Video processing method and device, equipment and medium

Abstract

The invention provides a video processing method and device, equipment and a medium, and relates to the technical field of video processing, in particular to the technical field of artificial intelligence and video content embedding. According to the implementation scheme, the method comprises the following steps: acquiring a to-be-processed original video and video content description information of the original video; determining a target area of each video frame in a plurality of video frames based on background areas of the plurality of video frames of the original video; determining a target text based on the video content description information and the sizes of the target areas of the plurality of video frames; and embedding the target text into the original video based on the positions of the target areas of the plurality of video frames.

Description

Technical Field

[0001] The present disclosure relates to the field of video processing technology, in particular to the field of artificial intelligence and video content embedding technology, and specifically to a video processing method, device, electronic device, computer-readable storage medium and computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] Video is an important information medium with rich media features that can provide an immersive experience. With the development of information technology, it is becoming more and more popular among users. Subtitles are explicit language included in videos and play an important role in conveying information to users. However, conventional subtitles are usually used to present dialogue content or simple and intuitive narration content, and there are relatively few explanations for video content.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a video processing method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0006] According to one aspect of the present disclosure, a video processing method is provided, comprising: obtaining an original video to be processed and video content description information of the original video; determining a target area of ​​each of the multiple video frames based on background areas of the multiple video frames of the original video; determining a target text based on the video content description information and the size of the target areas of the multiple video frames; and embedding the target text into the original video based on the positions of the target areas of the multiple video frames.

[0007] According to another aspect of the present disclosure, a video processing device is provided, including: an acquisition unit, configured to acquire an original video to be processed and video content description information of the original video; a first determination unit, configured to determine a target area of ​​each of the multiple video frames based on a background area of ​​the multiple video frames of the original video; a second determination unit, configured to determine a target text based on the video content description information and the size of the target area of ​​the multiple video frames; and an embedding unit, configured to embed the target text into the original video based on the position of the target area of ​​the multiple video frames.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the above-mentioned video processing method.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned video processing method.

[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program can implement the above-mentioned video processing method when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, text information for describing the video content may be added to the video to enhance the user's experience of watching the video.

[0012] It should be understood that the content described in this section is not intended to identify the key 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

[0013] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an exemplary embodiment of the present disclosure;

[0015] Figure 2A flowchart of a video processing method according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 3 A schematic diagram showing a video processing process according to an exemplary embodiment of the present disclosure is shown;

[0017] Figure 4 A structural block diagram of a video processing device according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0020] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0021] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0022] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0024] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable the video processing method to be performed.

[0025] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0026] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0027] The user may use client devices 101, 102, 103, 104, 105 and / or 106 to send raw videos to be processed or video processing requests. The client devices may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0028] Client devices 101, 102, 103, 104, 105 and / or 106 may include various categories of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various categories and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (eg, email applications), short message service (SMS) applications, and may use various communication protocols.

[0029] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0030] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0031] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0032] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0033] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0034] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different categories. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0035] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different categories of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0036] Figure 1The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0037] Video is an important information medium with rich media features that can provide an immersive experience. With the development of information technology, it is becoming more and more popular among users. Subtitles are explicit language included in videos and play an important role in conveying information to users. However, conventional subtitles are usually used to present dialogue content or simple and intuitive narration content, and there are relatively few explanations for video content. In order to provide users with video commentary content, related technologies usually extract or generate video summary information, and then display the video summary in the video sidebar. This method fails to embed the summary content in the video and cannot guarantee the effective display of the commentary content.

[0038] Based on this, the present disclosure provides a video processing method, which determines a target area in the video background area that can be used to embed text, and then determines the target text according to the video content description information and the size of the target area to ensure that the length of the target text is compatible with the size of the target area, so that the embedded text can be used to introduce the video content while avoiding the impact of the embedded text on the display of the main object in the video, that is, it is realized to add descriptive content in the video background, thereby improving the user's experience of watching the video.

[0039] Figure 2 FIG. 2 shows a flow chart of a video processing method 200 according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the method 200 includes:

[0040] Step S201, obtaining an original video to be processed and video content description information of the original video;

[0041] Step S202: determining a target area of ​​each video frame in the multiple video frames based on the background areas of the multiple video frames of the original video;

[0042] Step S203, determining the target text based on the video content description information and the size of the target area of ​​the multiple video frames; and

[0043] Step S204: embedding the target text into the original video based on the positions of the target areas of the multiple video frames.

[0044] By applying the above-mentioned video processing method 200, a target area for embedding text is determined in the background area of ​​the video, and the target text is determined according to the video content description information and the size of the target area to ensure that the length of the target text matches the size of the target area. The target text is embedded in the video based on the position of the target area, that is, the target text can be used to introduce the video content while avoiding the embedded text affecting the display of the main object in the video, so as to enhance the user's viewing experience.

