WO2023142913A1 - 视频处理方法、装置、可读介质及电子设备 - Google Patents

视频处理方法、装置、可读介质及电子设备 Download PDF

Info

Publication number
WO2023142913A1
WO2023142913A1 PCT/CN2023/070262 CN2023070262W WO2023142913A1 WO 2023142913 A1 WO2023142913 A1 WO 2023142913A1 CN 2023070262 W CN2023070262 W CN 2023070262W WO 2023142913 A1 WO2023142913 A1 WO 2023142913A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
processed
segment
audio
information
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/CN2023/070262
Other languages
English (en)
French (fr)
Inventor
孙佳
袁泽寰
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 Youzhuju Network Technology Co Ltd
Original Assignee
Beijing Youzhuju 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 Youzhuju Network Technology Co Ltd filed Critical Beijing Youzhuju Network Technology Co Ltd
Priority to US18/832,049 priority Critical patent/US20250118338A1/en
Publication of WO2023142913A1 publication Critical patent/WO2023142913A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
    • G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals
    • G11B27/036—Insert-editing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/19007—Matching; Proximity measures
    • G06V30/19093—Proximity measures, i.e. similarity or distance measures

Definitions

  • the present disclosure relates to the field of computer technology, and in particular, to a video processing method, device, readable medium, and electronic equipment.
  • the present disclosure provides a video processing method, the method comprising:
  • the target video segment Adding the target video segment to the position before the specified video frame in the video to be processed to obtain the target video, the specified video frame being any video frame in the previous preset number of video frames in the video to be processed .
  • the present disclosure provides a video processing device, the device comprising:
  • An information acquisition module configured to acquire key information corresponding to the video to be processed
  • a segment extraction module configured to extract one or more target video segments from the video to be processed according to the key information
  • the video processing module is used to add the target video segment to the position before the specified video frame in the video to be processed to obtain the target video, and the specified video frame is a preset number of video frames in the video to be processed Any video frame in .
  • the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the method described in the first aspect of the present disclosure are implemented.
  • an electronic device including:
  • a processing device configured to execute the computer program in the storage device to implement the steps of the method described in the first aspect of the present disclosure.
  • the user can quickly watch the target video segment with the highest similarity with the key information of the target video, so that the user can quickly identify whether the target video meets their own needs.
  • it can improve the user's choice of video
  • the efficiency on the other hand, can also make the video effectively attract users in need to watch.
  • Fig. 1 is a flow chart showing a video processing method according to an exemplary embodiment.
  • Fig. 2 is a flow chart showing a step of S102 according to the embodiment shown in Fig. 1 .
  • Fig. 3 is a block diagram of a video processing device according to an exemplary embodiment.
  • Fig. 4 is a block diagram of an electronic device according to an exemplary embodiment.
  • the term “comprise” and its variations are open-ended, ie “including but not limited to”.
  • the term “based on” is “based at least in part on”.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one further embodiment”; the term “some embodiments” means “at least some embodiments.” Relevant definitions of other terms will be given in the description below.
  • the present disclosure can be applied to video processing scenarios.
  • various videos are continuously emerging on the Internet. Because the content and quality of different videos vary greatly, when users search for a certain type of video according to their own needs, they need to browse a large number of videos to find them. Since the video content is played in order, the key information is in the video frame during video playback. , users need to browse a complete video or a large section of video before they can identify whether a certain video meets their own needs. It cannot effectively attract users in need to watch.
  • the present disclosure provides a video processing method, device, readable medium and electronic equipment, which extract one or more target video segments from the video to be processed according to the key information corresponding to the video to be processed; and
  • the target video segment is added to the position before the specified video frame in the video to be processed to obtain the target video, and the specified video frame is any video frame in the previous preset number of video frames in the video to be processed.
  • the user can quickly watch the target video segment with the highest similarity with the key information of the target video, so that the user can quickly identify whether the target video meets their own needs.
  • it can improve the user's choice of video The efficiency; on the other hand, it can also make the video effectively attract users in need to watch.
  • Fig. 1 is a video processing method shown according to an exemplary embodiment, as shown in Fig. 1, the method includes:
  • Step 101 Obtain key information corresponding to the video to be processed.
  • the key information may be the selling point information of the product introduced by the video to be processed; if the video to be processed is a popular science video, the key information may be the The knowledge point information of the popular science knowledge introduced in the video.
  • the video title of the video to be processed can be used as the key information, or the information input by the user for the video to be processed can be used as the key information, or the preset hot words can be used as the key information.
  • the combination of the above video title, user input information and hot words can also be used as key information.
  • Step 102 extract one or more target video clips from the video to be processed according to the key information.
  • the similarity between each video frame of the video to be processed and the above key information may be calculated, and one or more target video clips may be obtained by combining the top N video frames with the highest similarity.
  • Step 103 Add the target video segment to the position before the specified video frame in the video to be processed to obtain the target video.
  • the specified video frame may be any video frame in the previous preset number of video frames in the video to be processed.
  • the preset number can be a fixed value, such as 10 or 20; the preset number can also be a value determined according to the total number of video frames of the video to be processed, for example, the preset number can be five of the total number of video frames of the video to be processed One-tenth or one-tenth.
  • the first frame of the video to be processed can be used as the specified video frame, so that the target video segment can be added to the front of the video to be processed.
  • the video frame after the title frame can be used as the specified video frame, so that the target video segment can be added after the title frame and before the content frame of the video to be processed.
  • the specified video frame is any video frame in the previous preset number of video frames in the video to be processed.
  • FIG. 2 is a flow chart of a step S102 according to the embodiment shown in FIG. 1. As shown in FIG. 2, the above step 102 may include the following steps:
  • Step 1021 according to the image information and audio information of the video to be processed, obtain one or more candidate video segments of the video to be processed.
  • the candidate video segment includes a complete segment of semantic information in the video to be processed.
  • the video to be processed can be segmented according to the image similarity between images of adjacent video frames and the audio similarity between audio frames corresponding to adjacent video frames to obtain one or more candidate video segments.
  • adjacent video frames whose image similarity is less than or equal to the first preset image similarity threshold and whose audio similarity is less than or equal to the first preset audio similarity threshold can be used as segmentation frames, and the video to be processed is segmented according to a plurality of segmentation frames, Get one or more candidate video clips.
  • Step 1022 obtaining the similarity between each candidate video segment and key information.
  • Step 1023 taking one or more candidate video segments with the highest similarity as the target video segment.
  • the similarity between each candidate video segment and key information can be determined through a pre-trained video analysis model, and the one or a preset number of candidate video segments with the highest similarity can be used as target video segments according to the similarity sorting results.
  • video clips including complete semantic information can be obtained, avoiding the truncated semantic information in the video clips and making it impossible to display complete semantic information to the user, and through similarity comparison, one or more candidates with the highest similarity to key information
  • the video segment is used as the target video segment, so that the target video segment can completely and accurately display the key information of the video to be processed.
