[go: up one dir, main page]

WO2022105656A1 - Procédé, système et appareil de division de vidéo, et dispositif et support de stockage - Google Patents

Procédé, système et appareil de division de vidéo, et dispositif et support de stockage Download PDF

Info

Publication number
WO2022105656A1
WO2022105656A1 PCT/CN2021/129848 CN2021129848W WO2022105656A1 WO 2022105656 A1 WO2022105656 A1 WO 2022105656A1 CN 2021129848 W CN2021129848 W CN 2021129848W WO 2022105656 A1 WO2022105656 A1 WO 2022105656A1
Authority
WO
WIPO (PCT)
Prior art keywords
stripping
video
rule
strip
processed
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.)
Ceased
Application number
PCT/CN2021/129848
Other languages
English (en)
Chinese (zh)
Inventor
李梦晨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Kingsoft Cloud Network Technology Co Ltd
Original Assignee
Beijing Kingsoft Cloud Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Kingsoft Cloud Network Technology Co Ltd filed Critical Beijing Kingsoft Cloud Network Technology Co Ltd
Publication of WO2022105656A1 publication Critical patent/WO2022105656A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23424—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
    • 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

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to a video stripping method, system, apparatus, device and storage medium.
  • Video stripping refers to the secondary processing of videos, such as traditional TV media programs, due to the needs of Internet video and new media short video content platforms. multiple videos. Among them, the logical thinking or specific needs based on the splitting process can be understood as the splitting rules.
  • the user sends a Hyper Text Transfer Protocol (HTTP) request that includes a plurality of fields to the strip service, and the request includes the field corresponding to the identification information of the video to be processed sent by the strip service, and the strip scene.
  • HTTP Hyper Text Transfer Protocol
  • the stripping service parses the HTTP request, obtains the video to be processed according to the obtained identification information, and treats the to-be-processed video according to the stripping rule corresponding to the stripping scene.
  • Process video for stripping is
  • the purpose of the embodiments of the present application is to provide a video stripping method, system, device, device, and storage medium, so as to configure the stripping rules more flexibly and make the stripping process simpler.
  • the specific technical solutions are as follows:
  • an embodiment of the present application provides a video stripping method, which is applied to a stripping service, including: acquiring stripping rules configured by a user through a stripping platform; stripping a video to be processed according to the stripping rules, The split video corresponding to the to-be-processed video is obtained.
  • the method before the to-be-processed video is split according to the split rule to obtain a split video corresponding to the to-be-processed video, the method further includes: acquiring a video split request, the The video splitting request carries the identification information of the to-be-processed video; the to-be-processed video is acquired according to the identification information.
  • the acquiring the stripping rule configured by the user through the stripping platform includes: acquiring stripping rule parameters configured by the user based on configuration rule information, and combining the configuration rule information and the stripping rule
  • the rule parameter is used as the stripping rule
  • the configuration rule information is configuration rule information corresponding to different stripping scenarios included in the stripping rule configuration page provided by the stripping platform.
  • the video splitting request further includes a scene to be split;
  • the splitting the to-be-processed video according to the splitting rule to obtain the splitting video corresponding to the to-be-processed video includes:
  • the to-be-processed video is subjected to frame extraction processing to obtain multiple video frames; a preset algorithm model corresponding to the to-be-split scene is determined; the multiple video frames are respectively identified by using the preset algorithm model, and the meeting is obtained.
  • the video frame of the scene to be split; the video frames that satisfy the scene to be split are synthesized according to the split rule to obtain the split video that satisfies the split rule.
  • the method further includes: storing the split video The address is fed back to the client where the user is located, so that the user obtains the split video by using the storage address.
  • an embodiment of the present application provides a video stripping method, which is applied to a stripping platform, including: providing a stripping rule configuration page; receiving stripping rules configured by a user on the stripping rule configuration page, to The splitting service is enabled to split the video to be processed based on the splitting rule to obtain a splitting video corresponding to the video to be processed.
  • the stripping rule configuration page includes configuration rule information corresponding to different stripping scenarios; the receiving a stripping rule configured by a user on the stripping rule configuration page includes: receiving the user A strip rule parameter configured based on the configuration rule information, and the configuration rule information and the strip strip rule parameter are used as the strip strip rule.
  • the method further includes: providing a split log page, where the split log page is used to display split log information.
  • the method further includes: providing a data statistics page, where the data statistics page is used to display data statistics results.
  • the method further includes: providing a face sample library adding page, where the face sample library adding page is used to add matched face samples in the stripping process.
  • an embodiment of the present application provides a video stripping system, including: a stripping platform, configured to receive stripping rules configured by a user through the stripping platform; stripping services, configured to obtain the stripping platform rule; splitting the video to be processed according to the splitting rule to obtain the splitting video corresponding to the video to be processed.
  • the strip stripping platform is configured to provide strip stripping rule configuration page; and receive strip stripping rules configured by the user on the strip stripping rule configuration page.
  • the stripping service is an application program interface API.
  • the embodiments of the present application provide a video stripping device, which is applied to stripping services, including: a first acquisition module, configured to acquire stripping rules configured by a user through a stripping platform; stripping module, set to Split the video to be processed according to the split rule to obtain the split video corresponding to the video to be processed.