[0045] According to some embodiments, obtaining the original video to be processed and the video content description information of the original video in step S201 includes: obtaining the original video; identifying the text content in the original video, wherein the text content includes image text included in multiple video frames of the original video or audio text included in the original video; and determining the video content description information based on the text content. Thus, the video content description information can be determined based on the image text or audio text contained in the video to more comprehensively and accurately describe the content of the video. Based on this, a more accurate target text can be obtained to introduce the content of the video to the user and enhance the user's viewing experience.

[0046] In some examples, the video frames of the original video may be recognized using OCR (Optical Character Recognition) technology to obtain image text, and the audio content of the original video may be recognized using ASR (Automatic Speech Recognition) technology to obtain audio text.

[0047] It is understandable that the image text or audio text obtained by identifying the original video may include the position information of each text in the original video. In this case, when the text content recognition result includes both the image text and the audio text, the text content fusion can be performed based on the content and position information of the image text and the audio text. In one example, the image text and the audio text can be subjected to correlation analysis, for example, the same character proportion can be calculated based on the image text and the audio text, and the two are regarded as the same content for fusion when the text correlation exceeds a preset threshold. For the image text and the audio text with low correlation, processing rules can be pre-set, for example, the two can be spliced ​​to obtain a fused text, or different priorities can be set for the image text and the audio text, and a text content with a higher priority can be selected when a certain image text and a certain audio text correspond to the same timeline position of the original video.

[0048] According to some embodiments, determining the target area of ​​each of the multiple video frames in step S202 includes: dividing the original video into multiple video segments, wherein the multiple video frames included in each video segment include the same main object; for each of the multiple video segments, determining at least one target frame from the video segment; determining a background area of ​​the at least one target frame that does not include the main object; and determining the target area of ​​each video frame in the video segment based on the background area of ​​the at least one target frame. By dividing the original video into multiple video segments, performing background detection and determining the target area only for the target frame in each video segment, and then determining the target areas of all video frames in the video segment, the amount of calculation can be reduced and the processing efficiency can be improved.

[0049] According to some embodiments, dividing the original video into multiple video segments includes: performing shot analysis on the original video to determine multiple shots included in the original video; and determining the multiple video segments based on the multiple shots. Generally speaking, the size and position of the main objects of the video frames in the same shot are relatively similar. Determining the video shots through physical shot analysis can more conveniently determine multiple video segments and improve processing efficiency.

[0050] By performing physical shot analysis on the original video, the original video can be segmented into a series of temporally continuous shots, each shot being taken continuously by a camera. This segmentation is based on the physical properties of the video (such as the continuity of the video frame images). In some examples, physical shot analysis can be implemented using a transnet algorithm based on three-dimensional convolution. The convolution kernel of the three-dimensional convolution operation not only processes the video frame images in the spatial dimension, but also extracts the features of the video frame sequence in the dimension of the time axis, thereby more accurately identifying the shot boundaries in the video based on the spatial information and temporal information of the video.

[0051] In some examples, the step of dividing the original video into multiple video segments can also be implemented using other methods, such as performing video semantic analysis on the original video, and then dividing the original video based on the semantic analysis results, so that multiple video frames in each of the divided video segments correspond to the same semantic content, that is, include the same main object.

[0052] After the original video is divided into multiple video segments, since the multiple video frames in each video segment include the same main object, the target area of ​​each video frame in the video segment can be determined based on the background detection results of one or more target frames in each video segment, thereby reducing the calculation amount of background detection and improving processing efficiency.

[0053] According to some embodiments, determining at least one target frame from the video clip includes: in response to determining that the video clip includes multiple video frames, performing a frame extraction operation on the video clip based on the target frame interval to obtain multiple target frames. By using the interval frame extraction operation to determine the target frame, it is possible to ensure that the multiple target frames are evenly distributed in the video clip, so that the background detection results of the multiple target frames can accurately indicate the size and position of the main object in the video clip, thereby accurately determining the target area of ​​each video frame, and avoiding the embedded text from affecting the display of the main content of the video.

[0054] In some examples, the above-mentioned operation of determining at least one target frame from each video clip may also be implemented based on other methods, for example, one or more target frames in the video clip may be randomly extracted to determine the target frame more conveniently and efficiently, thereby further improving processing efficiency.

[0055] In some examples, after determining the target frame in each video clip, salient region detection may be performed on each target frame to distinguish a foreground region (ie, a region including a main object) from a background region in the target frame.

[0056] In some examples, other methods may be used to determine the background area of ​​the target frame in the video clip, for example, background detection may be performed based on background difference method, color space conversion method, etc. As long as the background area in the video image can be determined, the present disclosure does not limit the specific implementation method of background detection.

[0057] According to some embodiments, determining the target area of ​​each video frame in the video clip based on the background area of ​​the at least one target frame includes: determining the intersection of the background areas of the multiple target frames; and determining the target area of ​​each video frame in the video clip based on the intersection. By determining the target area based on the intersection of the background areas of the multiple target frames, it is possible to avoid including the main object in the target area of ​​each video frame, thereby avoiding the embedded text from affecting the display of the main object, and improving the user's experience of watching the video.

