers in multiple video frames, and the fingerprint segments are converted to a transparent background color through an alpha channel.

Optionally, in some of the implementation manners, the fingerprint segment includes: the location of the fingerprint segment, the total number of fingerprint segments, and fingerprint data, as shown in FIG. 4 . The position of the fingerprint segment is used to represent the position of the corresponding fingerprint data in the video fingerprint, and the total number of fingerprint segments is used to represent the number of fingerprint data obtained by splitting the video fingerprint. For example, assuming that a video fingerprint is split into 10 fingerprint data, the total number of fingerprint segments is 10; fingerprint segment positions 1 to 10 are sequentially assigned to each fingerprint data according to the positions of the 10 fingerprint data in the fingerprint data.

Correspondingly, after 601, the position of the fingerprint segments and the total number of fingerprint segments in the multiple fingerprint segments can also be read, and then, it is identified whether the number of fingerprint segments extracted from the multiple fingerprint segments is consistent with the total number of fingerprint segments. , and whether the positions of the fingerprint segments in the plurality of fingerprint segments are not repeated. Correspondingly, if the number of fingerprint segments is consistent with the total number of fingerprint segments, and the positions of the fingerprint segments in the multiple fingerprint segments are not repeated, the multiple fingerprint segments are all fingerprint segments corresponding to the complete video fingerprint. , in 602, splicing the fingerprint data included in each fingerprint segment of the multiple fingerprint segments according to the fingerprint segment positions of the multiple fingerprint segments, to obtain a video fingerprint of the video.

Based on this embodiment, whether to extract all fingerprint segments corresponding to a complete video fingerprint can be determined based on the fingerprint segment positions in the fingerprint segments and the total number of fingerprint segments. The fingerprint data in the multiple fingerprint segments are spliced to obtain the video fingerprint of the video.

Further optionally, in the above implementation manner, if the number of fingerprint segments is inconsistent with the total number of fingerprint segments, and/or the positions of fingerprint segments in the plurality of fingerprint segments are duplicated, the number of fingerprint segments in the subsequent video frames of the video is extracted. Extracting at least one fingerprint segment, and reading the location of the fingerprint segment and the total number of fingerprint segments in the at least one fingerprint segment; then, identifying the multiple fingerprint segments and the at least one fingerprint segment in which the location of the fingerprint segment is not repeated. Whether the number is consistent with the total number of fingerprint segments; if the number of fingerprint segments with non-repetitive positions of the fingerprint segments is consistent with the total number of fingerprint segments, the fingerprint The fingerprint data included in each fingerprint segment in the fingerprint segments whose segment positions are not repeated are spliced to obtain the video fingerprint of the video. Otherwise, if the number of fingerprint segments whose positions are not repeated is inconsistent with the total number of fingerprint segments, continue to perform the extraction of at least one fingerprint segment from subsequent video frames of the video, and read the at least one fingerprint segment The operation of the fingerprint segment position in the fingerprint segment and the total number of fingerprint segments, until the number of fingerprint segments that do not repeat the fingerprint segment position is consistent with the total number of fingerprint segments, according to the fingerprint segment position of the fingerprint segment location is not repeated. The fingerprint data included in each fingerprint segment in the fingerprint segments whose positions of the fingerprint segments are not repeated are spliced to obtain the video fingerprint of the video.

Based on this embodiment, multiple fingerprint segments are added to the video cyclically. Even if a segment of the original video is intercepted by other users or the head and tail of the video are removed, the desired fingerprint can still be extracted from subsequent video frames. All the fingerprint segments included in a complete video fingerprint are obtained, so that a complete video fingerprint can be obtained by splicing, so as to realize the repetitive identification of the video.

Further optionally, in the above implementation manner, after reading the fingerprint segment positions and the total number of fingerprint segments in the plurality of fingerprint segments, it is also possible to identify whether the read fingerprint segment positions include preset fingerprint segment positions, The preset fingerprint segment position is used to indicate that the complete fingerprint includes complete video fingerprint data; if the read fingerprint segment position includes the preset fingerprint segment position, it is determined that the fingerprint segment including the preset fingerprint segment position is: Complete fingerprint, extract the fingerprint data in the complete fingerprint, and obtain the video fingerprint.