  • the apparatus further includes: a second acquisition module, configured to acquire the split video corresponding to the to-be-processed video by splitting the to-be-processed video according to the split rule to obtain the split video corresponding to the to-be-processed video
  • a second acquisition module configured to acquire the split video corresponding to the to-be-processed video by splitting the to-be-processed video according to the split rule to obtain the split video corresponding to the to-be-processed video
  • a video stripping request where the video stripping request carries the identification information of the to-be-processed video; the to-be-processed video is acquired according to the identification information.
  • the first obtaining module is configured to obtain the strip-breaking rule parameters configured by the user based on configuration rule information, and use the configuration rule information and the strip-breaking rule parameters as the strip-breaking rule parameters rule, and the configuration rule information is configuration rule information corresponding to different strip strip scenarios included in the strip strip rule configuration page provided by the strip strip platform.
  • the video stripping request further includes a scene to be stripped;
  • the stripping module is configured to perform frame extraction processing on the to-be-processed video to obtain multiple video frames; determine the to-be-removed video frame The preset algorithm model corresponding to the scene; using the preset algorithm model to identify the plurality of video frames respectively, to obtain the video frame that satisfies the scene to be split; according to the split rule to meet the to-be split
  • the video frames of the scene are synthesized to obtain the split video that satisfies the split rule.
  • the apparatus further includes: a feedback module, configured to split the video to be processed according to the split rule to obtain the split video corresponding to the video to be processed, and then split the video to be processed.
  • the storage address of the split video is fed back to the client where the user is located, so that the user can obtain the split video by using the storage address.
  • the embodiments of the present application provide a video stripping device, which is applied to a stripping platform, including: a first providing module configured to provide a stripping rule configuration page; a receiving module configured to receive user The splitting rule configured on the rule configuration page, so that the splitting service splits the video to be processed based on the splitting rule, and obtains the splitting video corresponding to the to-be-processed video.
  • the stripping rule configuration page includes configuration rule information corresponding to different stripping scenarios; the receiving module is configured to receive stripping rule parameters configured by the user based on the configuration rule information, and The configuration rule information and the stripping rule parameter are used as the stripping rule.
  • the apparatus further includes: a second providing module configured to provide a strip log page, where the strip log page is used to display strip log information.
  • the apparatus further includes: a third providing module configured to provide a data statistics page, where the data statistics page is used to display data statistics results.
  • the apparatus further includes: a fourth providing module, configured to provide a face sample library adding page, where the face sample library adding page is used to add matched face samples in the stripping process.
  • the application embodiment provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory , which is set to store the computer program; the processor is set to implement the method steps described in the first aspect when executing the program stored in the memory.
  • the application embodiment provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory , which is set to store the computer program; the processor is set to implement the method steps described in the second aspect when the processor is set to execute the program stored in the memory.
  • the embodiments of the present application provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program implements the first aspect when executed by a processor. method steps.
  • the embodiments of the present application provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program implements the second aspect when executed by a processor. method steps.
  • FIG. 1 is a schematic flowchart of a video stripping method applied to a stripping service provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a video stripping method applied to a stripping platform provided by an embodiment of the present application
  • FIG. 3 is a schematic diagram of a strip rule configuration page in an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of a strip strip process based on strip strip rules in an embodiment of the present application
  • FIG. 5 is a schematic diagram of an intelligent strip strip operation platform in an embodiment of the application.
  • FIG. 6 is a schematic structural diagram of a video stripping system provided by an embodiment of the present application.
  • FIG. 7A is a schematic structural diagram of a video stripping device applied to a stripping service provided by an embodiment of the present application
  • FIG. 7B is another schematic structural diagram of a video stripping device applied to a stripping service provided by an embodiment of the present application.
  • FIG. 7C is a schematic structural diagram of a video stripping device applied to a stripping service provided by an embodiment of the present application.
  • 8A is another schematic structural diagram of a video stripping device applied to a stripping platform provided by an embodiment of the present application.
  • 8B is another schematic structural diagram of a video stripping device applied to a stripping platform provided by an embodiment of the present application.
  • 8C is another schematic structural diagram of a video stripping device applied to a stripping platform provided by an embodiment of the present application.
  • 8D is another schematic structural diagram of a video stripping device applied to a stripping platform provided by an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of an electronic device applied to a stripping service provided by an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an electronic device applied to a stripping platform according to an embodiment of the present application.
  • the embodiment of the present application provides a video stripping method, which is applied to stripping services. As shown in FIG. 1 , it may include:
  • splitting the video to be processed according to the splitting rule to obtain a split video corresponding to the video to be processed.
  • the user can configure the stripping rules through the stripping platform, instead of writing the fields corresponding to the stripping rules for different stripping scenarios when configuring the stripping rules, but directly using the configuration page to generate the stripping rules, like this This will make the configuration process of the strip rule more flexible and the strip strip process easier.