  • the above step 1021 may also obtain one or more candidate video segments of the video to be processed in the following manner:
  • each of the pending video segments includes one or more frames of images.
  • the image text in each frame image of the video to be processed may be obtained; the text similarity of the image text between adjacent frame images is calculated; and the undetermined video segment is determined according to the text similarity.
  • OCR Optical Character Recognition, optical character recognition
  • the pending text can be used as image text, or can be filtered out according to the text area of each pending text
  • the pending text whose text area is smaller than or equal to the preset area can be used as the invalid small text, and the other texts in the pending text except the invalid small text can be used as the above image text.
  • the undetermined text whose text area is larger than the preset area can also be directly used as the above-mentioned image text.
  • OCR refers to the process of determining the shape of characters by detecting dark and bright patterns, and then using character recognition methods to translate the shape of characters into text.
  • noise removal can be performed on each frame of image , tilt correction, character cutting and other preprocessing processes, after preprocessing, character recognition is performed to obtain the above-mentioned undetermined text.
  • the video to be processed can be segmented according to the text similarity of the image text corresponding to adjacent video frames, and one or more video segments to be determined can be obtained.
  • adjacent video frames whose image similarity is less than or equal to a second preset image similarity threshold may be used as segmented frames, and the video to be processed is segmented according to the plurality of segmented frames to obtain one or more undetermined video segments.
  • video frames with the same or similar image text can be divided into one undetermined video segment, so that each undetermined video segment has the same or similar semantics.
  • the audio text corresponding to the audio information may be acquired; sentence segmentation inference is performed on the audio text to obtain sentence segmentation information in the audio text; and one or more pending audio segments are determined according to the sentence segmentation information.
  • ASR Automatic Speech Recognition, automatic speech recognition technology
  • sentence segmentation can be inferred based on audio text and timestamps, for example, to obtain the time difference between adjacent text characters, and use two adjacent text characters with a time difference greater than the preset time threshold as sentence segmentation characters, and then according to the semantics before and after the sentence segmentation characters
  • sentence break punctuation and the position information of the sentence break punctuation may be used as the above sentence break punctuation; the audio between two sentence break punctuation is used as the audio segment to be determined.
  • the acquisition of the above-mentioned sentence segmentation characters and sentence segmentation punctuation can also be obtained by processing the audio text through a pre-trained text segmentation model.
  • the structure and training method of the text segmentation model can refer to the implementation methods in the prior art. This disclosure does not limit this.
  • the candidate video segment can be obtained by correcting the pending audio segment and the pending video segment in the following manner:
  • the corresponding relationship between the undetermined audio segment and the undetermined video segment may be determined according to the text similarity between the audio text corresponding to the undetermined audio segment and the image text corresponding to the undetermined video segment.
  • the pending audio segments are sorted according to the text similarity, and the pending audio segment with the highest text similarity is taken as the pending audio segment corresponding to the pending video segment.
  • the time coincidence degree is calculated according to the start and end times of the undetermined audio segment and the pending video segment in the video to be processed, and for each video to be processed, the pending audio segment with the highest time coincidence degree is used as the corresponding to the undetermined video segment Pending audio clips for .
  • integrity correction may be performed on the undetermined video segment according to the undetermined audio segment corresponding to the undetermined video segment to obtain a candidate video segment.
  • an integrity correction operation may be performed on the pending video segment according to the time information of the pending audio segment, and the integrity correction operation may include correcting the start and end time of the video segment or merging adjacent video segments.
  • the time of the first pending video segment is between the 15th second and the 20th second after the video starts playing, if the time of the first pending audio segment corresponding to the first pending video segment is the first pending audio segment after the video starts playing 15 seconds to the 21st second, then the time of the first pending video segment can be corrected to the 15th second to the 20th second.
  • the second undetermined video segment adjacent to the first undetermined video segment can also be modified, for example, the time of the second undetermined video segment is corrected from "the 21st second to the 30th second" to "Second 22 to Second 30"
  • the time of the first pending video segment is between the 15th second and the 20th second after the video starts playing
  • the time of the second pending video segment adjacent to it is between the 21st second and the 25th second after the video starts playing
  • the second pending video segment can be combined with the The first pending video segment is merged into a new first pending video segment.
  • correcting the integrity of the video segment through the audio information can enable the obtained candidate video segment to display complete semantics, avoiding that the semantics in the candidate video segment are truncated and cannot display complete semantic information to the user.
  • the above step 103 adds the target video segment to the position before the specified video frame in the video to be processed, and the method for obtaining the target video may include:
  • the target video segment is updated according to preset description information.
  • the preset description information is used to characterize the key information of the target video segment corresponding to the video to be processed.
  • the preset description information may be the text "Video Introduction”, and the text is added to each video frame of the target video segment, so as to remind the user that the video frame is the introduction part of the video, not the main content of the video.
  • the updated target video segment is added to the position before the specified video frame in the video to be processed to obtain the target video.
  • the user can distinguish the target video segment displaying the key information from the main content of the video, so as to prevent the user from being unable to understand the video information due to video content jumping.
  • Fig. 3 is a block diagram of a video processing device according to an exemplary embodiment. As shown in Figure 3, the video processing device includes:
  • An information acquisition module 301 configured to acquire key information corresponding to the video to be processed
  • the video processing module 303 is used to add the target video segment to the position before the specified video frame in the video to be processed to obtain the target video, and the specified video frame is a preset number of videos in the video to be processed Any video frame in the frame.
  • the segment extraction module 302 is configured to obtain one or more candidate video segments of the video to be processed according to image information and audio information of the video to be processed; wherein, the candidate video segments include the Describe a complete semantic information in the video to be processed; obtain the similarity between each candidate video segment and the key information; use one or more candidate video segments with the highest similarity as the target video segment.
  • the segment extraction module 302 is configured to acquire one or more pending video segments of the video to be processed according to the image information, each of the pending video segments includes one or more frames of images; Acquire one or more pending audio segments of the video to be processed according to the audio information; determine the candidate video segment according to the pending video segment and the pending audio segment.
  • the segment extraction module 302 is configured to obtain the image text in each frame image of the video to be processed; calculate the text similarity of the image text between adjacent frame images; according to the text similarity, The pending video segment is determined.
  • the segment extraction module 302 is configured to obtain the audio text corresponding to the audio information; perform sentence segmentation inference on the audio text, and obtain sentence segmentation information in the audio text; according to the sentence segmentation information, One or more of the pending audio segments are determined.
  • the segment extraction module 302 is configured to determine the correspondence between pending audio segments and pending video segments; for each pending video segment, according to the pending audio segment corresponding to the pending video segment, the pending video segment Integrity correction is performed on the fragments to obtain candidate video fragments.
