Video summarization method and device

Abstract

The embodiment of the invention provides a video summarization method, which comprises the steps of displaying a playing page, the playing page comprises a player and a video summarization control, the player is used for playing a target video, and the target video comprises a plurality of video clips; in response to the selected video summary control, displaying the video summary area, the video summary area comprising a first display control; in response to selection of the first display control, displaying a video summary list in the video summary area, the video summary list comprising a plurality of video content summaries, and the plurality of video content summaries being in one-to-one correspondence with the plurality of video clips; the video content summary comprises a text summary and a picture summary, the picture summary comprises a frame image of the corresponding video clip, and the frame image is determined according to the text summary. According to the technical scheme provided by the embodiment of the invention, more visual and easier-to-understand picture summarization can be provided on the basis of text summarization, and the video watching efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to a video summarization method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the continuous development of artificial intelligence technology, large language models have been widely used in information extraction, text credibility assessment, machine translation and other fields due to their good generalization ability. In order to help viewers quickly understand the content of the video, artificial intelligence technology can be used to summarize the video content.

[0003] However, current summaries of video content are often lengthy and difficult to understand, requiring viewers to spend a lot of time browsing them, resulting in reduced video viewing efficiency.

[0004] It should be noted that the above content is not necessarily prior art, nor is it intended to limit the scope of patent protection of this application. Summary of the invention

[0005] The embodiments of the present application provide a video summarization method, apparatus, computer device, computer-readable storage medium, and computer program product to solve or alleviate one or more of the technical problems raised above.

[0006] One aspect of an embodiment of the present application provides a video summarization method, the method comprising:

[0007] Displaying a play page, the play page including a player and a video summary control, the player is used to play a target video, the target video including multiple video clips;

[0008] In response to selecting the video summary control, displaying the video summary area, the video summary area including a first display control;

[0009] In response to selecting the first display control, displaying a video summary list in the video summary area, the video summary list including a plurality of video content summaries, the plurality of video content summaries corresponding one-to-one to the plurality of video clips;

[0010] The video content summary includes a text summary and a picture summary of the corresponding video clip, and the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

[0011] Optionally, the video content summary further includes a first time jump control; the first time jump control and the text summary are obtained by the following operations:

[0012] Acquire text information of the target video, where the text information includes multiple subtitles of the target video, each subtitle having a corresponding time mark;

[0013] Inputting the text information into a pre-trained language model to obtain a plurality of text summaries through the language model;

[0014] Wherein, one text summary corresponds to one video clip, and each text summary has a corresponding first time jump control, and the first time jump control is used to locate the corresponding video clip of the text summary.

[0015] Optionally, the video summarization method further includes:

[0016] In response to selecting a first time jump control of one of the video content summaries, generating a jump instruction;

[0017] Execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the first time jump control for playing.

[0018] Optionally, the video summary area further includes a second display control; and the method further includes:

[0019] In response to selecting the second display control, a subtitle list is displayed in the video summary area, the subtitle list including multiple subtitles of the target video and a second time jump control corresponding to each subtitle, the second time jump control being used to locate the corresponding video segment of the subtitle.

[0020] Optionally, the video summarization method further includes:

[0021] In response to selecting a second time jump control of one of the subtitles, generating a jump instruction;

[0022] Execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the second time jump control for playing.

[0023] Optionally, the video summarization method further includes:

[0024] Determining a corresponding video segment according to the selected second time jump control;

[0025] Determine a corresponding video content summary according to the corresponding video clip;

[0026] Generating a first list synchronization instruction according to the corresponding video content summary;

[0027] The first list synchronization instruction is executed, where the first list synchronization instruction is used to instruct the video summary area to adjust the video summary list to display the corresponding video content summary at a predetermined position in the video summary list.

[0028] Optionally, the video summarization method further includes:

[0029] Determining a corresponding video segment according to the selected first time jump control;

[0030] Determining subtitles of the corresponding video segment according to the corresponding video segment;

[0031] generating a second list synchronization instruction according to the subtitles of the corresponding video clip;

[0032] The second list synchronization instruction is executed, where the second list synchronization instruction is used to instruct the video summary area to adjust the subtitle list to display the subtitles of the corresponding video segment at a predetermined position in the subtitle list.

[0033] Optionally, the frame image is determined according to the text summary:

[0034] According to the first time jump control of the text summary, determine the corresponding video segment;

[0035] Extracting a plurality of frame images based on the corresponding video clip;

[0036] Determine text feature vectors of the plurality of frame images and an image feature vector and an aesthetic score corresponding to each frame image;

[0037] Determine the image-text similarity corresponding to each frame image according to the text feature vector and the image feature vector corresponding to each frame image;

[0038] Based on the image-text similarity and the aesthetic score corresponding to each frame image, a target frame image is determined, and the target frame image is determined as the picture summary.

[0039] Optionally, determining the text feature vectors of the multiple frame images and the image feature vector and aesthetic score corresponding to each frame image includes:

[0040] Inputting the text summary into a pre-trained generative embedding model to obtain the text feature vector through the generative embedding model;

[0041] Inputting the plurality of frame images into a pre-trained contrastive language image model to obtain an image feature vector corresponding to each frame image through the contrastive language image model;

[0042] The multiple frame images are input into a pre-trained aesthetic scoring model to obtain a corresponding aesthetic score of each frame image through the aesthetic scoring model.

[0043] Optionally, the player is further used to display a playback progress bar of the target video, and the video summary area further includes a progress bar linkage switch; the method further includes:

[0044] In response to turning on the progress bar linkage switch, a plurality of video summary nodes are displayed on the playback progress bar, and the plurality of video summary nodes correspond one-to-one to the plurality of video clips;

[0045] In response to selecting one of the video summary nodes, determining a corresponding video segment;

[0046] Based on the corresponding video clip, obtaining a corresponding video content summary;

[0047] Based on the display position of the selected video summary node, the corresponding video content summary is displayed.