  • operators and others can configure the stripping rules through the stripping platform by themselves, without the need for operators to notify the technical R&D personnel of the stripping requirements, and then the technical R&D personnel will carry the identification information of the video to be processed in the stripping requirements, the stripping scene and the corresponding information.
  • the request for the corresponding fields of the stripping rules and other information is sent to the stripping service to complete the process of video stripping, which makes the video stripping process simpler and more flexible.
  • the embodiment of the present application also provides a video stripping method, which is applied to the stripping platform, as shown in FIG. 2 , including:
  • S202 Receive the stripping rule configured by the user on the stripping rule configuration page, so that the stripping service strips the video to be processed based on the stripping rule, and obtains the stripping video corresponding to the to-be-processed video.
  • the user can configure the stripping rules through the stripping platform, instead of writing the fields corresponding to the stripping rule source code for different stripping scenarios when configuring stripping rules, but directly using the configuration page to generate stripping rules , which will make the configuration process of the strip rule more flexible and the strip strip process easier.
  • operators and others can configure the stripping rules through the stripping platform by themselves, without the need for operators to notify the technical R&D personnel of the stripping requirements, and then the technical R&D personnel will carry the identification information of the video to be processed in the stripping requirements, the stripping scene and the corresponding information.
  • the request for the corresponding fields of the stripping rules and other information is sent to the stripping service to complete the process of video stripping, which makes the video stripping process simpler and more flexible.
  • the stripping service acquires stripping rules configured by a user through a stripping platform.
  • the stripping platform can be a visualization platform.
  • the stripping rule is the rule based on the process of stripping the video to be processed, which may include logical thinking or specific needs, for example, adding a face sample set to be stripped, and modifying the appearance of characters within a specified time. time percentage, etc.
  • the rule of dismantling can be a new face sample set of Actor A and Actor B, and set Actor A within 5 minutes.
  • the ratio of the appearance time of actor B is 3 to 2, then according to the stripping rule, a 5-minute strip video can be obtained, in which actor A appears for 3 minutes and actor B appears for 2 minutes.
  • the stripping platform can provide a stripping rule configuration page; the user configures through the stripping rule configuration page, such as inputting various parameters related to stripping, and the stripping platform can receive the user's configuration on the stripping rule configuration page.
  • Each parameter generates a strip rule. For example, as shown in Figure 3, enter the parameter 180 in the input box corresponding to the shortest strip duration, and the generated strip strip rule is the shortest strip strip duration of 180 seconds; in this way, the strip strip service is based on strip stripping.
  • the rule splits the video to be processed to obtain the split video corresponding to the video to be processed.
  • the strip rule configuration page may include configuration rule information corresponding to different strip strip scenarios.
  • the configuration rule information can also be understood as a rule template abstracted from the strip strip rules of different strip strip scenarios. Based on the rule template, the user can directly set corresponding parameters in the rule template, that is, configure strip strip rule parameters.
  • the stripping rules of each stripping scenario can be abstracted. For example, as shown in FIG. 3 , it can be abstracted into multiple information parts that require user parameters, so as to obtain configuration rule information corresponding to different stripping scenarios.
  • the rule configuration page is provided to the user; the user can configure it based on the rule configuration page. During the configuration process, you can directly enter the strip rule parameters that meet the strip strip requirements on the strip strip rule configuration page.
  • Stripping scenarios can be determined according to different business needs. For example, a "just look at him/her" scene, a “boxing KO scene”, a “boxing consecutive hits” scene, and the like may be included.
  • S202 Receive strip strip rules configured by the user on the strip strip rule configuration page, which may include:
  • the dismantling rule configuration page may include a “just look at him/her” scene, a “knock out KO (Knock Out, knockout opponent wins) scene”, and a “boxing continuous blow” Configuration rule information corresponding to the scene.
  • the strip rule configuration page may include configuration rule information corresponding to the "just look at him/her" scenario: the shortest strip duration, the longest strip duration, and the proportion of the characters/specific scenes appearing.
  • the configuration rule information corresponding to the "Just look at him/her” scene for example, the shortest time interval, the longest time interval, the proportion of characters/specific scenes, and so on.
  • the dots can be understood as marking the time stamp from the start time of the original video between the video frame containing the specified face specified by the "just look at him/her” scene, and so on.
  • the dismantling rule configuration page may include configuration rule information corresponding to the "boxing KO scene", such as: KO pre-duration, KO post-duration. It may include configuration rule information corresponding to the "boxing continuous hitting” scenario, such as: the shortest continuous hitting duration, the continuous hitting pre-positioning time, and the continuous hitting post-positioning period.
  • the user can configure based on the configuration rule information on the strip rule configuration page, and the user only needs to configure the corresponding parameters at the corresponding options, and the configuration is flexible. For example, if the requirement for stripping and renewing is for the "only look at him/her" scenario, then only the configuration rule information corresponding to the "only look at him/her" scenario needs to configure the shortest stripping duration, longest stripping duration, character/specific
  • the duration of scene appearance accounts for the corresponding parameters; for example, the shortest splitting duration is 180 seconds, the longest splitting duration is 800 seconds, and the proportion of characters/specific scenes appearing in every 60 seconds is not less than 70%.