[0058] In some examples, the target area of ​​each video frame may be determined by other methods. For example, a correlation analysis may be performed on the background areas of multiple target frames in each video clip, and the target area of ​​each video frame in the video clip is determined based on the intersection of the background areas of a group of target frames with higher similarity, so as to maximize the area of ​​the target area, facilitate embedding more video commentary text based on the target area, so as to provide users with more comprehensive video commentary content and enhance the user's video viewing experience.

[0059] According to some embodiments, method 200 further includes: for each video segment in the multiple video segments, based on the background area and area shape condition of at least one target frame in the video segment, determining a candidate area set of the video segment, wherein the candidate area set includes at least one candidate area that satisfies the area shape condition; performing the following update operation on the candidate area set in the multiple video segments: in response to determining that the first candidate area and the second candidate area meet the target condition, determining a fusion area based on the first candidate area and the second candidate area, wherein the target condition includes: the first video segment corresponding to the first candidate area is adjacent to the second video segment corresponding to the second candidate area, and the correlation between the first candidate area and the second candidate area is not less than a correlation threshold; and replacing the first candidate area and the second candidate area with the fusion area; wherein determining the target area of ​​each video frame in the video segment based on the background area of ​​the at least one target frame includes: determining the target area from the updated candidate area set corresponding to the video segment. By first determining the candidate area set based on the area shape condition and then fusing the candidate areas with higher correlation in the adjacent video segments, the fused candidate areas can represent the background areas of more video segments. By selecting the target area based on the fused candidate area set, the video frames in multiple video clips can correspond to the same target area, thereby reducing the jump of the target area when the video clips are switched, so that the embedded text can be stably displayed in the same position, thereby improving the text display effect.

[0060] In some examples, the region shape condition may include a restriction on the region shape type, such as limiting the region shape to a rectangle, and the region shape condition may also include a restriction on the region shape size, such as limiting the aspect ratio of the rectangle. By selecting candidate regions based on the region shape condition, the probability of successful fusion of candidate regions can be increased, so that the fused candidate regions correspond to a larger number of video clips, that is, the video frames in multiple video clips can correspond to the same target region, reducing the jump in the target text embedding position and improving the display effect.

[0061] For ease of understanding, the following example is used to illustrate how to determine and update the candidate region set for each video segment:

[0062] In this example, the region shape condition may indicate a plurality of rectangular shapes with different aspect ratios, for example, including an A-size rectangle, a B-size rectangle, and a C-size rectangle. In this example, the original video may be divided into four video segments, namely, segment 1, segment 2, segment 3, and segment 4. Based on the above region shape condition, for example, the following candidate region sets may be determined for the four video segments:

[0063] Segment 1: Candidate region 1A, candidate region 1B, candidate region 1C;

[0064] Segment 2: Candidate region 2A, Candidate region 2B;

[0065] Segment 3: candidate region 3A, candidate region 3B, candidate region 3C;

[0066] Segment 4: Candidate region 4B, candidate region 4C.

[0067] After determining the candidate region set corresponding to each video clip, you can try to perform region fusion operations on multiple candidate region sets. For example, when candidate region 1A, candidate region 2A, and candidate region 3A can be fused into candidate region 123A, candidate region 1B and candidate region 2B can be fused into candidate region 12B, and candidate region 3B and candidate region 4B can be fused into candidate region 34B, the following updated candidate region set can be obtained:

[0068] Segment 1: candidate region 123A, candidate region 12B, candidate region 1C;

[0069] Segment 2: candidate region 123A, candidate region 12B;

[0070] Segment 3: candidate region 123A, candidate region 34B, candidate region 3C;

[0071] Segment 4: Candidate region 34B, candidate region 4C.

[0072] On this basis, the target area corresponding to the video clip can be selected from the updated candidate area set corresponding to each video clip. Since the updated candidate area sets of multiple video clips include the same candidate areas, the probability that the same target area can correspond to multiple video clips is increased, so that the target text corresponds to the same embedded position in multiple video clips, thereby improving the text display effect.

[0073] According to some embodiments, the correlation between the first candidate region and the second candidate region includes an intersection-over-union ratio between the first candidate region and the second candidate region. Thus, the intersection-over-union ratio can be used to more accurately indicate the spatial correlation of the candidate regions, thereby avoiding excessive deviation in the fusion result and affecting the text display effect.

[0074] In some examples, the correlation between the first candidate region and the second candidate region may also be calculated based on other methods, for example, the similarity between the two may be calculated based on various dimensions such as shape, size, similar position, etc. As long as the correlation between the spatial features of the first candidate region and the second candidate region can be determined, the present disclosure does not limit the specific method of calculating the correlation.

[0075] According to some embodiments, determining the fusion region based on the first candidate region and the second candidate region includes: determining a union of the first candidate region and the second candidate region; and determining the fusion region based on the union. When the intersection-over-union ratio of the candidate regions meets a preset condition, fusion can be performed based on the union to obtain a fusion region as large as possible, thereby increasing the display area of ​​the target text.

