Video processing method, device, equipment and storage medium

Abstract

Embodiments of the present disclosure relate to methods, devices, equipment, and storage media for video editing. The method proposed herein includes: determining a video segment from the first video based on access information of the first video, where the access information indicates the distribution of access statistics of the first video over time; determining semantic continuity between the video segment and the first video; and generating a second video by appending the video segment to the front of the first video in response to the semantic continuity being greater than a threshold. Based on the above approach, embodiments of the present disclosure can increase the attractiveness of a video to a user by appending a specific segment from the video to the front of the video.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for video processing. Background Art

[0002] With the development of computer technology, various video contents have become one of the main ways for people to obtain content. Especially for some short video contents, people usually use the initial playback of some content to determine whether they are interested in it and decide whether to continue watching the subsequent content or switch to other video content. Summary of the Invention

[0003] In a first aspect of the present disclosure, a method for video processing is provided. The method includes: determining a video segment from the first video based on access information of the first video, wherein the access information indicates a distribution of access statistics of the first video over time; determining semantic continuity between the video segment and the first video; and, in response to the semantic continuity being greater than a threshold, generating a second video by appending the video segment to the front of the first video.

[0004] In a second aspect of the present disclosure, a device for video processing is provided. The device includes: a determination module configured to determine a video segment from the first video based on access information of the first video, where the access information indicates a distribution of access statistics of the first video over time; a judgment module configured to determine semantic continuity between the video segment and the first video; and an editing module configured to generate a second video by appending the video segment to the front of the first video in response to the semantic continuity being greater than a threshold.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram illustrating an example environment in which embodiments according to the present disclosure may be implemented;

[0010] Figure 2 A flowchart illustrating an example process for video processing according to some embodiments of the present disclosure is shown;

[0011] Figure 3 A schematic structural block diagram of an apparatus for video processing according to some embodiments of the present disclosure is shown; and

[0012] Figure 4 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0013] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0014] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0015] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0016] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects shall comply with the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms them. Accordingly, when implementing the various embodiments of the present disclosure, the types, scope of use, and usage scenarios of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method may vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0017] If this specification and the solutions in the examples involve the processing of personal information, such processing will be done only with a legitimate basis (such as with the consent of the subject of personal information or as necessary for the performance of a contract) and only within the prescribed or agreed scope. A user's refusal to process personal information other than that required for basic functions will not affect the user's use of basic functions.

[0018] As briefly mentioned above, the initial content of a video has a significant impact on whether users continue watching. Traditionally, the most appealing part of a video isn't always located at the beginning, which can lead to people missing it. Furthermore, manually selecting highlights from videos is labor-intensive and can be inaccurate.

[0019] Embodiments of the present disclosure provide a scheme for video processing. According to this scheme, a video segment can be determined from a first video based on access information of the first video, where the access information indicates the distribution of access statistics of the first video over time. Furthermore, semantic continuity between the video segment and the first video can be determined. If the semantic continuity exceeds a threshold, a second video can be generated by appending the video segment to the first video.

[0020] In this way, the embodiments of the present disclosure can automatically identify video clips that the user may be interested in from the video, and if such video clips have good semantic continuity with the original video, append the video clips to the original video. As a result, the embodiments of the present disclosure can improve the appeal of the video content's opening credits and ensure the semantic continuity of the video content.

[0021] Various example implementations of this solution are described in detail below in conjunction with the accompanying drawings.

[0022] Sample Environment

[0023] Figure 11 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1 As shown, environment 100 may include a processing device 120. Processing device 120 may include any suitable electronic device, examples of which may include, but are not limited to, a mobile device, a tablet computer, a laptop computer, a desktop computer, a cloud server, an edge computing device, and the like.

[0024] like Figure 1 As shown, the processing device 120 can obtain the first video 110 and access information 130 of the first video 110. In some embodiments, the first video 110 can be a video published by a creator. For example, the first video 110 can include an advertisement video. Such an advertisement video can receive a user click operation and perform corresponding interaction, such as guiding the user to a corresponding promotional page or purchase page.

[0025] In some embodiments, the access information 130 may indicate the distribution of access statistics of the first video 110 over time. Such access statistics may include, for example, the user click-through rate and / or user churn rate of the first video 110. It should be understood that if the user click-through rate of a video at a certain moment is high, it may indicate that users are more interested in the content at that moment; conversely, if the user churn rate of a video at a certain moment is high (i.e., the proportion of users who stop watching the video), it may indicate that users are less interested in the content at that moment.

[0026] like Figure 1 As shown, the processing device 120 may determine a video segment 140 from the first video 110 according to the access information 130 of the first video 110. Such a video segment 140 may be part of the content of the first video 110, or may be generated based on part of the content of the first video 110.