Based on this embodiment, when the read fingerprint segment position includes a preset fingerprint segment position, it can be determined that the fingerprint segment is a complete fingerprint, and the video fingerprint can be obtained by extracting the fingerprint data in the complete fingerprint. A complete fingerprint is added to the frame, so that it can avoid the damage of the fingerprint segment during the video transmission process, or the loss of intermediate frames when other users modify the video, which makes it impossible to obtain a complete video fingerprint. Based on the complete fingerprint, it can be implemented independently. Repetitive recognition of videos.

Obtaining a complete video fingerprint includes all fingerprint segments, so as to obtain a complete video fingerprint by splicing, so as to realize the repetitive identification of the video.

In the embodiment of the present application, there is no limit to the number of fingerprint segments that can be split by the video fingerprint, which can be determined according to the length of the video, the length of the video fingerprint, the frame rate of the video, etc. The video fingerprint may not be split, and it is understandable is split into 1 fingerprint segment, or into multiple video segments. Under normal circumstances, the refresh rate of the video is 30fps, and if each frame carries a fingerprint segment in a 1-second playback video frame, a video fingerprint can be divided into 30 video segments at most.

The technical solution of the present application can be applied to applications in devices such as terminals and video servers, for example, any video data processing applications and playback applications. When video data processing applications and playback applications are used to perform the video repeatability identification method provided by the embodiments of the present application, videos with repeated content can be identified based on the video fingerprint of each video; and, since the video fingerprint of a video is split Dividing into multiple fingerprint segments and adding them to different video frames of the video can avoid the subsequent playback of the video being affected due to the large amount of added data when a complete video fingerprint is added to each video frame.

In addition, since it is possible to identify whether there are videos with duplicate content based on video fingerprints, it is possible to avoid video platforms and self-media platforms from repeatedly recording videos with the same content, saving storage resources and maintenance resources.

In addition, since it can identify whether there is a video with duplicate content based on the video fingerprint, it can avoid recommending multiple videos with the same content to the user when recommending a video to the user, and avoid the user from repeatedly playing the video with the same content, which can effectively improve the user experience.

It should be noted that, for the sake of simple description, the foregoing method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence. Because in accordance with the present application, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Figure 7 shows a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present application. The computer system/server 12 shown in FIG. 7 is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

As shown in FIG. 7, computer system/server 12 takes the form of a general purpose computing device. Components of computer system/server 12 may include, but are not limited to, one or more processors or processing units 16, storage or system memory 28, and a bus 18 connecting various system components including system memory 28 and processing unit 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.

Computer system/server 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer system/server 12, including both volatile and non-volatile media, removable and non-removable media.

System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 . Computer system/server 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 7, commonly referred to as a "hard drive"). Although not shown in Figure 7, disk drives for reading and writing to removable non-volatile magnetic disks (eg "floppy disks") and removable non-volatile optical disks (eg CD-ROM, DVD-ROM) may be provided or other optical media) to read and write optical drives. In these cases, each drive may be connected to bus 18 through one or more data media interfaces. System memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present application.

A program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other Program modules and program data, each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.

The computer system/server 12 may also communicate with one or more external devices 14 (eg, keyboard, pointing device, display 24, etc.), and may also communicate with one or more devices that enable a user to interact with the computer system/server 12, and/or with any device (eg, network card, modem, etc.) that enables the computer system/server 12 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 44 . Also, the computer system/server 12 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 20 . As shown, network adapter 20 communicates with other modules of computer system/server 12 via bus 18 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with computer system/server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, Tape drives and data backup storage systems, etc.

The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28 , for example, implementing the video repetition identification method provided by any of the embodiments corresponding to FIG. 1 to FIG. 6 .

Another embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, realizes the video provided by any of the embodiments corresponding to FIG. 1 to FIG. 6 . Repetitive identification method.

In particular, any combination of one or more computer-readable media may be employed. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (a non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for performing the operations of the present application may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional Procedural programming language - such as "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to via Internet connection).

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or page components may be combined. Either it can be integrated into another system, or some features can be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software functional units.