[0076] In some examples, regional fusion can also be achieved based on other methods. For example, the fusion area can be determined based on the intersection of the first candidate area and the second candidate area, thereby avoiding including the main object in the target area of ​​the video frame and avoiding embedded text affecting the display of the main object, so as to enhance the user's video viewing experience.

[0077] According to some embodiments, method 200 further includes: for each candidate area in the updated multiple candidate area sets, based on the duration of at least one video clip corresponding to the candidate area, determining the residence time of the candidate area, wherein determining the target area from the updated candidate area set corresponding to the video clip includes: determining the candidate area with the longest residence time in the updated candidate area set corresponding to the video clip as the target area. By selecting the target area based on the residence time of the candidate area, the target text is stably displayed using the target area with the longest residence time, thereby improving the text display effect.

[0078] In some examples, determining the target region from the updated candidate region set corresponding to the video clip can also be implemented based on the following method: determining the candidate region with the largest number of corresponding video clips in the updated candidate region set corresponding to the video clip as the target region. By applying this method to select the target region, the number of jumps in the target text embedding position can be reduced, and the stability of text display can be improved.

[0079] According to some embodiments, determining the target text based on the video content description information and the size of the target area of ​​the multiple video frames in step S203 includes: for each video segment in the multiple video segments, determining the segment description information of the video segment based on the video content description information; and determining the segment text of the video segment based on the segment description information and the size of the target area of ​​the video segment; and wherein, embedding the target text into the original video based on the position of the target area of ​​the multiple video frames in step S204 includes: embedding the segment text of the video segment into the video segment based on the position of the target area of ​​each video segment. Thus, different segment description information can be determined for different video segments and displayed separately, effectively compressing the length of the target text, improving the display effect, and facilitating the user to view the description text accordingly as the segment switches when watching the video, thereby improving the user's video viewing experience.

[0080] In some examples, when the target area is determined based on the updated candidate area set described above, that is, the same target area corresponds to multiple video clips, the multiple video clips can be divided into multiple clip sets based on the target area, and the target text can be determined based on the clip description information of one or more video clips in the clip set.

[0081] In one example, when the original video includes four video segments, segment 1, segment 2, segment 3, and segment 4, and the target regions corresponding to the four video segments are region M, region M, region N, and region N, respectively, segment 1 and segment 2 corresponding to region M can be taken as segment set a, and segment 3 and segment 4 corresponding to region N can be taken as segment set b. On this basis, the segment description information of segment 1 and segment 2 can be combined as the target text embedded in region M, and the segment description information of segment 3 and segment 4 can be combined as the target text embedded in region N.

[0082] In some examples, a large-scale language model can be used to extract key information and perform semantic segmentation on the segment description information of multiple video segments to obtain description information corresponding to each video segment or each segment set, that is, the natural language processing capabilities of the large-scale language model are used to improve the efficiency of generating description information.

[0083] According to some embodiments, determining the segment description information of the video segment based on the video content description information includes: inputting multiple video frames of the video segment into a visual language model; and determining the segment description information based on an output result of the visual language model and the video content description information, wherein the visual language model is trained using sample data annotated with reference segment description information.

[0084] By using a visual language model (VLM) to determine the segment description information of a video segment, the semantic parsing capability of the VLM model can be fully utilized to more efficiently determine the segment description information that can indicate the semantic content of the video segment.

[0085] In some examples, the input content of the VLM model may also include one or more video segments preceding each video segment, so that the VLM model can more accurately parse the semantic content of the video segment.

[0086] In some examples, information fusion can also be performed based on the video clip semantic analysis results output by the VLM model and the video content description information (such as the image text or audio text contained in the video described above) to obtain more comprehensive and accurate video clip description information.

[0087] According to some embodiments, method 200 further includes: for each video segment in the multiple video segments, determining a text display duration based on the segment text of the video segment, wherein embedding the segment text of the video segment into the video segment based on the position of the target area of ​​each video segment includes: determining multiple embedded frames from the video segment based on the text display duration; and embedding the segment text of the video segment into the multiple embedded frames based on the position of the target area of ​​the video segment. By determining the text display duration based on the segment text, it is possible to avoid the target text used to describe the video content from staying continuously, making it easier for users to view the target text and the original video content, thereby improving the user's experience of watching the video.

[0088] In some examples, the starting time point of each video segment can be recorded in the step of segmenting the original video to obtain multiple video segments, and on this basis, multiple embedded frames can be selected based on the starting time point of each video segment. For example, when the text display duration is 10 seconds, multiple embedded frames corresponding to the duration of 10 seconds can be selected starting from the starting time point of the video segment.

[0089] In some examples, the text display duration may be determined based on the number of words in the text segment and a preset reading speed.

[0090] According to some embodiments, determining the target text based on the video content description information and the size of the target area of ​​the multiple video frames in step S203 includes: determining a word count threshold based on the size of the target area of ​​the multiple video frames; and determining the target text based on the video content description information and the word count threshold. By determining the word count threshold based on the size of the target area, the target text that meets the word count condition is obtained, so as to avoid the target text from exceeding the target area, that is, to avoid the target text from affecting the main object of the video.