  • the video processing module 303 is configured to update the target video segment according to preset description information; the preset description information is used to characterize key information of the target video segment corresponding to the video to be processed ; Add the updated target video segment to the position before the specified video frame in the video to be processed to obtain the target video.
  • FIG. 4 it shows a schematic structural diagram of an electronic device (such as a terminal device or a server) 900 suitable for implementing an embodiment of the present disclosure.
  • the terminal equipment in the embodiment of the present disclosure may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle terminal (such as mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like.
  • the electronic device shown in FIG. 4 is only an example, and should not limit the functions and application scope of the embodiments of the present disclosure.
  • an electronic device 900 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 901, which may be randomly accessed according to a program stored in a read-only memory (ROM) 902 or loaded from a storage device 908.
  • a processing device such as a central processing unit, a graphics processing unit, etc.
  • RAM random access memory
  • Various appropriate actions and processes are executed by programs in the memory (RAM) 903 .
  • RAM 903 In the RAM 903, various programs and data necessary for the operation of the electronic device 900 are also stored.
  • the processing device 901 , ROM 902 , and RAM 903 are connected to each other via a bus 904 .
  • An input/output (I/O) interface 905 is also connected to the bus 904 .
  • the following devices can be connected to the I/O interface 905: input devices 906 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration an output device 907 such as a computer; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909.
  • the communication means 909 may allow the electronic device 900 to perform wireless or wired communication with other devices to exchange data. While FIG. 4 shows electronic device 900 having various means, it should be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, where the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network via communication means 909 , or from storage means 908 , or from ROM 902 .
  • the processing device 901 When the computer program is executed by the processing device 901, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, 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 device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may 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 data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and the server can communicate using any currently known or future network protocols such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol), and can communicate with digital data in any form or medium
  • HTTP HyperText Transfer Protocol
  • the communication eg, communication network
  • Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains key information corresponding to the video to be processed; according to the key information, from the Extracting one or more target video segments from the video to be processed; adding the target video segment to the position before the specified video frame in the video to be processed to obtain the target video, and the specified video frame is in the video to be processed Any one of the previous preset number of video frames.
  • Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages - such as "C" or similar programming languages.
  • 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.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connected via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, using an Internet service provider to connected via the Internet.
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware.
  • the name of the module does not constitute a limitation of the module itself under certain circumstances, for example, the information acquisition module can also be described as "a module for acquiring key information corresponding to the video to be processed".
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs System on Chips
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • Example 1 provides a video processing method, the method comprising:
  • the target video segment Adding the target video segment to the position before the specified video frame in the video to be processed to obtain the target video, the specified video frame being any video frame in the previous preset number of video frames in the video to be processed .
  • Example 2 provides the method described in Example 1, wherein extracting one or more target video segments from the video to be processed according to the key information includes:
  • One or more candidate video segments with the highest similarity are used as the target video segment.
  • Example 3 provides the method described in Example 2, the acquisition of one or more candidate video segments of the video to be processed according to the image information and audio information of the video to be processed includes :
  • each of the undetermined video segments includes one or more frames of images
  • the candidate video segment is determined according to the pending video segment and the pending audio segment.
  • Example 4 provides the method described in Example 3, wherein the acquiring one or more pending video segments of the video to be processed according to the image information includes:
  • Example 5 provides the method described in Example 3, wherein the acquiring one or more pending audio segments of the video to be processed according to the audio information includes:
  • Example 6 provides the method described in Example 3, wherein determining the candidate video segment according to the pending video segment and the pending audio segment includes:
  • the integrity correction is performed on the undetermined video segment to obtain a candidate video segment.
  • Example 7 provides the method described in any one of Examples 1 to 6, wherein the target video segment is added to the position before the specified video frame in the video to be processed , get the target video including:
  • the preset description information is used to characterize key information of the target video segment corresponding to the video to be processed;
  • the updated target video segment is added to the position before the specified video frame in the video to be processed to obtain the target video.
  • Example 8 provides a video processing device, the device comprising:
  • An information acquisition module configured to acquire key information corresponding to the video to be processed
  • a segment extraction module configured to extract one or more target video segments from the video to be processed according to the key information
  • the video processing module is used to add the target video segment to the position before the specified video frame in the video to be processed to obtain the target video, and the specified video frame is a preset number of video frames in the video to be processed Any video frame in .
  • Example 9 provides the device described in Example 8, the segment extraction module is configured to acquire one or more of the video to be processed according to the image information and audio information of the video to be processed.
  • a plurality of candidate video clips wherein, the candidate video clips include a complete piece of semantic information in the video to be processed; obtain the similarity between each candidate video clip and the key information; the one with the highest similarity or multiple candidate video segments as the target video segment.
  • Example 10 provides the device described in Example 9, the segment extraction module is configured to acquire one or more pending video segments of the video to be processed according to the image information, Each of the undetermined video clips includes one or more frames of images; one or more pending audio clips of the video to be processed are obtained according to the audio information; according to the pending video clips and the pending audio clips, determine the Describe candidate video segments.
  • Example 11 provides the device described in Example 10, the segment extraction module is used to obtain the image text in each frame image of the video to be processed; The text similarity of the image text; according to the text similarity, determine the undetermined video segment.
  • Example 12 provides the device described in Example 10, the segment extraction module is configured to obtain the audio text corresponding to the audio information; perform sentence inference on the audio text, and obtain Sentence information in the audio text; according to the sentence information, determine one or more audio segments to be determined.
  • Example 13 provides the device described in Example 10, the segment extraction module is used to determine the correspondence between pending audio segments and pending video segments; for each pending video segment, according to Integrity correction is performed on the undetermined audio segment corresponding to the undetermined video segment to obtain a candidate video segment.
  • Example 14 provides the device described in any one of Examples 8 to 13, the video processing module is configured to update the target video segment according to preset description information; the The preset description information is used to characterize the key information of the target video segment corresponding to the video to be processed; the updated target video segment is added to the position before the specified video frame in the video to be processed to obtain the target video.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