  • the strip stripping rules of each strip stripping scenario can be abstracted, visualized on the platform side, and can be deployed by customers according to business requirements.
  • S101 may include: acquiring the stripping rule parameters configured by the user based on the configuration rule information, and using the configuration rule information and the stripping rule parameters as the stripping rule.
  • the configuration rule information is configuration rule information corresponding to different strip strip scenarios included in the strip strip rule configuration page provided by the strip strip platform.
  • S101 may include: determining the strip rule configuration information corresponding to the strip strip scene according to the strip strip scene; acquiring strip strip rule parameters configured by the user based on the strip strip rule configuration information; The strip rule parameter is used as strip rule.
  • strip rule parameters configured by the user on the strip rule configuration page based on the configuration rule information, and use strip strip rule configuration information and strip strip rule parameters as strip strip rules.
  • the splitting service splits the video to be processed according to the splitting rule, and obtains the splitting video corresponding to the video to be processed.
  • the video to be processed needs to be obtained first, and the above method may further include: obtaining a video split request, The video splitting request carries the identification information of the video to be processed; the to-be-processed video is obtained according to the identification information.
  • the video frame can be identified by an artificial intelligence (AI) algorithm, and a video frame that satisfies the stripping rule is selected from multiple video frames, and the video frame that satisfies the stripping rule can constitute a stripping video.
  • AI artificial intelligence
  • the video stripping request further includes a scene to be stripped.
  • S102 may include:
  • the frame extraction method of the video refer to the frame extraction method in the related art.
  • one frame of video frame is extracted every certain number of frames; for example, each key frame of the video to be processed is extracted; for example, one can calculate The Euclidean distance of two adjacent video frames in the video to be processed. When the Euclidean distance is greater than the preset distance threshold, one frame of video frame is extracted.
  • S1022 Determine a preset algorithm model corresponding to the scene to be stripped.
  • the acquired video stripping request may further include the scene to be stripped. It can parse the to-be-split scene included in the video split request.
  • the preset algorithm model corresponding to the scene to be stripped can be obtained according to the pre-established corresponding relationship between different strip-splitting scenarios and different algorithm models.
  • the video frame can be identified by invoking the corresponding preset algorithm model.
  • the preset algorithm model may include face recognition and/or specific scene recognition, and so on. Among them, face recognition is to identify whether there is a face in an image through an AI algorithm.
  • the specific scene recognition is to identify whether the image content is a scene specified by the customer through the AI algorithm.
  • a pre-trained deep learning model can be used to perform face or scene recognition on an image. Taking scene recognition as an example, a sample image marked with a scene can be input into a deep learning model for training, thereby obtaining a pre-trained deep learning model; when performing scene recognition, the image to be recognized is input into the deep learning model, The deep learning model automatically outputs the scene for that image.
  • the related model training technology which is not specifically limited in this application.
  • the stripping rule includes: the shortest stripping time is 180 seconds, the longest stripping time is 800 seconds, and the proportion of characters/specific scenes in every 60 seconds is not less than 70%, then according to the stripping rule, S1023 Synthesize the video frames that meet the scene to be split, and obtain a short video that meets the rules for splitting, the real-time length is between 180 seconds and 800 seconds, and the proportion of characters/specific scenes appearing in every 60 seconds is not large. Below 70% split video.
  • the process of stripping the video to be processed can be completed. Because the user can configure the stripping rules through the stripping platform, there is no need to write the fields corresponding to the stripping rules for different stripping scenarios when configuring stripping rules. This will make the configuration process of stripping rules more flexible and the stripping process easier. .
  • the stripping video can be fed back to the user.
  • the split video can be directly sent to the user, and the user saves the split video locally on the client where the user is located, so that the user can directly process the split video saved locally on the client when the split video is required. .
  • the split video may also be saved in other devices other than the local client where the user is located, such as a third-party device, a cloud device, and the like.
  • the storage address of the splitting video can be fed back to the client where the user is located, so that the user can obtain the splitting video using the storage address.
  • the strip stripping rules of each strip stripping scenario can be abstracted, visualized on the platform side, and support customers to deploy according to business requirements.
  • the user can configure the stripping rules through the stripping platform, and there is no need to write the fields corresponding to the stripping rules for different stripping scenarios when configuring the stripping rules. This will make the configuration process of the stripping rules more flexible and the stripping process easier.
  • operators and others can directly configure the stripping rules through the stripping platform, without the need for operators to notify the technical R&D personnel of the stripping requirements, and then the technical R&D personnel will carry the identification information of the video to be processed in the stripping requirements, the stripping scene and the corresponding information.
  • the request for the corresponding field of the stripping rule and other information is sent to the stripping service to complete the process of video stripping, which makes the video stripping process simpler and more flexible.
  • the stripping platform may further provide a stripping log page, and the stripping log page is used to display stripping log information.
  • the split log page can display the log list, and the split log in the log list can correspond to the log details.
  • the log list can display the splitting videos generated by splitting logs in reverse order of generation time, such as 30 records per page; and can provide a query function, which can support fuzzy query of video name or person name, It supports querying logs according to the scene type of strips, supports querying according to date, and so on.