[0091] In some examples, when the original video is divided into multiple video segments and each video segment corresponds to different segment description information, the word count threshold can also be determined based on the target area of ​​each video segment, and then the target text for embedding in the video segment can be determined based on the segment description information of the video segment and the word count threshold corresponding to the video segment.

[0092] In some examples, a word range for the target text used to describe the video content may be pre-set. On this basis, the font size of the target text may be determined based on the size of the target area of ​​the multiple video frames and the preset word range to obtain the target text information for embedding in the target area, so that the display effect of the target text is adapted to the size of the target area, thereby preventing the target text from affecting the display of the main content of the video and improving the user's experience of watching the video.

[0093] According to some embodiments, determining the target text based on the video content description information and the word count threshold comprises: determining a text generation instruction based on the video content description information and the word count threshold; and inputting the text generation instruction into a generative language model to obtain the target text output by the generative language model. Thus, the generative language model can be used to more efficiently obtain the target text.

[0094] Figure 3 FIG. 2 is a schematic diagram showing a video processing process according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the video processing process may include the following processes:

[0095] Step S1, performing a shot segmentation operation on an original video. By performing physical shot analysis on the original video, the original video can be segmented into multiple shots, that is, multiple video clips are obtained.

[0096] Step S2, identifying text content. For example, the video frames of the original video may be identified using OCR technology to obtain image text, and the audio content of the original video may be identified using ASR technology to obtain audio text, and then the image text and audio text may be merged to obtain video content description information.

[0097] In some examples, step S1 and step S2 may be performed in parallel to improve processing efficiency.

[0098] Step S3, obtaining video segment description. After obtaining multiple video segments, the VLM model can be used to obtain the segment semantic content corresponding to each video segment.

[0099] Step S4: Perform a salient area detection operation on the video frame. By performing salient area detection, the foreground area and the background area of ​​the video frame can be distinguished.

[0100] Step S5, determining the target area. After determining the background area of ​​the video frame, the target area for embedding the target text can be determined based on the background area to avoid the embedded text affecting the display of the main content of the video and improve the user's experience of watching the video.

[0101] It should be noted that step S4-step S5 can be implemented using the various methods described above, which will not be repeated here.

[0102] Step S6: Information merging: By merging the video content description information obtained in the above steps and the segment semantic content output by the VLM model, segment description information that can more comprehensively and accurately describe the semantic content of the video segment can be obtained.

[0103] Step S7, generating a target text. After determining the size of the target area and the segment description information, a word count threshold can be determined based on the size of the target area to obtain a target text that meets the word count condition.

[0104] By applying the above-mentioned video processing method, a target area for embedding text can be determined in the background area of ​​the video, and the target text can be determined according to the description information of the video clip and the size of the target area to ensure that the length of the target text matches the size of the target area. While using the target text to introduce the video content, the embedded text can be prevented from affecting the display of the main object in the video, thereby improving the user's experience of watching the video.

[0105] According to one aspect of the present disclosure, a video processing device is also provided. Figure 4 FIG. 4 shows a structural block diagram of a video processing device 400 according to an exemplary embodiment of the present disclosure. Figure 4 As shown, the device 400 includes:

[0106] An acquisition unit 401 is configured to acquire an original video to be processed and video content description information of the original video;

[0107] A first determining unit 402 is configured to determine a target area of ​​each video frame in the plurality of video frames based on background areas of the plurality of video frames of the original video;

[0108] A second determining unit 403 is configured to determine the target text based on the video content description information and the size of the target area of ​​the plurality of video frames; and

[0109] The embedding unit 404 is configured to embed the target text into the original video based on the positions of the target areas of the multiple video frames.

[0110] According to some embodiments, the first determining unit 402 includes: a segmentation subunit configured to segment the original video into a plurality of video segments, wherein each video segment includes a plurality of video frames including the same subject object; a first determining subunit configured to determine, for each video segment in the plurality of video segments, at least one target frame from the video segment; a second determining subunit configured to determine a background area of ​​the at least one target frame that does not include the subject object; and

[0111] The third determining subunit is configured to determine the target area of ​​each video frame in the video segment based on the background area of ​​the at least one target frame.

[0112] According to some embodiments, the slicing sub-unit includes: an analysis module configured to perform shot analysis on the original video to determine a plurality of shots included in the original video; and a first determination module configured to determine the plurality of video segments based on the plurality of shots.

[0113] According to some embodiments, the first determining subunit is configured to: in response to determining that the video segment includes a plurality of video frames, perform a frame extraction operation on the video segment based on a target frame interval to obtain a plurality of target frames.

[0114] According to some embodiments, the third determination subunit includes: a second determination module configured to determine the intersection of the background areas of the multiple target frames; and a third determination module configured to determine the target area of ​​each video frame in the video clip based on the intersection.