The above-mentioned integrated units implemented in the form of software functional units can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute parts of the methods described in the various embodiments of the present application step. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions recorded in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (18)

1. a video repetitive identification method, is characterized in that, comprises: Generate a video fingerprint of the video based on the video identification information of the video, and the video identification information is used to uniquely identify the video; Splitting the video fingerprint to obtain a plurality of fingerprint segments; The plurality of fingerprint segments are correspondingly added to different video frames of the video. 2. The method according to claim 1, wherein the video identification information comprises any one or more of the following: The frame data within the preset playback time range at the beginning of the video or the frame data of the preset number of frames at the beginning of the video, the frame data within the preset playback time range at the end of the video, or the frame data at the end preset in the video The frame data of the frame number, the name of the video, the producer of the video, and the production date of the video. 3. The method according to claim 1, wherein the video fingerprint is split to obtain a plurality of fingerprint segments, comprising: Splitting the video fingerprint into multiple parts to obtain multiple fingerprint data; assigning a fingerprint segment position to the fingerprint data according to the positions of the plurality of fingerprint data in the video fingerprint; Respectively encapsulate each fingerprint data in the plurality of fingerprint data, the corresponding fingerprint segment position and the total number of fingerprint segments into a fingerprint segment to obtain a plurality of fingerprint segments; wherein, the fingerprint segment position is used to represent the corresponding fingerprint data In the position in the video fingerprint, the total number of fingerprint segments is used to represent the number of fingerprint data obtained by splitting the video fingerprint. 4. The method according to any one of claims 1 to 3, wherein after the obtaining of multiple fingerprint segments, the method further comprises: respectively performing alpha channel conversion on the multiple fingerprint segments, and converting the alpha channels of the multiple fingerprint segments into a transparent background color; The correspondingly adding the plurality of fingerprint segments to different video frames of the video includes: The plurality of fingerprint segments converted from the alpha channel are correspondingly added to the macroblocks that carry the skip running identifier in different video frames of the video. 5. The method according to any one of claims 1 to 3, wherein after the obtaining of the plurality of fingerprint segments, the method further comprises: respectively performing alpha channel conversion on each of the fingerprint segments in the plurality of fingerprint segments, and converting the alpha channel of each fingerprint segment into a transparent background color; A fingerprint macroblock is generated based on each fingerprint segment converted from the alpha channel, and a skip run mark is added in the fingerprint macroblock; The correspondingly adding the plurality of fingerprint segments to different video frames of the video includes: A plurality of fingerprint macroblocks added with skip running flags are correspondingly added to different video frames of the video. The method according to any one of claims 1 to 3, wherein the correspondingly adding the plurality of fingerprint segments to different video frames of the video comprises: adding the plurality of fingerprint segments sequentially to a plurality of consecutive different video frames; or, The plurality of fingerprint segments are randomly added to a plurality of different video frames. 7. The method according to any one of claims 1 to 3, wherein the correspondingly adding the plurality of fingerprint segments to different video frames of the video comprises: The multiple fingerprint segments are respectively added to different video segments of the video, and the multiple fingerprint segments are correspondingly added to different video frames in the video segments. 8. The method of claim 1, further comprising: Encapsulate the video fingerprint with the preset fingerprint segment position and the total number of fingerprint segments to obtain a complete fingerprint; wherein, the preset fingerprint segment location is used to indicate that the complete fingerprint includes complete video fingerprint data, and the total number of fingerprint segments is 1; The complete fingerprint is added to at least one video frame in the video to which the fingerprint segment is not added. 9. The method according to claim 8, wherein the encapsulating the video fingerprint with the preset fingerprint segment position and the total number of fingerprint segments to obtain a complete fingerprint, further comprising: Alpha channel conversion is performed on the complete fingerprint, and the alpha channel of the complete fingerprint is converted into a transparent background color; Generate a fingerprint macroblock based on the complete fingerprint converted from the alpha channel, and add a skip running flag to the fingerprint macroblock; The adding the complete fingerprint to at least one video frame in the video to which the fingerprint segment is not added includes: The fingerprint macroblocks to which the skip running identifier is added are respectively added to at least one video frame in the video to which the fingerprint segment is not added. 