  • the log details corresponding to each stripped log may include a short video that can be played, that is, the stripped video; the name of the original video; the unique identifier of the original video, where the original video is the pending video corresponding to the stripped video; The storage address of the short video of the strip, that is, the storage address of the strip video; the log strip scene.
  • the stripping platform may further provide a data statistics page, and the data statistics page is used to display the data statistics results.
  • the data statistics result may include data corresponding to all the strip splitting scenarios in the preset time range. It can be displayed according to the date dimension.
  • the video information identified in different time ranges can be displayed according to the time series, the video information can be split, and so on.
  • the time range can be the current day, or one or more days in history.
  • the display style for displaying the statistical results of the data may be displayed in the form of a data report.
  • the identified video information may be information related to videos that have been split and completed, such as the number of identified videos, video IDs, and the like.
  • the split video information may include information related to the split video, such as the video quantity of the split video, and so on.
  • the stripping platform may further provide a face sample library adding page, and the face sample library adding page is used to add matching face samples in the stripping process.
  • the face sample library add page can display the face samples that have been stored in the library by category, support query by name, and support face sample upload function, etc.
  • the face sample library add page supports the upload function of face samples. Users can add face samples through the face sample library add page. For example, if a user wants to watch actor A's split video, he can add face samples through the face sample library add page. A sample face of actor A.
  • the face sample library adding page can display the face samples that have been stored in the database by category. For example, the face samples stored in the database can be classified according to the categories of movie actors, TV actors, and variety actors. When selecting a face sample, the category to which the face sample belongs can be uploaded at the same time. In addition, when uploading an actor's face sample, the user can also upload the name of the corresponding actor, and can query the face sample by the actor's name through the face sample library add page.
  • the stripping platform may be understood as an intelligent stripping operation platform.
  • the intelligent strip operation platform may include: login interface, user information, data statistics, strip strip logs, face sample library, options corresponding to rule configuration and system configuration respectively.
  • the corresponding data statistics page is used to display the data statistics results.
  • the strip rule configuration page corresponding to the rule configuration is used to support the configuration of strip strip rules for each strip scene.
  • the split log page corresponding to the split log, and the face sample library add page corresponding to the face sample library.
  • the stripping rule configuration page, the data statistics page, the stripping log page, and the face sample library adding page have been described in detail in the above embodiment, and will not be repeated here.
  • the intelligent strip strip operation platform provides a login interface, based on which the user can input user information to log in to the intelligent strip strip operation platform, such as user name and password.
  • the user name can be echoed when the user logs in, and the options of "change password” and "log out” can be displayed by clicking the display drop-down form.
  • users can perform operations based on the intelligent strip strip operation platform, such as configuring strip strip rules, query strip strip logs, data statistics results, and adding face samples, etc.
  • the system configuration in the embodiment of the present application may correspondingly provide two pages of user management and role management.
  • the page corresponding to user management can support users to choose different roles to log in.
  • the page corresponding to role management can support users to set roles corresponding to their user information, etc.
  • Roles can include super administrator, administrator, operation, and different permissions can be set for different roles, that is, different roles are used for the intelligent strip operation platform. have different permissions.
  • the embodiment of the present application also provides a video stripping system, as shown in FIG. 6 , which may include:
  • the stripping platform 601 is configured to receive stripping rules configured by the user through the stripping platform 601 .
  • the stripping service 602 is configured to obtain stripping rules; stripping the video to be processed according to the stripping rules, to obtain a stripping video corresponding to the to-be-processed video.
  • the stripping platform 601 is configured to provide a stripping rule configuration page; and receive stripping rules configured by a user on the stripping rule configuration page.
  • the stripping service 602 is an application programming interface (Application Programming Interface, API).
  • the stripping service 602 and the stripping platform 601 may be deployed on one device, or may be deployed on different devices respectively.
  • the stripping service 602 can be packaged as an API.
  • the stripping platform 601 can implement the stripping service process by calling an API.
  • the video stripping system provided by the embodiment of the present application is a system corresponding to the video stripping method in the above-mentioned embodiments, and all embodiments of the above-mentioned video stripping method are applicable to the device, and can achieve the same or similar beneficial effects.
  • the embodiment of the present application provides a video stripping device, which is applied to the stripping service. As shown in FIG. 7A , it may include:
  • the first obtaining module 701 is configured to obtain the stripping rules configured by the user through the stripping platform.
  • the splitting module 702 is configured to split the video to be processed according to the splitting rule, and obtain the splitting video corresponding to the video to be processed.
  • the apparatus further includes: a second obtaining module 703, configured to obtain a split video corresponding to the to-be-processed video before splitting the to-be-processed video according to the splitting rule.
  • a video stripping request carries the identification information of the video to be processed; the to-be-processed video is obtained according to the identification information.