[0027] Furthermore, the processing device 120 may determine semantic continuity between the video segment 140 and the first video 110 , and if the semantic continuity is above a threshold, append the video segment 140 to the first video 110 to generate the second video 150 .

[0028] For example, the video segment 140 can be edited as the beginning of the second video 150. The process of generating the video segment 140 and determining the semantic continuity will be described below in conjunction with Figure 2 Detailed description.

[0029] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0030] Example Process

[0031] Figure 2 FIG2 is a flow chart showing an example process 200 for video processing according to some embodiments of the present disclosure. The process 200 may be implemented at the processing device 120. Figure 1 2. Process 200 will be described.

[0032] like Figure 2 As shown, at block 210 , the processing device 120 determines a video segment 140 from the first video 110 based on access information 130 of the first video 110 , wherein the access information 130 indicates a distribution of access statistics of the first video 110 over video time.

[0033] In some embodiments, processing device 120 may obtain a first video 110. Such first video 110 may be, for example, a previously published video. For example, processing device 120 may determine first video 110 from the video collection based on the number of views and / or clicks on the videos in the video collection. For example, processing device 120 may obtain first video 110 from a publicly accessible video library based on the number of views and / or clicks on the videos, and the number of views exceeding a predetermined number.

[0034] Furthermore, the processing device 120 may also obtain access information 130 of the first video 110. Such access information 130 is used to indicate the distribution of the user's interest in the first video 110 over the video time.

[0035] Taking the first video 110 as an advertisement video as an example, the access information 130 may include, for example, the distribution of the video click rate and / or video loss rate of the first video 110 along with the video time of the first video 110 .

[0036] To identify video segments 140 from the first video 110 that the user may be more interested in, the processing device 120 can determine the time interval corresponding to the segments based on the access statistics. Specifically, the processing device 120 can determine a target time for the first video 110 based on the access information 130, where the access statistics for the first video at the target time meet a threshold requirement. For example, such a target time can be the time when the user click-through rate of the first video 110 is the highest and / or the time when the user churn rate is the lowest.

[0037] Furthermore, in order to ensure that the determined video segment is semantically continuous, the processing device 120 may also determine a time interval associated with the target moment based on semantic recognition of the text content of the first video 110 , wherein the text segment corresponding to the time interval has continuous semantics.

[0038] For example, the processing device 120 may recognize the speech of the first video 110 to obtain its text content. Additionally, the processing device 120 may obtain a text segment associated with the target moment and having continuous semantics based on semantic recognition of the text content.

[0039] In some embodiments, the time length of such a text segment (ie, the length of the determined time interval) needs to meet a preset length range. For example, the processing device 120 may determine a time interval of 3 to 7 seconds based on the target time and semantic information.

[0040] In some embodiments, in addition to considering semantic continuity, the processing device 120 may also add punctuation to the text content, and determine a single complete sentence associated with the target moment based on the text content after the punctuation.

[0041] Based on this approach, the embodiments of the present disclosure can ensure that the text content corresponding to the determined time interval is semantically continuous and complete.

[0042] Furthermore, the processing device 120 may obtain a video segment 140 corresponding to the time interval. For example, the processing device 120 may directly determine the segment of the first video 110 corresponding to the time interval as the video segment 140.

[0043] In some embodiments, in order to ensure that the generated video segment 140 is visually continuous, the processing device 120 can also use an appropriate storyboard model (for example, the transnetv2 model) to divide the first video 110 into a group of storyboard segments, each of which can, for example, correspond to a different storyboard.

[0044] Additionally, if the determined time interval is associated with multiple storyboard segments, the processing device 120 may generate a video segment based on the multiple storyboard segments. For example, the processing device 120 may generate the video segment 140 by combining the multiple storyboard segments. Alternatively, the processing device 120 may also add a smoothing effect, such as a fade-in or fade-out, between the multiple storyboard segments to construct the video segment 140.

[0045] In this way, the embodiment of the present disclosure can provide a semantically continuous, semantically complete, and frame-continuous video segment 140 .

[0046] In some embodiments, if the determined target time falls within the target time range, the processing device 120 may not generate the video segment 140. Such a target time range may, for example, include a first preset duration associated with the start time of the first video 110 (e.g., the first five seconds of the video), and / or a second preset duration associated with the end time of the first video 110 (e.g., the last five seconds of the video).

[0047] On the contrary, if the determined target moment does not fall within the target time range, the processing device 120 may perform determination of a time interval to generate the video segment 140 .

[0048] Continue to refer Figure 2 At block 220 , the processing device 120 determines semantic continuity between the video segment 140 and the first video 110 .