一种视频处理方法、装置、可读介质及电子设备。方法包括：获取待处理视频对应的关键信息；根据关键信息，从待处理视频中提取一个或多个目标视频片段；将目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频，指定视频帧为待处理视频中前预设数量个视频帧中的任一视频帧。

Description

视频处理方法、装置、可读介质及电子设备
本申请要求于2022年01月29日提交的，申请名称为“视频处理方法、装置、可读介质及电子设备”的、中国专利申请号为“202210113116.0”的优先权，该中国专利申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域，具体地，涉及一种视频处理方法、装置、可读介质及电子设备。
背景技术
随着计算机技术的发展，多媒体的应用也越来越广泛，各种各样的视频在网络上不断涌现，在大量的网络视频中，用户难以根据自身需求快速确定所需要的视频。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
第一方面，本公开提供了一种视频处理方法，所述方法包括：
获取待处理视频对应的关键信息；
根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
第二方面，本公开提供了一种视频处理装置，所述装置包括：
信息获取模块，用于获取待处理视频对应的关键信息；
片段提取模块，用于根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
视频处理模块，用于将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
第三方面，本公开提供一种计算机可读介质，其上存储有计算机程序，该程序被处理装置执行时实现本公开第一方面所述方法的步骤。
第四方面，本公开提供一种电子设备，包括：
存储装置，其上存储有计算机程序；
处理装置，用于执行所述存储装置中的所述计算机程序，以实现本公开第一方面所述方 法的步骤。
采用上述技术方案，获取待处理视频对应的关键信息；根据关键信息，从待处理视频中提取一个或多个目标视频片段；将目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频，该指定视频帧为待处理视频中前预设数量个视频帧中的任一视频帧。这样，可以使得用户在浏览到目标视频后，能够快速观看到与目标视频的关键信息相似度最高的目标视频片段，使得用户能够快速甄别该目标视频是否符合自身需求，一方面能够提升用户选择视频的效率，另一方面也能够使得视频有效吸引有需求的用户观看。
本公开的其他特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。在附图中：
图1是根据一示例性实施例示出的一种视频处理方法的流程图。
图2是根据图1所示实施例示出的一种S102步骤的流程图。
图3是根据一示例性实施例示出的一种视频处理装置的框图。
图4是根据一示例性实施例示出的一种电子设备的框图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域 技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
首先，对本公开的应用场景进行说明。本公开可以应用于视频处理场景，随着计算机技术的发展，各种各样的视频在网络上不断涌现。由于不同视频的内容和质量差异很大，当用户根据自身需求寻找某一类视频时，需要浏览大量视频寻找，由于视频内容是按照顺序播放的，关键信息都在视频播放过程中的视频帧中，用户需要浏览完整的视频或一大段视频后，才能够甄别某个视频是否符合自身需求，这样一方面会导致用户难以根据自身需求快速浏览得到所需要的视频；另一方面也会导致视频无法有效吸引有需求的用户观看。
为了解决上述问题，本公开提供了一种视频处理的方法、装置、可读介质及电子设备，根据待处理视频对应的关键信息，从待处理视频中提取一个或多个目标视频片段；并将目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频，该指定视频帧为待处理视频中前预设数量个视频帧中的任一视频帧。这样，可以使得用户在浏览到目标视频后，能够快速观看到与目标视频的关键信息相似度最高的目标视频片段，使得用户能够快速甄别该目标视频是否符合自身需求，一方面能够提升用户选择视频的效率；另一方面也能够使得视频有效吸引有需求的用户观看。
以下结合附图对本公开的具体实施方式进行详细说明。
图1是根据一示例性实施例示出的一种视频处理方法，如图1所示，该方法包括：
步骤101、获取待处理视频对应的关键信息。
示例地，若该待处理视频为商品介绍视频，则该关键信息可以是该待处理视频所介绍的商品的卖点信息；若该待处理视频为科普知识视频，则该关键信息可以为该待处理视频所介绍的科普知识的知识点信息。
在本步骤中，可以将该待处理视频的视频标题作为关键信息，或者，将用户针对该待处理视频输入的信息作为关键信息，或者，将预先设置的热点词语作为关键信息。当然，也可以将上述视频标题、用户输入信息和热点词语组合作为关键信息。
步骤102、根据关键信息，从待处理视频中提取一个或多个目标视频片段。
示例地，可以计算待处理视频的每个视频帧与上述关键信息的相似度，根据相似度最高的前N个视频帧组合得到一个或多个目标视频片段。
步骤103、将目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频。
其中，该指定视频帧可以为待处理视频中前预设数量个视频帧中的任一视频帧。该预设数量可以是固定数值，例如10或20；该预设数量也可以是根据待处理视频的视频帧总数确 定的数值，例如该预设数量可以是该待处理视频的视频帧总数的五分之一或十分之一。
例如，可以将待处理视频的第一帧作为该指定视频帧，这样，可以将目标视频片段添加至待处理视频的最前面。再例如，可以将标题帧之后的视频帧作为该指定视频帧，这样，可以将目标视频片段添加至待处理视频的标题帧之后，内容帧之前。
采用上述方法，获取待处理视频对应的关键信息；根据关键信息，从待处理视频中提取一个或多个目标视频片段；将目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频，该指定视频帧为待处理视频中前预设数量个视频帧中的任一视频帧。这样，可以使得用户在浏览到目标视频后，能够快速观看到与目标视频的关键信息相似度最高的目标视频片段，使得用户能够快速甄别该目标视频是否符合自身需求，一方面能够提升用户选择视频的效率，另一方面也能够使得视频有效吸引有需求的用户观看。
图2是根据图1所示实施例示出的一种S102步骤的流程图，如图2所示，上述步骤102可以包括以下步骤：
步骤1021、根据待处理视频的图像信息和音频信息，获取该待处理视频的一个或多个候选视频片段。
其中，该候选视频片段包括该待处理视频中的一段完整的语义信息。
可以通过相邻视频帧图像之间的图像相似度，以及相邻视频帧对应的音频帧之间的音频相似度，对待处理视频进行分割，得到一个或多个候选视频片段。
例如，可以将图像相似度小于等于第一预设图像相似阈值且音频相似度小于等于第一预设音频相似阈值的相邻视频帧作为分割帧，根据多个分割帧，对待处理视频进行分割，得到一个或多个候选视频片段。
步骤1022、获取每个候选视频片段与关键信息的相似度。
步骤1023、将相似度最高的一个或多个候选视频片段作为目标视频片段。
示例地，可以通过预先训练的视频分析模型，确定每个候选视频片段与关键信息的相似度，根据相似度排序结果，将相似度最高的一个或预设数目个候选视频片段作为目标视频片段。
