Video comment display method and device

Abstract

The embodiment of the invention provides a video comment display method, and the method comprises the steps: segmenting a target video, and obtaining video segments of the target video; obtaining a comment of the target video, and determining a segmented comment corresponding to each video clip based on the comment; and under the condition that a target video clip of the target video is played, displaying a segmentation comment corresponding to the target video clip in a predetermined area of a playing interface of the target video. According to the technical scheme provided by the embodiment of the invention, the user can conveniently view the comments corresponding to the video clip, and the user experience is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of multimedia technology, and in particular, to a method, device, computer device, computer-readable storage medium, and computer program product for video comment display. Background Art

[0002] The comment systems of current video platforms are mainly divided into two parts: bullet screens and bottom comment areas. Among them, although bullet screens have the advantage of real-time, the information is relatively fragmented and it is difficult to support in-depth discussions. When viewers want to view the user comments corresponding to a certain segment of a video, they usually have to go to the bottom comment area to search. However, since the bottom comment area is not associated with the segments of the video, users cannot determine which video segments these comments are related to during the search process in the bottom comment area, and it is difficult to find the user comments corresponding to the corresponding segments; moreover, the bottom comment area is usually arranged in the chronological order of comments, so the comments related to video segments may be relatively scattered. Users usually need to browse through all the comments to roughly know the comments related to the segments, resulting in low efficiency and poor experience for users to view the comments of the relevant segments.

[0003] It should be noted that the above content is not necessarily prior art and is not used to limit the patent protection scope of the present application. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, computer device, computer-readable storage medium, and computer program product for video comment display to solve or alleviate one or more of the above technical problems.

[0005] One aspect of the embodiments of the present application provides a method for video comment display, and the method includes: Segment the target video to obtain video segments of the target video; Obtain the comments of the target video, and determine segmented comments corresponding to each of the video segments based on the comments; When playing a target video segment of the target video, display the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video.

[0006] Optionally, the segmenting the target video to obtain video segments of the target video includes: Display a segment editing interface of the target video based on a preset instruction; Segment the target video based on an input instruction for the segment editing interface and generate segmented target information to obtain the video segments of the target video, where the target information includes at least some of the ID, segment start time, segment end time, and segment description of the target video.

[0007] Optionally, segmenting the target video to obtain video segments of the target video includes: Obtaining target modality information of the target video, where the target modality information includes at least one of frame images, audio, and text of the target video; Analyzing the target modality information to determine segmentation feature information of the target video; Segmenting the target video based on the segmentation feature information to obtain video segments of the target video.

[0008] Optionally, analyzing the target modality information to determine segmentation feature information of the target video includes: Performing image analysis on frame images of the target video to obtain scene transition information in the frame images; Performing speech recognition on the audio of the target video to obtain an audio recognition text, and analyzing the audio recognition text to obtain audio analysis information; Analyzing the text of the target video to obtain text analysis information; Determining the segmentation feature information based on the scene transition information, the audio analysis information, and / or the text analysis information.

[0009] Optionally, determining a segmentation comment corresponding to each video segment based on the comment includes: Generating a segmentation description for each video segment based on the target modality information; Analyzing and extracting keywords of the comment of the target video based on a natural language processing method; Determining a segmentation comment corresponding to each video segment through semantic similarity based on the keywords and the segmentation description.

[0010] Optionally, the method further includes: Receiving an adjustment instruction for the video segment, where the adjustment instruction is used to merge or split the video segment; When the adjustment instruction is received, adjusting the video segment according to the adjustment instruction to obtain an adjusted video segment.

[0011] Optionally, displaying a segmentation comment corresponding to the target video segment in a predetermined area of the playback interface of the target video includes: Displaying a segmentation comment corresponding to the target video segment in a sidebar on the playback interface of the target video, and adjusting the playback screen of the target video so that the playback screen does not overlap with the sidebar; Upon receiving a close instruction for the sidebar, close the sidebar and restore the playback screen to its original size.

[0012] Optionally, the method further includes: Display the comments of the target video and the segmented comments in different areas at the bottom of the target video, where the segmented comments correspond to target time intervals, and the target time intervals are the time intervals of the video segments corresponding to the segmented comments; Upon receiving a selection instruction for a target segmented comment, jump to the video segment corresponding to the target segmented comment, where the target segmented comment is any segmented comment.

[0013] Another aspect of the embodiments of the present application provides a video comment display device, where the device includes: A segmentation module, configured to segment a target video to obtain video segments of the target video; A determination module, configured to obtain comments of the target video and determine segmented comments corresponding to each of the video segments based on the comments; A display module, configured to display the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video when playing the target video segment of the target video.

[0014] Another aspect of the embodiments of the present application provides a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; where: 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 execute the method as described above.

[0015] Another aspect of the embodiments of the present application provides a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed by a processor, the method as described above is implemented.

[0016] Another aspect of the embodiments of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method as described above is implemented.