[0048] Optionally, in response to selecting the video summary control, a video summary area is displayed, including:

[0049] In response to selecting the video summary control, obtaining the video summary list and the subtitle list;

[0050] In case the video summary list and the subtitle list are acquired, the video summary area is displayed, and the video summary list and the subtitle list are displayed through the video summary area;

[0051] In the case where the video summary list and the subtitle list are not obtained: obtain a basic content list of the target video, the basic content list including one or more of manuscript information, comments, and barrage; display the video summary area, and display the basic content list through the video summary area.

[0052] Another aspect of an embodiment of the present application provides a video summarization device, the device comprising:

[0053] A first display module, used to display a play page, the play page includes a player and a video summary control, the player is used to play a target video, the target video includes multiple video clips;

[0054] a second display module, configured to display the video summary area in response to selecting the video summary control, wherein the video summary area includes a first display control;

[0055] a third display module, configured to display a video summary list in the video summary area in response to selecting the first display control, wherein the video summary list includes a plurality of video content summaries, and the plurality of video content summaries correspond one-to-one to the plurality of video clips;

[0056] The video content summary includes a text summary and a picture summary of the corresponding video clip, and the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

[0057] Another aspect of an embodiment of the present application provides a computer device, including:

[0058] at least one processor; and

[0059] a memory communicatively coupled to the at least one processor;

[0060] Wherein: 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 so that the at least one processor can execute the method as described above.

[0061] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0062] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the method described above when executed by a processor.

[0063] The above technical solution adopted in the embodiment of the present application may have the following advantages:

[0064] A playback page including a player and a video summary control is displayed, and the player can be used to play a target video including multiple video clips. Select the video summary control, and the playback page can pop up a video summary area with a built-in first display control. Select the first display control, and the video summary area can display a video summary list. Among them, the video summary list includes multiple video content summaries corresponding to multiple video clips one by one, and each video content summary includes a text summary and a picture summary of the corresponding video clip. The picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary. It can be seen that the embodiment of the present application can provide a more intuitive and easier to understand picture summary on the basis of the text summary. The audience can obtain the key content of the video in a shorter time without spending a lot of time browsing lengthy texts, effectively improving the efficiency of video viewing. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] 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.

[0066] Figure 1 The flowchart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0067] Figure 2 The following schematically shows a playback page according to the first embodiment of the present application;

[0068] Figure 3 The video summary area according to the first embodiment of the present application is schematically shown;

[0069] Figure 4 A flowchart for obtaining a first time jump control and a text summary according to Embodiment 1 of the present application is schematically shown;

[0070] Figure 5 Another flowchart for obtaining a first time jump control and a text summary according to the first embodiment of the present application is schematically shown;

[0071] Figure 6 A flowchart for obtaining a picture summary according to Embodiment 1 of the present application is schematically shown;

[0072] Figure 7 Schematically shows Figure 6 Flow chart of sub-steps of step S604;

[0073] Figure 8 The newly added flow chart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0074] Fig. 9 The first time jump control according to the first embodiment of the present application is schematically shown;

[0075] Fig.10 The subtitle list according to the first embodiment of the present application is schematically shown;

[0076] Fig.11 The newly added flow chart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0077] Fig.12 The second time jump control according to the first embodiment of the present application is schematically shown;

[0078] Fig.13 The newly added flow chart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0079] Fig.14 The newly added flow chart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0080] Fig.15 The newly added flow chart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0081] Fig.16 The progress bar linkage switch according to the first embodiment of the present application is schematically shown;

[0082] Fig.17 The video summary node according to the first embodiment of the present application is schematically shown;

[0083] Fig.18 Schematically showing the display of the corresponding video content summary based on the position of the video summary node according to the first embodiment of the present application;

[0084] Fig.19 Schematically shows Figure 2 Flow chart of sub-steps of step S102;

[0085] Fig. 20 The newly added flow chart of the video summarization method according to the first embodiment of the present application is schematically shown;

[0086] Fig.21 A block diagram of a video summarizing device according to Embodiment 2 of the present application is schematically shown; and

[0087] Fig. 22 The hardware architecture diagram of the computer device according to the third embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0088] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0089] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0090] In the description of the present application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed, but are only used to facilitate the description of the present application and to distinguish each step, and therefore should not be understood as a limitation on the present application.

[0091] First, the following terms are explained:

[0092] AI (Artificial Intelligence): Artificial Intelligence.

[0093] LLM (Large Language Model): A large language model is a deep learning model trained with a large amount of data that can understand and generate natural language text.

[0094] CLIP (Contrastive Language-Image Pretraining): Contrastive language-image pretraining model.

[0095] BGE (Bilingual Generative Embeddings): A bilingual generative embedding model that converts input text into a high-dimensional embedding representation, such as a text feature vector.

[0096] UGC (User-Generated Content): User-generated content community.

[0097] Secondly, in order to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the relevant technologies are described below:

[0098] With the continuous development of artificial intelligence technology, large language models have been widely used in information extraction, text credibility assessment, machine translation and other fields due to their good generalization ability. In order to help viewers quickly understand the content of the video, artificial intelligence technology can be used to summarize the video content.

[0099] However, current summaries of video content are often lengthy and difficult to understand, requiring viewers to spend a lot of time browsing them, resulting in reduced video viewing efficiency.