这样，可以获取包括完整语义信息的视频片段，避免视频片段中的语义被截断导致无法向用户展示完整的语义信息，并通过相似度对比，将与关键信息的相似度最高的一个或多个候选视频片段作为目标视频片段，从而使得目标视频片段能够完整准确的展示待处理视频的关键信息。
在本公开的另一实施例中，上述步骤1021还可以通过以下方式获取该待处理视频的一个或多个候选视频片段：
S11、根据图像信息获取待处理视频的一个或多个待定视频片段。
其中，每个该待定视频片段包括一帧或多帧图像。
示例地，可以获取待处理视频的每帧图像中的图像文本；计算相邻帧图像之间的图像文本的文本相似度；根据该文本相似度，确定该待定视频片段。
例如，可以通过OCR(Optical Character Recognition，光学字符识别)，获取待处理视频的每帧图像中的待定文本；然后可以将该待定文本作为图像文本，也可以根据每个待定文本的文本面积过滤掉每帧图像中的无效小文本，例如，可以将文本面积小于或等于预设面积的待定文本作为无效小文本，将待定文本中除了无效小文本之外的其他文本作为上述图像文本。当然，也可以直接将文本面积大于预设面积的待定文本作为上述图像文本。
需要说明的是，OCR是指通过检测暗、亮的模式确定字符形状，然后用字符识别方法将字符形状翻译成文本的过程，为了提高OCR识别文本的准确性，可以对每帧图像进行噪声去除、倾斜较正、字符切割等预处理过程，经过预处理后在进行字符识别得到上述待定文本。
进一步地，可以通过相邻视频帧对应的图像文本的文本相似度，对待处理视频进行分割，得到一个或多个待定视频片段。例如，可以将图像相似度小于或等于第二预设图像相似阈值的相邻视频帧作为分割帧，根据多个分割帧，对待处理视频进行分割，得到一个或多个待定视频片段。
这样，可以将具有相同或相似图像文本的视频帧分割到一个待定视频片段中，从而使得每个待定视频片段具有相同或相似的语义。
S12、根据音频信息获取待处理视频的一个或多个待定音频片段。
示例地，可以获取音频信息对应的音频文本；对该音频文本进行断句推断，获取该音频文本中的断句信息；根据该断句信息，确定一个或多个该待定音频片段。
例如，可以通过ASR(Automatic Speech Recognition，自动语音识别技术)，获取待处理视频的音频信息对应的音频文本，以及每个音频文本中每个文本字符对应的时间戳。然后，可以根据音频文本及时间戳进行断句推断，例如获取相邻文本字符之间的时间差，将时间差大于预设时间阈值的两个相邻文本字符作为断句字符，然后可以根据断句字符前后的语义确定断句标点，可以将该断句标点及该断句标点的位置信息作为上述断句信息；将两个断句标点之间的音频作为待定音频片段。
需要说明的是，上述断句字符和断句标点的获取，也可以通过预先训练的文本断句模型对音频文本进行处理后得到，该文本断句模型的结构及训练方法可以参考现有技术中的实现方式，本公开对此不作限制。
S13、根据该待定视频片段和该待定音频片段，确定该候选视频片段。
在本步骤中，可以通过以下方式，根据待定音频片段对待定视频片段进行修正，得到该候选视频片段：
首先，确定待定音频片段与待定视频片段的对应关系。
在本步骤中，可以根据待定音频片段对应的音频文本和待定视频片段对应的图像文本的文本相似度，确定待定音频片段与待定视频片段的对应关系。
例如，针对每个待定视频片段，根据文本相似度对待定音频片段进行排序，将文本相似度最高的待定音频片段作为与该待定视频片段对应的待定音频片段。
进一步地，也可以根据待定音频片段和待定视频片段在待处理视频中的起止时间进行时间重合度计算，针对每个待处理视频，将时间重合度最高的待定音频片段作为与该待定视频片段对应的待定音频片段。
然后，针对每个待定视频片段，可以根据与该待定视频片段对应的待定音频片段，对该待定视频片段进行完整性修正，得到候选视频片段。
示例地，可以根据待定音频片段的时间信息，对待定视频片段进行完整性修正操作，该完整性修正操作可以包括视频片段起止时间修正或者相邻视频拍片段合并。
例如，第一待定视频片段的时间为视频开始播放后的第15秒至第20秒之间，若与该第一待定视频片段相对应的第一待定音频片段的时间为视频开始播放后的第15秒至第21秒之间的片段，则可以将该第一待定视频片段的时间修正为第15秒至第20秒。另外，为了避免视频片段重复，还可以将与该第一待定视频片段相邻的第二待定视频片段进行修正，例如将第二待定视频片段的时间从“第21秒至第30秒”修正为“第22秒至第30秒”
例如，第一待定视频片段的时间为视频开始播放后的第15秒至第20秒之间，与之相邻的第二待定视频片段的时间为视频开始播放后的第21秒至第25秒之间，若与该第一待定视频片段相对应的第一待定音频片段的时间为视频开始播放后的第15秒至第25秒之间的片段，则可以将该第二待定视频片段与该第一待定视频片段合并为新的第一待定视频片段。
这样，通过音频信息对视频片段进行完整性修正，可以使得得到的候选视频片段能够展示完整语义，避免候选视频片段中的语义被截断导致无法向用户展示完整的语义信息。
在本公开的另一实施例中，上述步骤103将目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频的方法可以包括：
首先，根据预设描述信息更新该目标视频片段。
该预设描述信息用于表征该目标视频片段对应该待处理视频的关键信息。例如，该预设描述信息可以是文本“视频简介”，将该文本增加至目标视频片段的每个视频帧中，以便提 示用户，该视频帧为视频简介部分，不是视频的主体内容。
然后，将更新后的目标视频片段添加至待处理视频中指定视频帧之前的位置，得到目标视频。
这样，可以使得用户能够区分展示关键信息的目标视频片段和视频的主体内容，避免由于视频内容跳跃导致用户对视频信息无法理解。
图3是根据一示例性实施例示出的一种视频处理装置的框图。如图3所示，该视频处理装置包括：
信息获取模块301，用于获取待处理视频对应的关键信息；
片段提取模块302，用于根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
视频处理模块303，用于将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
在一些实施例中，所述片段提取模块302，用于根据待处理视频的图像信息和音频信息，获取所述待处理视频的一个或多个候选视频片段；其中，所述候选视频片段包括所述待处理视频中的一段完整的语义信息；获取每个候选视频片段与所述关键信息的相似度；将所述相似度最高的一个或多个候选视频片段作为所述目标视频片段。
在一些实施例中，所述片段提取模块302，用于根据所述图像信息获取所述待处理视频的一个或多个待定视频片段，每个所述待定视频片段包括一帧或多帧图像；根据所述音频信息获取所述待处理视频的一个或多个待定音频片段；根据所述待定视频片段和所述待定音频片段，确定所述候选视频片段。
在一些实施例中，所述片段提取模块302，用于获取待处理视频的每帧图像中的图像文本；计算相邻帧图像之间的图像文本的文本相似度；根据所述文本相似度，确定所述待定视频片段。
在一些实施例中，所述片段提取模块302，用于获取所述音频信息对应的音频文本；对所述音频文本进行断句推断，获取所述音频文本中的断句信息；根据所述断句信息，确定一个或多个所述待定音频片段。
在一些实施例中，所述片段提取模块302，用于确定待定音频片段与待定视频片段的对应关系；针对每个待定视频片段，根据与该待定视频片段对应的待定音频片段，对该待定视频片段进行完整性修正，得到候选视频片段。
在一些实施例中，所述视频处理模块303，用于根据预设描述信息更新所述目标视频片 段；所述预设描述信息用于表征所述目标视频片段对应所述待处理视频的关键信息；将更新后的目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频。