[0115] According to some embodiments, the device 400 also includes: a third determination unit, configured to determine, for each video clip in the multiple video clips, a set of candidate regions for the video clip based on a background region and a region shape condition of at least one target frame in the video clip, wherein the set of candidate regions includes at least one candidate region that satisfies the region shape condition; an update unit, configured to perform an update operation on the set of candidate regions in the multiple video clips, the update unit including: a fusion subunit, configured to determine a fusion region based on the first candidate region and the second candidate region in response to determining that the first candidate region and the second candidate region satisfy a target condition, wherein the target condition includes: a first video clip corresponding to the first candidate region is adjacent to a second video clip corresponding to the second candidate region, and a correlation between the first candidate region and the second candidate region is not less than a correlation threshold; and a replacement subunit, configured to replace the first candidate region and the second candidate region with the fusion region; wherein the third determination subunit is configured to determine the target region from the updated candidate region set corresponding to the video clip.

[0116] According to some embodiments, the device 400 also includes: a fourth determination unit, configured to determine, for each candidate area in the updated multiple candidate area sets, a stay time of the candidate area based on the duration of at least one video clip corresponding to the candidate area, wherein the third determination subunit is configured to: determine the candidate area with the longest stay time in the updated candidate area set corresponding to the video clip as the target area.

[0117] According to some embodiments, the correlation between the first candidate region and the second candidate region comprises an intersection-over-union ratio of the first candidate region to the second candidate region.

[0118] According to some embodiments, the fusion subunit includes: a third determination module configured to determine a union of the first candidate region and the second candidate region; and a fusion module configured to determine the fusion region based on the union.

[0119] According to some embodiments, the second determination unit 403 includes: a fourth determination subunit, configured to determine, for each video segment in the multiple video segments, segment description information of the video segment based on the video content description information; and a fifth determination subunit, configured to determine the segment text of the video segment based on the segment description information and the size of the target area of ​​the video segment; and wherein the embedding unit 404 is configured to: embed the segment text of the video segment into the video segment based on the position of the target area of ​​each video segment.

[0120] According to some embodiments, the fourth determination subunit is configured to: input multiple video frames of the video segment into a visual language model; and determine the segment description information based on the output result of the visual language model and the video content description information, wherein the visual language model is trained using sample data annotated with reference segment description information.

[0121] According to some embodiments, the device 400 also includes: a fifth determination unit, configured to determine, for each video segment in the multiple video segments, a text display duration based on the segment text of the video segment, wherein the embedding unit 404 includes: a sixth determination subunit, configured to determine a plurality of embedded frames from the video segment based on the text display duration; and an embedding subunit, configured to embed the segment text of the video segment into the plurality of embedded frames based on the position of the target area of ​​the video segment.

[0122] According to some embodiments, the acquisition unit 401 includes: an acquisition subunit, configured to acquire the original video; an identification subunit, configured to identify text content in the original video, wherein the text content includes image text included in multiple video frames of the original video or audio text included in the original video; and a seventh determination subunit, configured to determine the video content description information based on the text content.

[0123] According to some embodiments, the second determination unit 403 includes: an eighth determination subunit, configured to determine a word count threshold based on the size of the target area of ​​the multiple video frames; and a ninth determination subunit, configured to determine the target text based on the video content description information and the word count threshold.

[0124] According to some embodiments, the ninth determination subunit includes: a fourth determination module, configured to determine a text generation instruction based on the video content description information and the word count threshold; and an input module, configured to input the text generation instruction into a generative language model to obtain the target text output by the generative language model.

[0125] It should be understood that Figure 4 The operations of the various units of the video processing device 400 shown in FIG. 4 can be compared with Figure 2 The steps in the video processing method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the apparatus 400 and the various units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0126] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the above-mentioned video processing method.

[0127] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned video processing method.

[0128] According to another aspect of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the above-mentioned video processing method when executed by a processor.

[0129] refer to Figure 5 , a block diagram of an electronic device 500 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0130] like Figure 5As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0131] Multiple components in the device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 can be any type of device that can input information to the device 500. The input unit 506 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 507 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 508 can include but is not limited to a disk, an optical disk. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0132] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as video processing methods. For example, in some embodiments, the video processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the video processing method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the video processing method in any other appropriate manner (e.g., by means of firmware).

[0133] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0135] In the context of the present disclosure, 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, device, or equipment. 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, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0138] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0139] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0140] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A video processing method, comprising: Obtaining an original video to be processed and video content description information of the original video; Determine a target area of ​​each video frame in the plurality of video frames based on background areas of the plurality of video frames of the original video; Determine the target text based on the video content description information and the size of the target area of ​​the plurality of video frames; as well as The target text is embedded into the original video based on the positions of the target areas of the multiple video frames.

2. The method of claim 1, wherein: Determining the target area of ​​each video frame in the plurality of video frames comprises: The original video is divided into a plurality of video segments, wherein each video segment includes a plurality of video frames including the same subject object; For each video segment in the plurality of video segments, determining at least one target frame from the video segment; determining a background area of ​​the at least one target frame that does not include the subject object; and Based on the background area of ​​the at least one target frame, a target area of ​​each video frame in the video segment is determined.