  • the first acquisition module 701 is configured to acquire the stripping rule parameters configured by the user based on the configuration rule information, and use the configuration rule information and stripping rule parameters as stripping rules, and the configuration rule information is the stripping platform The configuration rule information corresponding to different strip strip scenarios included in the provided strip strip rule configuration page.
  • the video stripping request further includes the scene to be stripped; the stripping module 702 is configured to perform frame extraction processing on the video to be processed to obtain a plurality of video frames; and determine the preset algorithm model corresponding to the to-be stripped scene ; Identify multiple video frames by using a preset algorithm model to obtain a video frame that satisfies the scene to be split; Combine the video frames that meet the scene to be split according to the split rule to obtain a split video that satisfies the split rule .
  • the apparatus further includes: a feedback module 704, configured to split the video to be processed according to the splitting rule to obtain the split video corresponding to the video to be processed, and then split the split video.
  • the storage address of the video is fed back to the client where the user is located, so that the user can obtain the split video by using the storage address.
  • the video stripping device applied to the stripping service provided by the embodiment of the present application is the device of the above-mentioned video stripping method applied to the stripping service, and all the above-mentioned embodiments of the video stripping method applied to the stripping service are applicable to The device can achieve the same or similar beneficial effects.
  • the embodiment of the present application provides a video stripping device, which is applied to the stripping platform. As shown in FIG. 8A , it may include:
  • the first providing module 801 is configured to provide a stripping rule configuration page; the receiving module 802 is set to receive stripping rules configured by the user on the stripping rule configuration page, so that the stripping service can deconstruct the video to be processed based on the stripping rules. bar to obtain the split video corresponding to the video to be processed.
  • the stripping rule configuration page includes configuration rule information corresponding to different stripping scenarios; the receiving module 802 is configured to receive the stripping rule parameters configured by the user based on the configuration rule information, and send the configuration rule information and stripping rule information to the stripping rule.
  • the rule parameter is used as a stripping rule.
  • the apparatus further includes: a second providing module 803 configured to provide a strip log page, where the strip log page is used to display strip log information.
  • the apparatus further includes: a third providing module 804 configured to provide a data statistics page, where the data statistics page is used to display data statistics results.
  • the apparatus further includes: a fourth providing module 805, configured to provide a face sample library adding page, and the face sample library adding page is used to add people matched in the stripping process face sample.
  • the video stripping device applied to the stripping platform provided by the embodiment of the present application is the device for the above-mentioned video stripping method applied to the stripping platform, and all the above-mentioned embodiments of the video stripping method applied to the stripping platform are applicable to The device can achieve the same or similar beneficial effects.
  • the embodiment of the present application provides an electronic device, as shown in FIG. 9 , including a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein, The processor 901, the communication interface 902, and the memory 903 complete the mutual communication through the communication bus 904; the memory 903 is set to store computer programs; The method steps of the video stripping method of the strip service.
  • the embodiment of the present application provides an electronic device, as shown in FIG. 10 , including a processor 1001, a communication interface 1002, a memory 1003 and a communication bus 1004, wherein The processor 1001, the communication interface 1002, and the memory 1003 complete the mutual communication through the communication bus 904; the memory 1003 is set to store computer programs; The method steps of the video stripping method of the strip platform.
  • the communication bus mentioned in the above electronic device may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like.
  • PCI peripheral component interconnect standard
  • EISA Extended Industry Standard Architecture
  • the communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used for communication between the above electronic device and other devices.
  • the memory may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk storage.
  • RAM Random Access Memory
  • NVM non-Volatile Memory
  • the memory may also be at least one storage device located remotely from the aforementioned processor.
  • the above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processing, DSP), dedicated integrated Circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processing
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • FPGA Field-Programmable Gate Array
  • a computer-readable storage medium is also provided, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned application to the stripping service is implemented The method steps of the video stripping method.
  • a computer-readable storage medium is also provided, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned application to the stripping platform is implemented The method steps of the video stripping method.
  • a computer program product including instructions is also provided, which, when running on a computer, causes the computer to execute the method steps of implementing the above-mentioned video stripping method applied to stripping service.
  • a computer program product including instructions is also provided, which, when running on a computer, causes the computer to execute the method steps of implementing the above-mentioned video stripping method applied to a stripping platform.
  • the collection, storage, use, processing, transmission, provision and disclosure of the user's personal information involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.
  • the face sample in this embodiment is not a human head model for a specific user, and cannot reflect the personal information of a specific user.
  • the face images in this embodiment come from public datasets.
  • the above-mentioned embodiments it may be implemented in whole or in part by software, hardware, firmware or any combination thereof.
  • software it can be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server, or data center is by wire (eg, coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes an integration of one or more available media.
  • the usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)), and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Library & Information Science (AREA)
  • Software Systems (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