下面参考图4，其示出了适于用来实现本公开实施例的电子设备(例如终端设备或服务器)900的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图4示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图4所示，电子设备900可以包括处理装置(例如中央处理器、图形处理器等)901，其可以根据存储在只读存储器(ROM)902中的程序或者从存储装置908加载到随机访问存储器(RAM)903中的程序而执行各种适当的动作和处理。在RAM903中，还存储有电子设备900操作所需的各种程序和数据。处理装置901、ROM902以及RAM903通过总线904彼此相连。输入/输出(I/O)接口905也连接至总线904。
通常，以下装置可以连接至I/O接口905：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置906；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置907；包括例如磁带、硬盘等的存储装置908；以及通信装置909。通信装置909可以允许电子设备900与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的电子设备900，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置909从网络上被下载和安装，或者从存储装置908被安装，或者从ROM902被安装。在该计算机程序被处理装置901执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、 磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取待处理视频对应的关键信息；根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言——诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个 模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块的名称在某种情况下并不构成对该模块本身的限定，例如，信息获取模块还可以被描述为“获取待处理视频对应的关键信息的模块”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，示例1提供了一种视频处理方法，所述方法包括：
获取待处理视频对应的关键信息；
根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
根据本公开的一个或多个实施例，示例2提供了示例1所述的方法，所述根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段包括：
根据待处理视频的图像信息和音频信息，获取所述待处理视频的一个或多个候选视频片段；其中，所述候选视频片段包括所述待处理视频中的一段完整的语义信息；
获取每个候选视频片段与所述关键信息的相似度；
将所述相似度最高的一个或多个候选视频片段作为所述目标视频片段。
根据本公开的一个或多个实施例，示例3提供了示例2所述的方法，所述根据待处理视频的图像信息和音频信息，获取所述待处理视频的一个或多个候选视频片段包括：
根据所述图像信息获取所述待处理视频的一个或多个待定视频片段，每个所述待定视频片段包括一帧或多帧图像；
根据所述音频信息获取所述待处理视频的一个或多个待定音频片段；
根据所述待定视频片段和所述待定音频片段，确定所述候选视频片段。
根据本公开的一个或多个实施例，示例4提供了示例3所述的方法，所述根据所述图像信息获取所述待处理视频的一个或多个待定视频片段包括：
获取待处理视频的每帧图像中的图像文本；
计算相邻帧图像之间的图像文本的文本相似度；
根据所述文本相似度，确定所述待定视频片段。
根据本公开的一个或多个实施例，示例5提供了示例3所述的方法，所述根据所述音频信息获取所述待处理视频的一个或多个待定音频片段包括：
获取所述音频信息对应的音频文本；
对所述音频文本进行断句推断，获取所述音频文本中的断句信息；
根据所述断句信息，确定一个或多个所述待定音频片段。
根据本公开的一个或多个实施例，示例6提供了示例3所述的方法，所述根据所述待定视频片段和所述待定音频片段，确定所述候选视频片段包括：
确定待定音频片段与待定视频片段的对应关系；
针对每个待定视频片段，根据与该待定视频片段对应的待定音频片段，对该待定视频片段进行完整性修正，得到候选视频片段。
根据本公开的一个或多个实施例，示例7提供了示例1至6中任一项所述的方法，所述将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频包括：
根据预设描述信息更新所述目标视频片段；所述预设描述信息用于表征所述目标视频片段对应所述待处理视频的关键信息；
将更新后的目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频。
根据本公开的一个或多个实施例，示例8提供了一种视频处理装置，所述装置包括：
信息获取模块，用于获取待处理视频对应的关键信息；
片段提取模块，用于根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
视频处理模块，用于将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
根据本公开的一个或多个实施例，示例9提供了示例8所述的装置，所述片段提取模块，用于根据待处理视频的图像信息和音频信息，获取所述待处理视频的一个或多个候选视频片段；其中，所述候选视频片段包括所述待处理视频中的一段完整的语义信息；获取每个候选视频片段与所述关键信息的相似度；将所述相似度最高的一个或多个候选视频片段作为所述目标视频片段。
根据本公开的一个或多个实施例，示例10提供了示例9所述的装置，所述片段提取模块，用于根据所述图像信息获取所述待处理视频的一个或多个待定视频片段，每个所述待定视频片段包括一帧或多帧图像；根据所述音频信息获取所述待处理视频的一个或多个待定音频片段；根据所述待定视频片段和所述待定音频片段，确定所述候选视频片段。
根据本公开的一个或多个实施例，示例11提供了示例10所述的装置，所述片段提取模块，用于获取待处理视频的每帧图像中的图像文本；计算相邻帧图像之间的图像文本的文本相似度；根据所述文本相似度，确定所述待定视频片段。
根据本公开的一个或多个实施例，示例12提供了示例10所述的装置，所述片段提取模块，用于获取所述音频信息对应的音频文本；对所述音频文本进行断句推断，获取所述音频文本中的断句信息；根据所述断句信息，确定一个或多个所述待定音频片段。
根据本公开的一个或多个实施例，示例13提供了示例10所述的装置，所述片段提取模块，用于确定待定音频片段与待定视频片段的对应关系；针对每个待定视频片段，根据与该待定视频片段对应的待定音频片段，对该待定视频片段进行完整性修正，得到候选视频片段。
根据本公开的一个或多个实施例，示例14提供了示例8至13中任一项所述的装置，所述视频处理模块，用于根据预设描述信息更新所述目标视频片段；所述预设描述信息用于表征所述目标视频片段对应所述待处理视频的关键信息；将更新后的目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特 征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。