[0049] In some embodiments, to ensure that the added header has good continuity with the original video, the processing device 120 may determine semantic continuity based on features of the video segment 140 and features of the first video 110 .

[0050] In some embodiments, the processing device 120 may process features of the video clip 140 and the first video 110 using an analysis model to determine semantic continuity, where the features include at least one of the following: visual features of the video, speech features of the video, or text features of the video.

[0051] Exemplarily, the processing device 120 may utilize an appropriate machine learning model as an analysis model, and may use the visual features, speech features, text features and / or other appropriate features or feature combinations of the two videos as inputs to the analysis model to determine the semantic continuity between the two videos.

[0052] In some embodiments, to train a machine learning model to be capable of determining semantic continuity in a video, a suitable training device (which may be the same as or different from the processing device 120) may analyze the model using sample data. Such sample data may include, for example, positive sample data and / or negative sample data.

[0053] In some embodiments, such positive sample data may include, for example, a first video segment and a second video segment, wherein the first video segment is related to the first semantic continuous shot of the reference video, and the second video segment is another video segment in the reference video different from the first video segment.

[0054] For example, the training device can extract semantically continuous shots from a published reference video based on the storyboard model. Furthermore, the training device can identify the video segment corresponding to the shot and other video segments of the reference video as positive sample data, indicating that the two video segments are semantically continuous.

[0055] In some embodiments, such negative sample data may include a third video segment and a fourth video segment from different videos to indicate that such video segments are discontinuous.

[0056] Based on this approach, the embodiments of the present disclosure can automatically and efficiently determine the semantic continuity between the generated video clip and the original video content.

[0057] At block 230 , in response to the semantic continuity being above the threshold, the processing device 120 generates the second video 150 by appending the video segment 140 to the front of the first video 110 .

[0058] Exemplarily, the analysis model may output semantic continuity as a continuous numerical value (e.g., a value between 0 and 1 to indicate its semantic continuity), or may output semantic continuity as a discrete numerical value (e.g., 0 represents discontinuity and 1 represents continuity).

[0059] If such semantic continuity is above a threshold (eg, the continuous value is greater than a certain threshold value, the discrete value is greater than 0), the processing device 120 may determine that the generated video segment 140 is suitable for being appended to the first video 110 .

[0060] Furthermore, the processing device 120 generates the second video 150 by editing the video clip 140 before the first video 110. Thus, the generated second video 150 can have a title content that is more attractive to users, and does not affect the continuous viewing experience of the second video 150.

[0061] In some embodiments, the processing device 120 may further publish the edited second video 150 .

[0062] Therefore, the embodiments of the present disclosure can utilize delayed knowledge of the video (for example, access information of the video) to perform intelligent editing of the video, thereby creating video content that can be more attractive to users and ensuring the viewing experience of such video content.

[0063] Example devices and equipment

[0064] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes.

[0065] Figure 3 FIG2 shows a schematic structural block diagram of an apparatus 300 for video processing according to some embodiments of the present disclosure. The apparatus 300 may be implemented as or included in the processing device 120. Each module / component in the apparatus 300 may be implemented by hardware, software, firmware, or any combination thereof.

[0066] The apparatus 300 includes a determining module 310 configured to determine a video segment from the first video based on access information of the first video, where the access information indicates a distribution of access statistics of the first video over video time.

[0067] The apparatus 300 further includes a determination module 320 configured to determine semantic continuity between the video segment and the first video.

[0068] In addition, the apparatus 300 further includes an editing module 330 configured to generate a second video by appending a video segment to the front of the first video in response to the semantic continuity being higher than a threshold.

[0069] In some embodiments, the determination module 310 is further configured to: determine the target moment of the first video based on the access information, wherein the access statistics of the first video at the target moment meet the threshold requirements; determine the time interval associated with the target moment based on the semantic recognition of the text content of the first video, wherein the text segment corresponding to the time interval has continuous semantics; and obtain the video segment corresponding to the time interval.

[0070] In some embodiments, the determination module 310 is further configured to: divide the first video into a group of storyboard segments using a storyboard model; and generate a video segment based on the multiple storyboard segments in response to the time interval being associated with the multiple storyboard segments.

[0071] In some embodiments, the length of the time interval is within a preset length range.

[0072] In some embodiments, the text segment corresponds to a single complete sentence in the text content, and the single complete sentence is determined based on punctuating the text content.

[0073] In some embodiments, the determination module 310 is further configured to: determine a time interval in response to the target moment not falling within the target time range, wherein the target time range includes: a first preset duration related to the start moment of the first video, and / or a second preset duration related to the end moment of the first video.