[0100] To this end, the embodiment of the present application provides a video summary technical solution. In this technical solution: (1) The video title, content, release information, etc. are used as inputs of the LLM to generate a brief description of the main content of the video. The large language model is used as one of the means to improve efficiency, combined with the attributes of UGC, to provide viewers with video summary services, so that viewers can understand the main content of the video more efficiently. (2) Based on the AI ​​text summary, it supports picture summary, video jump and progress bar linkage to display chapter summary (video content summary). Specifically: The picture summary enhances intuitiveness and comprehensibility, and improves video viewing efficiency. Users can obtain key content of the video in a shorter time without spending a lot of time browsing lengthy texts. It supports tapping, double-clicking, sliding or hovering the mouse with a jump control (first time jump control and second time jump control) to jump to the corresponding video screen. For users, there is no need to manually fast forward or rewind to find the target content. Just select the jump control with time in the video summary to accurately jump to the part you want to view, making the video viewing process smoother and more efficient. Furthermore, for video creators, it can help creators better understand the audience's focus. By analyzing the jumped video content, creators can know which parts of the video are more popular with users, so as to improve and optimize the subsequent creation content in a more targeted manner and enhance the quality and appeal of the video. By visually displaying the chapter nodes (video summary nodes) summarized by AI on the video playback progress bar, the audience can understand the general framework of the video and the distribution of key content at a glance, further improving the efficiency of video viewing. See below for details.

[0101] The technical solutions of the present application are described below through multiple embodiments. It should be noted that these embodiments can be implemented in a variety of different forms and should not be construed as being limited to the embodiments described here.

[0102] Embodiment 1

[0103] Figure 1 The flowchart of the video summarization method according to the first embodiment of the present application is schematically shown.

[0104] like Figure 1 As shown, the video summary method may include steps S100 to S104, wherein:

[0105] Step S100, displaying a play page, the play page including a player and a video summary control, the player is used to play a target video, the target video including multiple video clips.

[0106] Step S102: in response to selecting the video summary control, displaying the video summary area, wherein the video summary area includes a first display control.

[0107] Step S104: In response to selecting the first display control, a video summary list is displayed in the video summary area, wherein the video summary list includes a plurality of video content summaries, and the plurality of video content summaries correspond one to one to the plurality of video clips. The video content summary includes a text summary and a picture summary of the corresponding video clip, and the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

[0108] The video summary method provided in this embodiment displays a playback page including a player and a video summary control, and the player can be used to play a target video including multiple video clips. When the video summary control is selected, a video summary area with a built-in first display control can pop up on the playback page. When the first display control is selected, the video summary area can display a video summary list. Among them, the video summary list includes multiple video content summaries corresponding to multiple video clips one by one, and each video content summary includes a text summary and a picture summary of the corresponding video clip. The picture summary includes a frame image of the corresponding video clip, and the picture summary is determined based on the text summary. It can be seen that the embodiment of the present application can provide a more intuitive and easier to understand picture summary on the basis of the text summary. The audience can obtain the key content of the video in a shorter time without spending a lot of time browsing lengthy texts, effectively improving the efficiency of video viewing.

[0109] The following combination Figure 1 , each step in steps S100 to S104 and other optional steps are described in detail.

[0110] Step S100 , displaying a play page, the play page including a player and a video summary control, the player being used to play a target video, the target video including multiple video clips.

[0111] The playback page can be a web page or an application program interface. The playback page can include a player and a video summary control. The video summary control can be displayed inside the player or independently of the player and displayed at other locations on the playback page, such as Figure 2 As shown (AI Assistant). The player can be used to play the target video, which can be a video-on-demand file or a live stream. The target video can include multiple video clips, and each video clip can include multiple frame images.

[0112] Step S102 In response to selecting the video summary control, the video summary area is displayed, and the video summary area includes a first display control.

[0113] Select the video summary control to display the video summary area. The video summary area can be a pop-up page or a part of an existing page (such as a play page), suspended on the upper layer of the player or displayed independently of the player in other locations on the play page, such as Figure 3 The video summary area may include a first display control, such as Figure 3 'Video Summary'.

[0114] Step S104 In response to selecting the first display control, a video summary list is displayed in the video summary area, the video summary list includes a plurality of video content summaries, and the plurality of video content summaries correspond to the plurality of video clips one by one. The video content summary includes a text summary and a picture summary of the corresponding video clip, the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

[0115] Selecting the first display control can trigger the video summary area to display the video summary list, such as Figure 3 As shown. The video summary list can include multiple video content summaries, and one video content summary corresponds to one video clip. Furthermore, the multiple video content summaries can be divided into multiple chapters according to different themes, each chapter corresponds to a theme, and each chapter can have one or more video content summaries, so as to provide viewers with a more intuitive and clear video summary and effectively optimize the viewing experience. Figure 3 As shown, the first chapter may include three video content summaries. Each video content summary may include a text summary and a picture summary of the corresponding video segment.

[0116] The text summary may include any combination of the overall description, theme, key events, emotional color, characters, scenes, etc. of the corresponding video clip, which may be determined according to actual needs. The text summary may be obtained through technologies such as manual annotation, visual analysis, data mining, and large language models. An exemplary solution is provided below.

[0117] In an optional embodiment, the video content summary may further include a first time jump control, which may be used to locate the corresponding video segment of the text summary. Figure 4 As shown, the first time jump control and text summary can be obtained by following the steps below:

[0118] Step S400: Acquire text information of the target video, where the text information includes multiple subtitles of the target video, and each subtitle has a corresponding time mark.

[0119] Step S402: input the text information into a pre-trained language model to obtain multiple text summaries through the language model, wherein one text summary corresponds to one video clip, and each text summary has a corresponding first time jump control, and the first time jump control is used to locate the corresponding video clip of the text summary.