10. The method according to claim 8, wherein the encapsulating the video fingerprint with the preset fingerprint segment position and the total number of fingerprint segments to obtain a complete fingerprint, further comprising: Alpha channel conversion is performed on the complete fingerprint, and the alpha channel of the complete fingerprint is converted into a transparent background color; The adding the complete fingerprint to at least one video frame in the video to which the fingerprint segment is not added includes: The complete fingerprint converted from the alpha channel is added to a macroblock carrying a skip running flag in at least one video frame of the video to which the fingerprint segment is not added. 11. A method for video repeatability identification, characterized in that, comprising: Extracting fingerprint segments from multiple video frames of the video respectively to obtain multiple fingerprint segments; Splicing the extracted fingerprint segments to obtain a video fingerprint of the video; the video fingerprint is generated based on the video identification information of the video, and the video identification information is used to uniquely identify the video; Based on the video fingerprint, it is identified whether there are other videos that duplicate the content of the video. 12. The method according to claim 11, wherein the video identification information comprises any one or more of the following: The frame data within the preset playback time range at the beginning of the video or the frame data of the preset number of frames at the beginning of the video, the frame data within the preset playback time range at the end of the video, or the frame data at the end preset in the video The frame data of the frame number, the name of the video, the producer of the video, and the production date of the video. 13. The method according to claim 11, wherein the extracting fingerprint segments from multiple video frames of the video respectively comprises: Fingerprint segments are extracted from macroblocks carrying skip-run identifiers in multiple video frames, and the fingerprint segments are converted to a transparent background color via an alpha channel. 14. The method according to claim 13, wherein the fingerprint segment comprises: fingerprint segment position, total number of fingerprint segments and fingerprint data; wherein, the fingerprint segment location is used to indicate that the corresponding fingerprint data is in the video The position in the fingerprint, the total number of fingerprint segments is used to represent the number of fingerprint data obtained by splitting the video fingerprint; After the fingerprint segments are extracted from multiple video frames of the video respectively to obtain multiple fingerprint segments, the method further includes: Read the fingerprint segment positions and the total number of fingerprint segments in the plurality of fingerprint segments; Identify whether the number of fingerprint segments extracted from the plurality of fingerprint segments is consistent with the total number of fingerprint segments, and whether the positions of the fingerprint segments in the plurality of fingerprint segments are not repeated; The splicing of the extracted fingerprint segments to obtain the video fingerprint of the video, including: If the number of fingerprint segments is the same as the total number of fingerprint segments and the positions of the fingerprint segments in the plurality of fingerprint segments do not overlap, each of the The fingerprint data included in each fingerprint segment is spliced to obtain the video fingerprint of the video. 15. The method of claim 14, further comprising: If the number of fingerprint segments is inconsistent with the total number of fingerprint segments, and/or the positions of fingerprint segments in the plurality of fingerprint segments are repeated, extract at least one fingerprint segment from subsequent video frames of the video, and read the Fingerprint segment position and total number of fingerprint segments in at least one fingerprint segment; Identify whether the number of fingerprint segments in the plurality of fingerprint segments and the at least one fingerprint segment where the location of the fingerprint segment is not repeated is consistent with the total number of fingerprint segments; If the number of fingerprint segments with non-repeated fingerprint segment positions is consistent with the total number of fingerprint segments, each of the fingerprint segments with non-repetitive fingerprint segment positions is evaluated according to the fingerprint segment positions in the fingerprint segments with non-repetitive fingerprint segment positions. The fingerprint data included in the fingerprint segment is spliced to obtain the video fingerprint of the video; Otherwise, if the number of fingerprint segments whose positions are not repeated is inconsistent with the total number of fingerprint segments, continue to perform the extraction of at least one fingerprint segment from subsequent video frames of the video, and read the at least one fingerprint segment Operations on the fingerprint segment position and the total number of fingerprint segments. 16. The method according to claim 14 or 15, wherein after reading the fingerprint segment positions and the total number of fingerprint segments in the plurality of fingerprint segments, the method further comprises: Identifying whether the read fingerprint segment position includes a preset fingerprint segment position, and the preset fingerprint segment position is used to indicate that the complete fingerprint includes complete video fingerprint data; If the read fingerprint segment position includes a preset fingerprint segment position, the fingerprint segment including the preset fingerprint segment position is determined to be a complete fingerprint, and fingerprint data in the complete fingerprint is extracted to obtain the video fingerprint. 17. An electronic device, characterized in that the electronic device comprises: one or more processors; storage means for storing one or more programs, The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-16. 18. A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the method according to any one of claims 1 to 16 is implemented.

Images