L'invention concerne un procédé, un système et un appareil de division de vidéo, ainsi qu'un dispositif et un support de stockage qui se rapportent au domaine technique de l'Internet. Le procédé comprend les étapes suivantes : un service de division acquiert une règle de division qui est configurée par un utilisateur au moyen d'une plateforme de division ; et diviser, selon la règle de division, une vidéo à traiter afin d'obtenir une vidéo divisée correspondant à ladite vidéo. Le procédé, le système et l'appareil de division de vidéo, ainsi que le dispositif et le support de stockage fournis dans les modes de réalisation de la présente invention permettent de configurer une règle de division de manière plus flexible, de façon à rendre le processus de division plus simple et plus pratique.
PCT/CN2021/129848 2020-11-17 2021-11-10 Procédé, système et appareil de division de vidéo, et dispositif et support de stockage Ceased WO2022105656A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011286764.3 2020-11-17
CN202011286764.3A CN112423151A (zh) 2020-11-17 2020-11-17 一种视频拆条方法、系统、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022105656A1 true WO2022105656A1 (fr) 2022-05-27

Family

ID=74830942

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/129848 Ceased WO2022105656A1 (fr) 2020-11-17 2021-11-10 Procédé, système et appareil de division de vidéo, et dispositif et support de stockage

Country Status (2)