Claims (10)

  1. 一种视频处理方法，其中，所述方法包括：
    获取待处理视频对应的关键信息；
    根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
    将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
  2. 根据权利要求1所述的方法，其中，所述根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段包括：
    根据待处理视频的图像信息和音频信息，获取所述待处理视频的一个或多个候选视频片段；其中，所述候选视频片段包括所述待处理视频中的一段完整的语义信息；
    获取每个候选视频片段与所述关键信息的相似度；
    将所述相似度最高的一个或多个候选视频片段作为所述目标视频片段。
  3. 根据权利要求2所述的方法，其中，所述根据待处理视频的图像信息和音频信息，获取所述待处理视频的一个或多个候选视频片段包括：
    根据所述图像信息获取所述待处理视频的一个或多个待定视频片段，每个所述待定视频片段包括一帧或多帧图像；
    根据所述音频信息获取所述待处理视频的一个或多个待定音频片段；
    根据所述待定视频片段和所述待定音频片段，确定所述候选视频片段。
  4. 根据权利要求3所述的方法，其中，所述根据所述图像信息获取所述待处理视频的一个或多个待定视频片段包括：
    获取待处理视频的每帧图像中的图像文本；
    计算相邻帧图像之间的图像文本的文本相似度；
    根据所述文本相似度，确定所述待定视频片段。
  5. 根据权利要求3所述的方法，其中，所述根据所述音频信息获取所述待处理视频的一个或多个待定音频片段包括：
    获取所述音频信息对应的音频文本；
    对所述音频文本进行断句推断，获取所述音频文本中的断句信息；
    根据所述断句信息，确定一个或多个所述待定音频片段。
  6. 根据权利要求3所述的方法，其中，所述根据所述待定视频片段和所述待定音频片段，确定所述候选视频片段包括：
    确定待定音频片段与待定视频片段的对应关系；
    针对每个待定视频片段，根据与该待定视频片段对应的待定音频片段，对该待定视频片段进行完整性修正，得到候选视频片段。
  7. 根据权利要求1至6中任一项所述的方法，其中，所述将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频包括：
    根据预设描述信息更新所述目标视频片段；所述预设描述信息用于表征所述目标视频片段对应所述待处理视频的关键信息；
    将更新后的目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频。
  8. 一种视频处理装置，其中，所述装置包括：
    信息获取模块，用于获取待处理视频对应的关键信息；
    片段提取模块，用于根据所述关键信息，从所述待处理视频中提取一个或多个目标视频片段；
    视频处理模块，用于将所述目标视频片段添加至所述待处理视频中指定视频帧之前的位置，得到目标视频，所述指定视频帧为所述待处理视频中前预设数量个视频帧中的任一视频帧。
  9. 一种计算机可读介质，其上存储有计算机程序，其中，该程序被处理装置执行时实现权利要求1至7中任一项所述方法的步骤。
  10. 一种电子设备，其包括：
    存储装置，其上存储有计算机程序；
    处理装置，用于执行所述存储装置中的所述计算机程序，以实现权利要求1至7中任一项所述方法的步骤。
PCT/CN2023/070262 2022-01-29 2023-01-04 视频处理方法、装置、可读介质及电子设备 Ceased WO2023142913A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/832,049 US20250118338A1 (en) 2022-01-29 2023-01-04 Methods, devices, readable media and electronic devices for video processing