[0120] For example, Figure 5 As shown, the text information of the target video can be obtained. The text information may include but is not limited to the title, introduction and multiple subtitles of the target video. Each subtitle has a corresponding time identifier, and the time identifier may include a start time identifier and / or an end time identifier, which is used to indicate the start time and / or end time of each subtitle. The collected text information is spliced ​​together with the task of text summary as a prompt (prompt word) and input into a language model (such as LLM), and multiple text summaries can be obtained. The multiple text summaries can correspond one-to-one to multiple video clips. Each text summary can have a corresponding first time jump control, and the first time jump control can be used to locate the corresponding video clip of the text summary.

[0121] In this embodiment, the relevant information of the target video is understood through the language model, and the attributes of UGC can be combined to generate a text summary of the target video, providing the audience with a video summary service so that the audience can efficiently understand the main content of the video.

[0122] In some embodiments, LLM can also divide multiple text summaries into multiple chapters according to different topics, and generate a summary of each chapter, and finally form an outline of the target video. The outline can be displayed through chapter + text summary + first time jump control, as shown below:

[0123] 1. Through the three "don'ts" challenge, you can naturally become who you want to be, without self-discipline, accept chaos, and let chaos accomplish itself naturally.

[0124] 00:01-Don't be self-disciplined, just let it happen and become whoever you want to be.

[0125] 01:14-The essence of self-discipline is to do things you don’t want to do.

[0126] 04:38-Don’t be self-disciplined, accept the chaos, and let the chaos bring about its own natural achievements.

[0127] 2. The author describes the chaos caused by buying a pair of sneakers and how to use the chaos to change himself and achieve success.

[0128] 05:55-Commercial marketing breaks the linear thinking brought about by exam-oriented education.

[0129] 06:56-Let life flourish naturally through chaos, don’t be self-disciplined, don’t take on challenges.

[0130] 09:20-Take advantage of the source of chaos and let life naturally fulfill you.

[0131] 3. Don’t challenge the chaos theory, as well as the advantages and disadvantages of random behavior and self-discipline, emphasizing that only by accepting chaos in an uncertain world can we make progress.

[0132] 11:51-Don’t try to control yourself, random actions will bring new insights.

[0133] 13:48-Passive random behavior can also bring unexpected gains.

[0134] 15:57-In the business world, self-discipline requires acceptance of the existence of randomness and chaos.

[0135] In this embodiment, the language model can divide multiple text summaries into multiple chapters by topic and generate chapter summaries, which can optimize the structure of the video summary, facilitate audience navigation and understanding, and effectively improve video viewing efficiency.

[0136] In some embodiments, the LLM can also generate a summary of the target video, which can be an overall description of the target video. The summary can be displayed in the video summary area, and the video summary control can be displayed in the video summary list (such as Figure 3 ), or it can be displayed independently of the video summary list and in other locations in the video summary area.

[0137] An abstract can be a whole paragraph, as follows:

[0138] This video tells the story of a class reunion ten years later. Due to the busy work of five students and the absence of five students abroad, only 12 of the 22 students in the class attended the reunion. Although the average income of the 22 students in the class was relatively high, after the reunion, they began to realize the sense of loss brought by the fleeting time.

[0139] In this embodiment, LLM can generate a video summary and display it flexibly, further improving the efficiency of viewers obtaining key information of the video and the viewing experience.

[0140] The above embodiments describe how to obtain a text summary. A picture summary can be determined based on the text summary. The following is an exemplary introduction to a picture summary and a method for obtaining the picture summary.

[0141] The picture summary may be a representative frame image in the corresponding video clip, and the picture summary may be selected from multiple image frames in the corresponding video clip based on the text summary, for example: a multi-level analysis is performed on the text summary, and then the picture summary is determined based on the emotion, context, theme and other information obtained from the analysis. An exemplary solution is provided below.

[0142] In an optional embodiment, if Figure 6 As shown, the picture summary can be obtained by following the steps below:

[0143] Step S600, determining a corresponding video segment according to a first time jump control summarized in the text.

[0144] Step S602: extracting a plurality of frame images based on the corresponding video clip.

[0145] Step S604: determining the text feature vectors of the multiple frame images and the image feature vector and aesthetic score corresponding to each frame image.

[0146] Step S606: Determine the image-text similarity corresponding to each frame image based on the text feature vector and the image feature vector corresponding to each frame image.

[0147] Step S608, determining a target frame image based on the image-text similarity and the aesthetic score corresponding to each frame image, and determining the target frame image as the picture summary.

[0148] Exemplarily, for each text summary, the corresponding image summary can be obtained in the following manner. Specifically, the corresponding video segment can be determined from multiple video segments of the target video according to the time carried by the first time jump control of the text summary. Frame extraction can be performed based on the corresponding video segment to obtain multiple frame images. Feature extraction is performed on each frame image to obtain an image feature vector corresponding to each frame image. The image feature vector can reflect information such as the content, structure and semantics of the frame image. Aesthetic scoring is performed on each frame image to obtain an aesthetic score corresponding to each frame image. The aesthetic score can reflect the aesthetic quality of the frame image in terms of composition, color, clarity, etc. Feature extraction can be performed on the text summary to determine the text feature vectors of multiple frame images. The text feature vector can reflect information such as semantics and grammar of the text summary. For each frame image, similarity measurement can be performed based on the text feature vector and its corresponding image feature vector to obtain the corresponding image-text similarity. Among them, the image-text similarity can reflect the similarity between the frame image and the text summary. The image-text similarity and aesthetic score of each frame image are weighted and sorted to obtain the final score of each frame image. The weights of the image-text similarity and aesthetic score can be set according to actual needs and can be adjusted dynamically. For example, the weight of the aesthetic score can be increased to select a frame image with better visual effects as the image summary. If the goal is to make the image summary as close to the text summary as possible, the weight of the image-text similarity can be increased. The frame image with the highest score can be selected as the target frame image, and the target frame image can be used as the image summary.