[0074] In some embodiments, the judgment module 320 is further configured to: use the analysis model to process features of the video clip and the first video to determine semantic continuity, where the features include at least one of the following: visual features of the video, voice features of the video, or text features of the video.

[0075] In some embodiments, the analysis model is trained based on the following sample data: positive sample data, including a first video clip and a second video clip, where the first video clip is related to the first semantic continuous shot of a reference video, and the second video is another video clip in the reference video that is different from the first video clip; or negative sample data, including a third video clip and a fourth video clip from different videos.

[0076] In some embodiments, the access statistics indicate at least: a video click-through rate and / or a user churn rate.

[0077] In some embodiments, the apparatus 300 further includes a video selection module configured to determine a first video from the video set based on the number of plays and / or clicks of the videos in the video set.

[0078] In some embodiments, the first video comprises an advertisement video.

[0079] Figure 4 4 shows a block diagram of an electronic device 400 in which one or more embodiments of the present disclosure may be implemented. Figure 4 The illustrated electronic device 400 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 4 The electronic device 400 shown can be used to implement Figure 1 processing device 120.

[0080] like Figure 4 As shown, electronic device 400 is in the form of a general electronic device. Components of electronic device 400 may include, but are not limited to, one or more processors or processing units 410, memory 420, storage device 430, one or more communication units 440, one or more input devices 450, and one or more output devices 460. Processing unit 410 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 420. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 400.

[0081] The electronic device 400 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 400, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 420 can be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 430 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data (e.g., training data for training) and can be accessed within the electronic device 400.

[0082] The electronic device 400 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 4As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. Memory 420 may include a computer program product 425 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0083] The communication unit 440 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 400 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 400 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0084] Input device 450 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 460 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 400 may also communicate with one or more external devices (not shown) via communication unit 440 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with electronic device 400, or with any device that allows electronic device 400 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0085] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0086] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0087] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0088] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0089] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0090] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A video processing method, comprising: determining a video segment from the first video based on access information of the first video, the access information indicating a distribution of access statistics of the first video over video time; determining semantic continuity between the video segment and the first video; as well as In response to the semantic continuity being higher than a threshold, a second video is generated by appending the video segment to the front of the first video, wherein the video segment is a starting segment of the second video.

2. The method of claim 1 , wherein determining the video segment comprises: Determining a target time of the first video based on the access information, wherein the access statistics of the first video at the target time meet a threshold requirement; Determining a time interval associated with the target moment based on semantic recognition of text content in the first video, wherein a text segment corresponding to the time interval has continuous semantics; and The video segment corresponding to the time interval is obtained.

3. The method according to claim 2, wherein obtaining the video segment corresponding to the time interval comprises: Using a storyboard model, dividing the first video into a group of storyboard segments; as well as In response to the time interval being associated with a plurality of storyboard segments, the video segment is generated based on the plurality of storyboard segments. The method according to claim 2 , wherein the length of the time interval is within a preset length range. 5 . The method according to claim 2 , wherein the text segment corresponds to a single complete sentence in the text content, the single complete sentence being determined based on adding punctuation to the text content.

6. The method of claim 2, wherein determining the time interval comprises: In response to the target moment not falling within the target time range, the time interval is determined, wherein the target time range includes: a first preset duration related to the start moment of the first video, and / or a second preset duration related to the end moment of the first video.

7. The method of claim 1 , wherein determining semantic continuity between the video segment and the first video comprises: The semantic continuity is determined by processing features of the video clip and the first video using an analysis model, wherein the features include at least one of the following: visual features of the video, voice features of the video, or text features of the video.

8. The method according to claim 7, wherein the analysis model is trained based on the following sample data: Positive sample data includes a first video segment and a second video segment, wherein the first video segment is related to the first semantic continuous shot of a reference video, and the second video segment is another video segment in the reference video that is different from the first video segment; or The negative sample data includes a third video clip and a fourth video clip from different videos.

9. The method according to claim 1, wherein the access statistics at least indicate: video click rate and / or user churn rate.

10. The method according to claim 1, further comprising: A first video is determined from the video collection based on the number of views and / or clicks of the videos in the video collection. The method of claim 1 , wherein the first video comprises an advertisement video.

12. A device for video processing, comprising: a determining module configured to determine a video segment from a first video based on access information of the first video, wherein the access information indicates a distribution of access statistics of the first video over video time; a determination module, configured to determine semantic continuity between the video clip and the first video; as well as The editing module is configured to generate a second video by appending the video segment to the front of the first video in response to the semantic continuity being higher than a threshold, wherein the video segment is a starting segment of the second video.

13. An electronic device comprising: at least one processing unit; as well as At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processing unit.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 11.

Images