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210113116.0 2022-01-29
CN202210113116.0A CN114445754A (zh) 2022-01-29 2022-01-29 视频处理方法、装置、可读介质及电子设备

Publications (1)

Publication Number Publication Date
WO2023142913A1 true WO2023142913A1 (zh) 2023-08-03

Family

ID=81371989

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/070262 Ceased WO2023142913A1 (zh) 2022-01-29 2023-01-04 视频处理方法、装置、可读介质及电子设备

Country Status (3)

Country Link
US (1) US20250118338A1 (zh)
CN (1) CN114445754A (zh)
WO (1) WO2023142913A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240078807A1 (en) * 2022-09-01 2024-03-07 Douyin Vision Co., Ltd. Method, apparatus,electronic device and storage medium for video processing
CN118590625A (zh) * 2024-08-07 2024-09-03 宁德时代新能源科技股份有限公司 监控处理方法、装置、计算机设备、存储介质和程序产品

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114445754A (zh) * 2022-01-29 2022-05-06 北京有竹居网络技术有限公司 视频处理方法、装置、可读介质及电子设备
CN115881295B (zh) * 2022-12-06 2024-01-23 首都医科大学附属北京天坛医院 帕金森症状信息检测方法、装置、设备和计算机可读介质
CN116030380A (zh) * 2022-12-15 2023-04-28 青岛云天励飞科技有限公司 视频处理方法、装置、电子设备及存储介质
CN116112743B (zh) * 2023-02-01 2025-09-19 北京有竹居网络技术有限公司 视频处理的方法、装置、设备和存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160070962A1 (en) * 2014-09-08 2016-03-10 Google Inc. Selecting and Presenting Representative Frames for Video Previews
CN113536036A (zh) * 2021-01-07 2021-10-22 腾讯科技（深圳）有限公司 视频数据显示方法、装置、电子设备及存储介质
CN114445754A (zh) * 2022-01-29 2022-05-06 北京有竹居网络技术有限公司 视频处理方法、装置、可读介质及电子设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104540044B (zh) * 2014-12-30 2017-10-24 北京奇艺世纪科技有限公司 一种视频分段方法及装置
CN113672765A (zh) * 2020-05-14 2021-11-19 华为技术有限公司 一种视频处理方法、装置、设备及介质
CN111757170B (zh) * 2020-07-01 2022-09-23 三星电子（中国）研发中心 一种视频分段和标记的方法及装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160070962A1 (en) * 2014-09-08 2016-03-10 Google Inc. Selecting and Presenting Representative Frames for Video Previews
CN113536036A (zh) * 2021-01-07 2021-10-22 腾讯科技（深圳）有限公司 视频数据显示方法、装置、电子设备及存储介质
CN114445754A (zh) * 2022-01-29 2022-05-06 北京有竹居网络技术有限公司 视频处理方法、装置、可读介质及电子设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240078807A1 (en) * 2022-09-01 2024-03-07 Douyin Vision Co., Ltd. Method, apparatus,electronic device and storage medium for video processing
CN118590625A (zh) * 2024-08-07 2024-09-03 宁德时代新能源科技股份有限公司 监控处理方法、装置、计算机设备、存储介质和程序产品

Also Published As

Publication number Publication date
CN114445754A (zh) 2022-05-06
US20250118338A1 (en) 2025-04-10

Similar Documents

Publication Publication Date Title
WO2023142913A1 (zh) 视频处理方法、装置、可读介质及电子设备
CN110969012B (zh) 文本纠错方法、装置、存储介质及电子设备
WO2022252881A1 (zh) 图像处理方法、装置、可读介质和电子设备
WO2022247562A1 (zh) 多模态数据检索方法、装置、介质及电子设备
WO2023083142A1 (zh) 分句方法、装置、存储介质及电子设备
CN115052188B (zh) 一种视频剪辑方法、装置、设备及介质
CN112364829B (zh) 一种人脸识别方法、装置、设备及存储介质
WO2022161122A1 (zh) 一种会议纪要的处理方法、装置、设备及介质
WO2023279843A1 (zh) 内容搜索方法、装置、设备和存储介质
CN114697761B (zh) 一种处理方法、装置、终端设备及介质
CN112287206A (zh) 信息处理方法、装置和电子设备
CN114697760A (zh) 一种处理方法、装置、电子设备及介质
WO2022037419A1 (zh) 音频内容识别方法、装置、设备和计算机可读介质
WO2023000782A1 (zh) 获取视频热点的方法、装置、可读介质和电子设备
CN111767431A (zh) 用于视频配乐的方法和装置
CN113486212A (zh) 搜索推荐信息的生成和展示方法、装置、设备及存储介质
CN114780792A (zh) 一种视频摘要生成方法、装置、设备及介质
CN114880458A (zh) 书籍推荐信息的生成方法、装置、设备及介质
CN113033707B (zh) 视频分类方法、装置、可读介质及电子设备
CN115328362A (zh) 书籍信息显示方法、装置、设备和存储介质
CN114697763B (zh) 一种视频处理方法、装置、电子设备及介质
WO2023195914A2 (zh) 处理方法、装置、终端设备及介质
CN114117127B (zh) 视频生成方法、装置、可读介质及电子设备
WO2023130925A1 (zh) 字体识别方法、装置、可读介质及电子设备
CN115240711B (zh) 音频质量分析方法、装置、电子设备及计算机可读存储介质

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: 23745798

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18832049

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23745798

Country of ref document: EP

Kind code of ref document: A1

WWP Wipo information: published in national office

Ref document number: 18832049

Country of ref document: US