[0149] In this embodiment, a picture summary can be obtained based on the AI ​​text summary. The picture summary can enhance the intuitiveness and comprehensibility of information and improve the efficiency of video viewing. The audience can obtain the key content of the video in a shorter time without spending a lot of time browsing lengthy text.

[0150] Text feature vectors, image feature vectors, and aesthetic scores can all be obtained through manual annotation, traditional processing algorithms, or deep learning models. An exemplary solution is provided below.

[0151] In an optional embodiment, if Figure 7 As shown, step S604 may include:

[0152] Step S700: input the text summary into a pre-trained generative embedding model to obtain the text feature vector through the generative embedding model.

[0153] Step S702: input the plurality of frame images into a pre-trained contrastive language image model, so as to obtain an image feature vector corresponding to each frame image through the contrastive language image model.

[0154] Step S704: input the plurality of frame images into a pre-trained aesthetic scoring model, so as to obtain a corresponding aesthetic score of each frame image through the aesthetic scoring model.

[0155] Exemplarily, the text summary can be input into a pre-trained BGE (Bilingual Generative Embedding) model to calculate the text feature vector through the BGE model. The bilingual generative embedding model is applicable to two language scenarios, such as Chinese and English. Of course, the specific language can be set according to actual needs. Multiple frame images can be input into a pre-trained CLIP (Contrastive Language-Image) model to calculate the image feature vector of each frame image through the CLIP model. Each frame image can also be scored by a pre-trained aesthetic scoring model to obtain an aesthetic score for each frame image.

[0156] In this embodiment, through BGE, CLIP and aesthetic scoring model, comprehensive and efficient multimodal feature extraction can be achieved, the graphic and text understanding of video content can be improved, and the accuracy of similarity measurement can be improved.

[0157] The above embodiments describe how to display video summary content. The following embodiments describe how to interact with video summary content to further improve video viewing efficiency.

[0158] In an optional embodiment, if Figure 8 As shown, the video summarization method may further include:

[0159] Step S800, in response to selecting a first time jump control of one of the video content summaries, generating a jump instruction.

[0160] Step S802: execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the first time jump control for playing.

[0161] For example, the output of the LLM may be post-processed to convert the output into a standard format that can be jumped to, and displayed to the audience through the video summary list. In response to the first time jump control of any video content summary in the video summary list being selected, a jump instruction may be generated and executed to instruct the player to jump the target video to the position indicated by the selected first time jump control for playback, such as Fig. 9 shown.

[0162] In this embodiment, it supports clicking the first time jump control to jump to play the corresponding video screen, which can make video viewing smoother and more efficient.

[0163] In an optional embodiment, the video summary area may also include a second display control (such as Figure 3The video summary method may further include: in response to selecting the second display control, displaying a subtitle list in the video summary area, the subtitle list including multiple subtitles of the target video and a second time jump control corresponding to each subtitle, the second time jump control being used to locate the corresponding video segment of the subtitle.

[0164] Exemplarily, when the second display control is selected, the video summary area may display a subtitle list. The subtitle list may include multiple subtitles of the target video, and each subtitle may include a corresponding second time jump control. The second time jump control may be used to locate the corresponding video segment of the subtitle, such as Fig.10 As shown. It can be seen that in the video summary area, by setting the first display control and the second display control, the video summary list and the subtitle list can be switched and displayed, reducing the space occupied by the play page. Of course, the video summary area can also display the video summary list and the subtitle list at the same time, which is not limited here.

[0165] In this embodiment, by displaying the subtitle list in the video summary area, more detailed information of the target video can be provided, which enhances understanding, helps the audience obtain the specific dialogue of the target video, and improves the video viewing experience.

[0166] In an optional embodiment, if Fig.11 As shown, the video summarization method may further include:

[0167] Step S1101, in response to selecting a second time jump control of one of the subtitles, generating a jump instruction.

[0168] Step S1102: execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the second time jump control for playing.

[0169] For example, the time mark of each subtitle can be converted into a jumpable standard format, i.e., a second time jump control, and displayed to the audience through the subtitle list. In response to the second time jump control of any subtitle in the video summary list being selected, a jump instruction can be generated and executed to instruct the player to jump the target video to the position indicated by the selected second time jump control for playback, such as Fig.12 shown.

[0170] In this embodiment, it is supported to click the second time jump control to accurately jump to the video part you want to view. For the audience, there is no need to laboriously fast forward or rewind manually to find the target content, and a smooth and efficient video viewing experience is obtained.

[0171] In an optional embodiment, if Fig.13 As shown, the video summarization method may further include:

[0172] Step S1301: Determine a corresponding video segment according to the selected second time jump control.

[0173] Step S1302: Determine a corresponding video content summary according to the corresponding video clip.

[0174] Step S1303: Generate a first list synchronization instruction according to the corresponding video content summary.

[0175] Step S1304: execute the first list synchronization instruction, where the first list synchronization instruction is used to instruct the video summary area to adjust the video summary list to display the corresponding video content summary at a predetermined position in the video summary list.