3. The method of claim 2, wherein: The dividing the original video into a plurality of video segments comprises: Performing shot analysis on the original video to determine a plurality of shots included in the original video; and Based on the multiple storyboards, the multiple video clips are determined.

4. The method according to claim 2 or 3, wherein: Determining at least one target frame from the video clip comprises: In response to determining that the video segment includes a plurality of video frames, a frame extraction operation is performed on the video segment based on a target frame interval to obtain a plurality of target frames.

5. The method of claim 4, wherein: The determining the target area of ​​each video frame in the video clip based on the background area of ​​the at least one target frame comprises: determining an intersection of background regions of the plurality of target frames; and Based on the intersection, a target region of each video frame in the video segment is determined.

6. The method according to any one of claims 2 to 5, further comprising: For each video segment of the multiple video segments, based on a background region and a region shape condition of at least one target frame in the video segment, determining a candidate region set of the video segment, wherein the candidate region set includes at least one candidate region that satisfies the region shape condition; The following update operation is performed on the candidate region sets in the multiple video clips: In response to determining that the first candidate area and the second candidate area meet a target condition, determining a fusion area based on the first candidate area and the second candidate area, wherein the target condition includes: a first video segment corresponding to the first candidate area is adjacent to a second video segment corresponding to the second candidate area, and a correlation between the first candidate area and the second candidate area is not less than a correlation threshold; and Using the fused region to replace the first candidate region and the second candidate region; Wherein, determining the target area of ​​each video frame in the video clip based on the background area of ​​the at least one target frame comprises: The target region is determined from the updated candidate region set corresponding to the video clip.

7. The method of claim 6, further comprising: For each candidate region in the updated plurality of candidate region sets, based on the duration of at least one video segment corresponding to the candidate region, determine the residence time of the candidate region, The step of determining the target area from the updated candidate area set corresponding to the video clip includes: The candidate region with the longest stay time in the updated candidate region set corresponding to the video clip is determined as the target region.

8. The method according to claim 6 or 7, wherein: The correlation between the first candidate region and the second candidate region includes an intersection-over-union ratio of the first candidate region to the second candidate region.

9. The method of claim 8, wherein: The determining of the fusion region based on the first candidate region and the second candidate region comprises: determining a union of the first candidate area and the second candidate area; and The fused region is determined based on the union.

10. The method according to any one of claims 2 to 9, wherein: The determining of the target text based on the video content description information and the size of the target area of ​​the plurality of video frames comprises: For each video segment in the plurality of video segments, Determining segment description information of the video segment based on the video content description information; and Determine a segment text of the video segment based on the segment description information and the size of the target area of ​​the video segment; And wherein, embedding the target text into the original video based on the position of the target area of ​​the multiple video frames comprises: Based on the position of the target area of ​​each video segment, the segment text of the video segment is embedded into the video segment.

11. The method of claim 10, wherein: The determining the segment description information of the video segment based on the video content description information includes: Inputting a plurality of video frames of the video clip into a visual language model; and The segment description information is determined based on an output result of the visual language model and the video content description information, wherein the visual language model is trained using sample data annotated with reference segment description information.

12. The method according to claim 10 or 11, further comprising: For each video segment of the multiple video segments, determining a text display duration based on the segment text of the video segment, The embedding of the segment text of the video segment into the video segment based on the position of the target area of ​​each video segment comprises: Determining a plurality of embedded frames from the video clip based on the text presentation duration; and Based on the position of the target area of ​​the video segment, the segment text of the video segment is embedded into the multiple embedding frames.

13. The method according to any one of claims 1 to 12, wherein: The obtaining of the original video to be processed and the video content description information of the original video comprises: Obtaining the original video; Identifying text content in the original video, wherein the text content includes image text included in a plurality of video frames of the original video or audio text included in the original video; and The video content description information is determined based on the text content.

14. The method according to any one of claims 1 to 13, wherein: The determining of the target text based on the video content description information and the size of the target area of ​​the plurality of video frames comprises: Determining a word count threshold based on the size of the target area of ​​the plurality of video frames; and The target text is determined based on the video content description information and the word count threshold.

15. The method of claim 14, wherein: The determining the target text based on the video content description information and the word count threshold comprises: Determining a text generation instruction based on the video content description information and the word count threshold; and The text generation instruction is input into a generative language model to obtain the target text output by the generative language model.

16. A video processing device, wherein: An acquisition unit, configured to acquire an original video to be processed and video content description information of the original video; A first determining unit is configured to determine a target area of ​​each video frame in the plurality of video frames based on background areas of the plurality of video frames of the original video; A second determining unit is configured to determine the target text based on the video content description information and the size of the target area of ​​the plurality of video frames; as well as The embedding unit is configured to embed the target text into the original video based on the positions of the target areas of the multiple video frames.