Country Link
CN (1) CN112423151A (fr)
WO (1) WO2022105656A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115766977A (zh) * 2022-11-10 2023-03-07 北京百度网讯科技有限公司 视频处理方法、装置、设备及存储介质
CN116939291A (zh) * 2023-09-13 2023-10-24 浙江新华移动传媒股份有限公司 一种视频快速拆条方法及相关装置
CN117274856A (zh) * 2023-08-23 2023-12-22 杭州当虹科技股份有限公司 基于ai统计的新闻拆条方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112423151A (zh) * 2020-11-17 2021-02-26 北京金山云网络技术有限公司 一种视频拆条方法、系统、装置、设备及存储介质
CN116980644A (zh) * 2022-04-13 2023-10-31 华为云计算技术有限公司 一种视频处理方法、系统及相关设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109246441A (zh) * 2018-09-30 2019-01-18 武汉斗鱼网络科技有限公司 精彩时刻视频自动生成方法、存储介质、设备及系统
CN109565621A (zh) * 2016-08-01 2019-04-02 微软技术许可有限责任公司 视频管理系统中的视频分段
US20190281350A1 (en) * 2018-03-06 2019-09-12 Shoppar, Ltd. System and method for content delivery optimization based on a combined captured facial landmarks and external datasets
CN110659616A (zh) * 2019-09-26 2020-01-07 新华智云科技有限公司 一种从视频自动生成gif的方法
CN111654669A (zh) * 2020-05-26 2020-09-11 号百控股股份有限公司 一种基于视频结构化分析处理的视频拆条系统框架及方法
CN112423151A (zh) * 2020-11-17 2021-02-26 北京金山云网络技术有限公司 一种视频拆条方法、系统、装置、设备及存储介质
CN113542909A (zh) * 2020-04-21 2021-10-22 阿里巴巴集团控股有限公司 视频处理方法、装置、电子设备及计算机存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110166828A (zh) * 2019-02-19 2019-08-23 腾讯科技（深圳）有限公司 一种视频处理方法和装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109565621A (zh) * 2016-08-01 2019-04-02 微软技术许可有限责任公司 视频管理系统中的视频分段
US20190281350A1 (en) * 2018-03-06 2019-09-12 Shoppar, Ltd. System and method for content delivery optimization based on a combined captured facial landmarks and external datasets
CN109246441A (zh) * 2018-09-30 2019-01-18 武汉斗鱼网络科技有限公司 精彩时刻视频自动生成方法、存储介质、设备及系统
CN110659616A (zh) * 2019-09-26 2020-01-07 新华智云科技有限公司 一种从视频自动生成gif的方法
CN113542909A (zh) * 2020-04-21 2021-10-22 阿里巴巴集团控股有限公司 视频处理方法、装置、电子设备及计算机存储介质
CN111654669A (zh) * 2020-05-26 2020-09-11 号百控股股份有限公司 一种基于视频结构化分析处理的视频拆条系统框架及方法
CN112423151A (zh) * 2020-11-17 2021-02-26 北京金山云网络技术有限公司 一种视频拆条方法、系统、装置、设备及存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115766977A (zh) * 2022-11-10 2023-03-07 北京百度网讯科技有限公司 视频处理方法、装置、设备及存储介质
CN117274856A (zh) * 2023-08-23 2023-12-22 杭州当虹科技股份有限公司 基于ai统计的新闻拆条方法
CN116939291A (zh) * 2023-09-13 2023-10-24 浙江新华移动传媒股份有限公司 一种视频快速拆条方法及相关装置
CN116939291B (zh) * 2023-09-13 2023-11-28 浙江新华移动传媒股份有限公司 一种视频快速拆条方法及相关装置

Also Published As

Publication number Publication date
CN112423151A (zh) 2021-02-26

Similar Documents

Publication Publication Date Title
WO2022105656A1 (fr) Procédé, système et appareil de division de vidéo, et dispositif et support de stockage
US10613719B2 (en) Generating a form response interface in an online application
US20140095308A1 (en) Advertisement distribution apparatus and advertisement distribution method
US11115531B1 (en) Systems and methods for identifying a behavioral target during a conversation
US20210035025A1 (en) Systems and methods for optimizing machine learning models by summarizing list characteristics based on multi-dimensional feature vectors
JP2022538702A (ja) 音声パケット推薦方法、装置、電子機器およびプログラム
US20240184865A1 (en) Systems and methods for providing user validation
US10970485B1 (en) Systems and methods for selecting effective phrases to be presented during a conversation
CN109829064B (zh) 媒体资源分享及播放方法和装置、存储介质及电子装置
US20150287069A1 (en) Personal digital engine for user empowerment and method to operate the same
CN104866275B (zh) 一种用于获取图像信息的方法和装置
CN108197336B (zh) 一种视频查找的方法及装置
CN107977678A (zh) 用于输出信息的方法和装置
EP3923157A1 (fr) Traitement de flux de données
US11120812B1 (en) Application of machine learning techniques to select voice transformations
CN109451333A (zh) 一种弹幕显示方法、装置、终端及系统
CN112035727A (zh) 信息获取方法、装置、设备、系统及可读存储介质
CN108924598A (zh) 视频字幕显示方法及装置
CN110727782A (zh) 问答语料生成方法及系统
US11057332B2 (en) Augmented expression sticker control and management
CN112836767A (zh) 联邦建模方法、装置、设备、存储介质及程序产品
KR102197739B1 (ko) 연기자 정보 제공 방법
CN110209780B (zh) 一种问题模板生成方法、装置、服务器及存储介质
WO2020181783A1 (fr) Procédé et dispositif d'envoi d'informations
JP7430302B1 (ja) ページ生成装置、ウェブページの生産方法、およびプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21893803

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21893803

Country of ref document: EP

Kind code of ref document: A1