[0176] Exemplarily, the corresponding video clip can be determined according to the selected second time jump control. Based on the corresponding video clip, the corresponding video content summary can be located, and the first list synchronization instruction can be generated and executed. The first list synchronization instruction can be used to instruct the video summary area to adjust (such as scrolling up and down) the video summary list until the corresponding video content summary is adjusted to a predetermined position of the video summary list. The predetermined position can be the top, middle, etc. of the video summary list to synchronously highlight the corresponding video content summary. The predetermined position can be set according to actual needs.

[0177] In this embodiment, the first list synchronization instruction is generated based on the selected second time jump control, so that the video summary list can be accurately adjusted to align the display progress of the video summary list with the display progress of the subtitle list, thereby further optimizing the viewing experience.

[0178] In an optional embodiment, if Fig.14 As shown, the video summarization method may further include:

[0179] Step S1400: determining a corresponding video segment according to the selected first time jump control.

[0180] Step S1402: Determine the subtitles of the corresponding video segment according to the corresponding video segment.

[0181] Step S1404: Generate a second list synchronization instruction according to the subtitles of the corresponding video clip.

[0182] Step S1406: executing the second list synchronization instruction, where the second list synchronization instruction is used to instruct the video summary area to adjust the subtitle list to display the subtitles of the corresponding video segment at a predetermined position in the subtitle list.

[0183] Exemplarily, the corresponding video segment can be determined according to the selected first time jump control. Based on the corresponding video segment, the corresponding subtitle can be located, and the second list synchronization instruction can be generated and executed. The second list synchronization instruction can be used to instruct the video summary area to adjust the subtitle list until the corresponding subtitle is adjusted to a predetermined position of the subtitle list. The predetermined position can be the top, the middle, etc. of the subtitle list, so as to synchronously highlight the corresponding subtitle. The predetermined position can be set according to actual needs.

[0184] In this embodiment, the second list synchronization instruction is generated based on the selected first time jump control, so that the subtitle list can be accurately adjusted to align the display progress of the subtitle list with the display progress of the video summary list, thereby further optimizing the viewing experience.

[0185] In an optional embodiment, the player can also be used to display a playback progress bar of the target video (such as Figure 3 ), the video summary area can also include a progress bar linkage switch (such as Figure 3 ) Accordingly, if Fig.15 As shown, the video summarization method may further include:

[0186] Step S1500: In response to turning on the progress bar linkage switch, a plurality of video summary nodes are displayed on the playback progress bar, and the plurality of video summary nodes correspond one-to-one to the plurality of video clips.

[0187] Step S1502: In response to selecting one of the video summary nodes, a corresponding video segment is determined.

[0188] Step S1504: obtaining a corresponding video content summary based on the corresponding video clip.

[0189] Step S1506: displaying the corresponding video content summary based on the display position of the selected video summary node.

[0190] For example, the viewer can turn on the progress bar linkage switch, and the playback progress bar can correspondingly display multiple video summary nodes, such as Fig.16 and Fig.17 When any video summary node is detected to be selected (such as hovering the mouse over the video summary node for more than a preset time, tapping, double-clicking, or sliding), the corresponding video clip can be obtained. Based on the corresponding video clip, the corresponding video content summary can be obtained and displayed above the selected video summary node, such as Fig.18 shown.

[0191] In this embodiment, it supports visually displaying the video content summary on the playback progress bar of the target video. The audience can directly obtain the general framework and key content distribution of the target video on the playback progress bar, which greatly improves the video viewing efficiency.

[0192] In an optional embodiment, if Fig.19 As shown, step S102 may include:

[0193] Step S1900, in response to selecting the video summary control, obtaining the video summary list and the subtitle list.

[0194] Step S1902: when the video summary list and the subtitle list are acquired, the video summary area is displayed, and the video summary list and the subtitle list are displayed through the video summary area.

[0195] Step S1904, when the video summary list and the subtitle list are not obtained: obtain the basic content list of the target video, the basic content list including one or more of manuscript information, comments, and barrage; display the video summary area, and display the basic content list through the video summary area.

[0196] For example, Fig. 20 As shown, when the audience selects the video summary control, the interface can be called to obtain the running results of LLM (text summary, abstract, outline, etc.) and relevant information of the target video (such as subtitles) to obtain the video summary list and subtitle list. If the above content is not obtained, the basic content list of the target video can be pulled from the preset manuscript basic information library. The basic content list can be any combination of the manuscript information, popular comments and popular barrage of the target video. By displaying the basic content list in the video summary area, valuable information can still be provided to the audience, ensuring that the viewing experience is not affected and enhancing the usability and attractiveness of the content. When the video summary list and subtitle list are obtained, they can be displayed through the video summary area.

[0197] In this embodiment, when the video summary and subtitles cannot be obtained, the basic content list is displayed to ensure that the viewing experience is not affected.

[0198] Embodiment 2

[0199] Fig.21The block diagram of the video summarization device according to the second embodiment of the present application is schematically shown. The device can be divided into one or more program modules, one or more program modules are stored in a storage medium, and are executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Fig.21 As shown, the device 1000 may include: a first display module 1100, a second display module 1200 and a third display module 1300, wherein:

[0200] A first display module 1100 is used to display a play page, wherein the play page includes a player and a video summary control, wherein the player is used to play a target video, wherein the target video includes multiple video clips;

[0201] A second display module 1200, for displaying the video summary area in response to selecting the video summary control, wherein the video summary area includes a first display control;

[0202] A third display module 1300, configured to display a video summary list in the video summary area in response to selecting the first display control, wherein the video summary list includes a plurality of video content summaries, and the plurality of video content summaries correspond one-to-one to the plurality of video clips;

[0203] The video content summary includes a text summary and a picture summary of the corresponding video clip, and the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

[0204] As an optional embodiment, the video content summary further includes a first time jump control; the first time jump control and the text summary are obtained by the following operations:

[0205] Acquire text information of the target video, where the text information includes multiple subtitles of the target video, each subtitle having a corresponding time mark;

[0206] Inputting the text information into a pre-trained language model to obtain a plurality of text summaries through the language model;

[0207] Wherein, one text summary corresponds to one video clip, and each text summary has a corresponding first time jump control, and the first time jump control is used to locate the corresponding video clip of the text summary.