17. The device of claim 16, wherein: The first determining unit includes: A segmentation subunit is configured to segment the original video into a plurality of video segments, wherein each video segment includes a plurality of video frames including a same subject object; A first determining subunit is configured to determine at least one target frame from each video segment of the plurality of video segments; A second determining subunit is configured to determine a background area of ​​the at least one target frame that does not include the subject object; and The third determining subunit is configured to determine the target area of ​​each video frame in the video segment based on the background area of ​​the at least one target frame.

18. The device of claim 17, wherein: The cutting unit comprises: An analysis module, configured to perform shot analysis on the original video to determine a plurality of shots included in the original video; and The first determination module is configured to determine the multiple video clips based on the multiple storyboards.

19. The device according to claim 17 or 18, wherein: The first determining subunit is configured as follows: In response to determining that the video segment includes a plurality of video frames, a frame extraction operation is performed on the video segment based on a target frame interval to obtain a plurality of target frames.

20. The device of claim 19, wherein: The third determining subunit comprises: A second determination module is configured to determine an intersection of background areas of the plurality of target frames; and The third determination module is configured to determine a target area of ​​each video frame in the video segment based on the intersection.

21. The apparatus of any one of claims 17 to 20, further comprising: A third determining unit is configured to determine, for each video segment of the plurality of video segments, a candidate region set of the video segment based on a background region and a region shape condition of at least one target frame in the video segment, wherein the candidate region set includes at least one candidate region that satisfies the region shape condition; An updating unit is configured to perform an updating operation on the candidate region sets in the multiple video clips, the updating unit comprising: a fusion subunit, configured to determine a fusion region based on the first candidate region and the second candidate region in response to determining that the first candidate region and the second candidate region meet a target condition, wherein the target condition includes: a first video segment corresponding to the first candidate region is adjacent to a second video segment corresponding to the second candidate region, and a correlation between the first candidate region and the second candidate region is not less than a correlation threshold; and a replacement subunit, configured to replace the first candidate region and the second candidate region with the fused region; Wherein, the third determining subunit is configured as: The target region is determined from the updated candidate region set corresponding to the video clip.

22. The apparatus of claim 21, further comprising: The fourth determining unit is configured to determine, for each candidate region in the updated plurality of candidate region sets, a stay time of the candidate region based on a time length of at least one video segment corresponding to the candidate region, Wherein, the third determining subunit is configured as: The candidate region with the longest stay time in the updated candidate region set corresponding to the video clip is determined as the target region.

23. The device according to claim 21 or 22, wherein: The correlation between the first candidate region and the second candidate region includes an intersection-over-union ratio of the first candidate region to the second candidate region.

24. The device of claim 23, wherein: The fusion subunit comprises: A third determining module is configured to determine a union of the first candidate area and the second candidate area; and The fusion module is configured to determine the fusion area based on the union.

25. The device according to any one of claims 17 to 24, wherein: The second determining unit includes: a fourth determining subunit, configured to determine, for each video segment of the plurality of video segments, segment description information of the video segment based on the video content description information; and a fifth determining subunit, configured to determine a segment text of the video segment based on the segment description information and a size of a target area of ​​the video segment; And wherein the embedding unit is configured as: Based on the position of the target area of ​​each video segment, the segment text of the video segment is embedded into the video segment.

26. The device of claim 25, wherein: The fourth determining subunit is configured as follows: Inputting a plurality of video frames of the video clip into a visual language model; and The segment description information is determined based on an output result of the visual language model and the video content description information, wherein the visual language model is trained using sample data annotated with reference segment description information.

27. The apparatus of claim 25 or 26, further comprising: a fifth determining unit configured to determine, for each video segment of the plurality of video segments, a text display duration based on a segment text of the video segment, Wherein, the embedding unit comprises: a sixth determining subunit, configured to determine a plurality of embedded frames from the video segment based on the text display duration; and The embedding subunit is configured to embed the segment text of the video segment into the multiple embedding frames based on the position of the target area of ​​the video segment.

28. The device of any one of claims 16 to 27, wherein: The acquisition unit comprises: An acquisition subunit, configured to acquire the original video; a recognition subunit configured to recognize text content in the original video, wherein the text content includes image text included in a plurality of video frames of the original video or audio text included in the original video; and The seventh determining subunit is configured to determine the video content description information based on the text content.

29. The device of any one of claims 16 to 28, wherein: The second determining unit includes: an eighth determination subunit, configured to determine a word count threshold based on the size of the target area of ​​the plurality of video frames; and The ninth determination subunit is configured to determine the target text based on the video content description information and the word count threshold.

30. The apparatus of claim 29, wherein: The ninth determining subunit comprises: a fourth determination module, configured to determine a text generation instruction based on the video content description information and the word count threshold; and The input module is configured to input the text generation instruction into the generative language model to obtain the target text output by the generative language model.

31. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 15.

32. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-15.

33. A computer program product comprising a computer program, wherein: The computer program implements the method according to any one of claims 1-15 when executed by a processor.

Images