[0208] As an optional embodiment, the device 1000 is further used for:

[0209] In response to selecting a first time jump control of one of the video content summaries, generating a jump instruction;

[0210] Execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the first time jump control for playing.

[0211] As an optional embodiment, the video summary area further includes a second display control; and the device 1000 is further used for:

[0212] In response to selecting the second display control, a subtitle list is displayed in the video summary area, the subtitle list including multiple subtitles of the target video and a second time jump control corresponding to each subtitle, the second time jump control being used to locate the corresponding video segment of the subtitle.

[0213] As an optional embodiment, the device 1000 is further used for:

[0214] In response to selecting a second time jump control of one of the subtitles, generating a jump instruction;

[0215] Execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the second time jump control for playing.

[0216] As an optional embodiment, the device 1000 is further used for:

[0217] Determining a corresponding video segment according to the selected second time jump control;

[0218] Determine a corresponding video content summary according to the corresponding video clip;

[0219] Generating a first list synchronization instruction according to the corresponding video content summary;

[0220] The first list synchronization instruction is executed, where the first list synchronization instruction is used to instruct the video summary area to adjust the video summary list to display the corresponding video content summary at a predetermined position in the video summary list.

[0221] As an optional embodiment, the device 1000 is further used for:

[0222] Determining a corresponding video segment according to the selected first time jump control;

[0223] Determining subtitles of the corresponding video segment according to the corresponding video segment;

[0224] generating a second list synchronization instruction according to the subtitles of the corresponding video clip;

[0225] The second list synchronization instruction is executed, where the second list synchronization instruction is used to instruct the video summary area to adjust the subtitle list to display the subtitles of the corresponding video segment at a predetermined position in the subtitle list.

[0226] As an optional embodiment, the frame image is determined according to the text summary:

[0227] According to the first time jump control of the text summary, determine the corresponding video segment;

[0228] Extracting a plurality of frame images based on the corresponding video clip;

[0229] Determine text feature vectors of the plurality of frame images and an image feature vector and an aesthetic score corresponding to each frame image;

[0230] Determine the image-text similarity corresponding to each frame image according to the text feature vector and the image feature vector corresponding to each frame image;

[0231] Based on the image-text similarity and the aesthetic score corresponding to each frame image, a target frame image is determined, and the target frame image is determined as the picture summary.

[0232] As an optional embodiment, determining the text feature vectors of the multiple frame images and the image feature vector and aesthetic score corresponding to each frame image includes:

[0233] Inputting the text summary into a pre-trained generative embedding model to obtain the text feature vector through the generative embedding model;

[0234] Inputting the plurality of frame images into a pre-trained contrastive language image model to obtain an image feature vector corresponding to each frame image through the contrastive language image model;

[0235] The multiple frame images are input into a pre-trained aesthetic scoring model to obtain a corresponding aesthetic score of each frame image through the aesthetic scoring model.

[0236] As an optional embodiment, the player is further used to display a playback progress bar of the target video, and the video summary area further includes a progress bar linkage switch; the device 1000 is further used to:

[0237] In response to turning on the progress bar linkage switch, a plurality of video summary nodes are displayed on the playback progress bar, and the plurality of video summary nodes correspond one-to-one to the plurality of video clips;

[0238] In response to selecting one of the video summary nodes, determining a corresponding video segment;

[0239] Based on the corresponding video clip, obtaining a corresponding video content summary;

[0240] Based on the display position of the selected video summary node, the corresponding video content summary is displayed.

[0241] As an optional embodiment, in response to selecting the video summary control, a video summary area is displayed, including:

[0242] In response to selecting the video summary control, obtaining the video summary list and the subtitle list;

[0243] In case the video summary list and the subtitle list are acquired, the video summary area is displayed, and the video summary list and the subtitle list are displayed through the video summary area;

[0244] In the case where the video summary list and the subtitle list are not obtained: obtain a basic content list of the target video, the basic content list including one or more of manuscript information, comments, and barrage; display the video summary area, and display the basic content list through the video summary area.

[0245] Embodiment 3

[0246] Fig. 22 The schematic diagram of the hardware architecture of a computer device 10000 suitable for implementing the video summarization method according to the third embodiment of the present application is schematically shown. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers), etc. Fig. 22 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them:

[0247] The memory 10010 includes at least one type of computer-readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (such as an SD or DX memory), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as a hard disk or a memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10010 may also include both the internal storage module of the computer device 10000 and its external storage device. In this embodiment, the memory 10010 is generally used to store an operating system and various application software installed in the computer device 10000, such as program codes of a video summarization method, etc. In addition, the memory 10010 can also be used to temporarily store various data that have been output or are to be output.

[0248] In some embodiments, the processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0249] The network interface 10030 may include a wireless network interface or a wired network interface, and the network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and to establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0250] It should be pointed out that Fig. 22 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementation of all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0251] In this embodiment, the video summarization method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0252] Embodiment 4

[0253] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the video summarization method in the embodiment are implemented.

[0254] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEP ROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device, such as the program code of the video summarization method in the embodiment, etc. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0255] Embodiment 5

[0256] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0257] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by general-purpose computer devices, they can be concentrated on a single computer device, or distributed on a network composed of multiple computer devices, optionally, they can be implemented by executable program codes of computer devices, so that they can be stored in a storage device and executed by the computer device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0258] It should be noted that the above are only preferred embodiments of the present application, and the patent protection scope of the present application is not limited thereto. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A video summarization method, characterized in that: The method comprises: Displaying a play page, the play page including a player and a video summary control, the player is used to play a target video, the target video including multiple video clips; In response to selecting the video summary control, displaying the video summary area, the video summary area including a first display control; In response to selecting the first display control, displaying a video summary list in the video summary area, the video summary list including a plurality of video content summaries, the plurality of video content summaries corresponding one-to-one to the plurality of video clips; The video content summary includes a text summary and a picture summary of the corresponding video clip, and the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

2. The method according to claim 1, characterized in that The video content summary also includes a first time jump control; the first time jump control and the text summary are obtained by the following operations: Acquire text information of the target video, where the text information includes multiple subtitles of the target video, each subtitle having a corresponding time mark; Inputting the text information into a pre-trained language model to obtain a plurality of text summaries through the language model; Wherein, one text summary corresponds to one video clip, and each text summary has a corresponding first time jump control, and the first time jump control is used to locate the corresponding video clip of the text summary.

3. The method according to claim 2, characterized in that The method further comprises: In response to selecting a first time jump control of one of the video content summaries, generating a jump instruction; Execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the first time jump control for playing.

4. The method according to claim 3, characterized in that The video summary area also includes a second display control; the method also includes: In response to selecting the second display control, a subtitle list is displayed in the video summary area, the subtitle list including multiple subtitles of the target video and a second time jump control corresponding to each subtitle, the second time jump control being used to locate the corresponding video segment of the subtitle.

5. The method according to claim 4, characterized in that The method further comprises: In response to selecting a second time jump control of one of the subtitles, generating a jump instruction; Execute the jump instruction, where the jump instruction is used to instruct the player to jump the target video to the position indicated by the second time jump control for playing.

6. The method according to claim 4, characterized in that The method further comprises: Determining a corresponding video segment according to the selected second time jump control; Determine a corresponding video content summary according to the corresponding video clip; Generating a first list synchronization instruction according to the corresponding video content summary; The first list synchronization instruction is executed, where the first list synchronization instruction is used to instruct the video summary area to adjust the video summary list to display the corresponding video content summary at a predetermined position in the video summary list.

7. The method according to claim 4, characterized in that The method further comprises: Determining a corresponding video segment according to the selected first time jump control; Determining subtitles of the corresponding video segment according to the corresponding video segment; generating a second list synchronization instruction according to the subtitles of the corresponding video clip; The second list synchronization instruction is executed, where the second list synchronization instruction is used to instruct the video summary area to adjust the subtitle list to display the subtitles of the corresponding video segment at a predetermined position in the subtitle list.

8. The method according to claim 2, characterized in that: The frame image is determined according to the text summary: According to the first time jump control of the text summary, determine the corresponding video segment; Extracting a plurality of frame images based on the corresponding video clip; Determine text feature vectors of the plurality of frame images and an image feature vector and an aesthetic score corresponding to each frame image; Determine the image-text similarity corresponding to each frame image according to the text feature vector and the image feature vector corresponding to each frame image; Based on the image-text similarity and the aesthetic score corresponding to each frame image, a target frame image is determined, and the target frame image is determined as the picture summary.

9. The method according to claim 8, characterized in that Determining the text feature vectors of the plurality of frame images and the image feature vector and aesthetic score corresponding to each frame image includes: Inputting the text summary into a pre-trained generative embedding model to obtain the text feature vector through the generative embedding model; Inputting the plurality of frame images into a pre-trained contrastive language image model to obtain an image feature vector corresponding to each frame image through the contrastive language image model; The multiple frame images are input into a pre-trained aesthetic scoring model to obtain a corresponding aesthetic score of each frame image through the aesthetic scoring model.

10. The method according to claim 1, characterized in that The player is also used to display a playback progress bar of the target video, and the video summary area also includes a progress bar linkage switch; the method also includes: In response to turning on the progress bar linkage switch, a plurality of video summary nodes are displayed on the playback progress bar, and the plurality of video summary nodes correspond one-to-one to the plurality of video clips; In response to selecting one of the video summary nodes, determining a corresponding video segment; Based on the corresponding video clip, obtaining a corresponding video content summary; Based on the display position of the selected video summary node, the corresponding video content summary is displayed.

11. The method according to any one of claims 1 to 10, characterized in that: In response to selecting the video summary control, a video summary area is displayed, including: In response to selecting the video summary control, obtaining the video summary list and the subtitle list; In case the video summary list and the subtitle list are acquired, the video summary area is displayed, and the video summary list and the subtitle list are displayed through the video summary area; In the case where the video summary list and the subtitle list are not obtained: obtain a basic content list of the target video, the basic content list including one or more of manuscript information, comments, and barrage; display the video summary area, and display the basic content list through the video summary area.

12. A video summarizing device, characterized in that: The device comprises: A first display module, used to display a play page, the play page includes a player and a video summary control, the player is used to play a target video, the target video includes multiple video clips; a second display module, configured to display the video summary area in response to selecting the video summary control, wherein the video summary area includes a first display control; a third display module, configured to display a video summary list in the video summary area in response to selecting the first display control, wherein the video summary list includes a plurality of video content summaries, and the plurality of video content summaries correspond one-to-one to the plurality of video clips; The video content summary includes a text summary and a picture summary of the corresponding video clip, and the picture summary includes a frame image of the corresponding video clip, and the frame image is determined according to the text summary.

13. A computer device, characterized in that: include: 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 to enable the at least one processor to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 11 are implemented.

Images