[0017] The embodiments of the present application adopting the above technical solutions may include the following advantages: By segmenting the target video, video segments of the target video are obtained, comments of the target video are acquired, segmented comments corresponding to each video segment are determined based on the comments of the target video, and when the target video segment of the target video is played, the segmented comments corresponding to the target video segment are displayed in a predetermined area of the playback interface of the target video, which can enable users to conveniently view the comments corresponding to the video segments when watching the video, thereby effectively improving the user experience. Description of the Drawings

[0018] The drawings exemplarily show embodiments and form part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments of the embodiments. The shown embodiments are for illustrative purposes only and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0019] Figure 1 Schematically shows the operating environment diagram of the video comment display method according to Embodiment 1 of the present application; Figure 2 Schematically shows the flowchart of the video comment display method according to Embodiment 1 of the present application; Figure 3 Schematically shows Figure 2 the sub-step flowchart of step S200 in; Figure 4 Schematically shows Figure 2 another sub-step flowchart of step S200 in; Figure 5 Schematically shows Figure 4 the sub-step flowchart of step S402 in; Figure 6 Schematically shows the new process of the video comment display method according to Embodiment 1 of the present application; Figure 7 Schematically shows Figure 2 the sub-step flowchart of step S202 in; Figure 8 Schematically shows Figure 2 the sub-step flowchart of step S204 in; Figure 9 Schematically shows another new process of the video comment display method according to Embodiment 1 of the present application; Figure 10 Schematically shows the block diagram of the video comment display device according to Embodiment 2 of the present application; and Figure 11 Schematically shows the hardware architecture diagram of the computer device according to Embodiment 3 of the present application. Detailed Embodiments

[0020] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the following further elaborates on the present application 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 used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0021] It should be noted that in the embodiments of the present application, the descriptions involving "first", "second", etc. are only for descriptive purposes and cannot be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. Additionally, the technical solutions between various embodiments may be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0022] In the description of the present application, it should be understood that the numerical labels before the steps do not identify the order of execution of the steps, but are only used to conveniently describe the present application and distinguish each step. Therefore, it cannot be construed as a limitation to the present application.

[0023] First, the following provides an explanation of the terms involved in the present application: Sidebar: It can be a component in the user interface design, usually located on the left or right side of the application or web page, and in a few cases, located at the bottom.

[0024] Computer vision technology: It is a technology that studies how to enable a computer to "understand" visual information such as images and videos, and to understand, analyze, and make decisions. It involves knowledge and methods in multiple fields such as image processing, pattern recognition, machine learning, and deep learning, aiming to enable the computer to simulate the functions of the human visual system and automatically extract valuable information from visual data.

[0025] Secondly, to facilitate the understanding of the technical solutions provided in the embodiments of the present application by those skilled in the art, the following explains the related technologies: The comment systems of current video platforms are mainly divided into two parts: bullet comments and bottom comment areas. Although bullet comments can be viewed in real time, the information is relatively fragmented and does not support in-depth discussions. When viewers want to view the user comments corresponding to a certain segment of a video, they usually have to look in the bottom comment area. However, since the bottom comment area is not associated with the segments of the video, users cannot determine which comments are related to that segment and it is difficult to find the comments corresponding to that segment. Moreover, the bottom comment area is usually sorted in the order of comments, and the comments related to the video may be relatively scattered. Users usually need to browse through all the comments to roughly know the comments corresponding to that segment, resulting in a poor user experience.

[0026] For this reason, the embodiments of this application provide a technical solution for video comment display. In this technical solution, by segmenting the video, the segmented comments corresponding to each segment are determined. When playing the target segment of the video, the corresponding segmented comments are displayed in a predetermined area of the video playback interface, which can allow users to conveniently view the comments corresponding to the video segment and improve the user experience. See the following for details.

[0027] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0028] As Figure 1 shown, the environmental schematic diagram includes a service platform 2, a network 4, and a client 6, where: The service platform 2 can be composed of a single or multiple computing devices. The multiple computing devices can include virtualized computing instances. The virtualized computing instances can include virtual machines, such as emulations of computer systems, operating systems, servers, etc. The computing devices can load virtual machines based on virtual images and / or other data that define specific software (e.g., operating systems, dedicated applications, servers) for emulation. As the demand for different types of processing services changes, different virtual machines can be loaded and / or terminated on one or more computing devices. A hypervisor can be implemented to manage the use of different virtual machines on the same computing device.

[0029] The service platform 2 can be configured to communicate with the client 6, etc. through the network 4. The network 4 includes various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and / or the like. The network 4 can include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, and combinations thereof, or wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0030] The service platform 2 can provide services such as storage, reading, writing, querying, deleting, etc., such as providing services for clients to watch videos.

[0031] The client 6 can be an electronic device running operating systems such as Windows, Android™, or iOS, such as a smart phone, a tablet device, a laptop computer, a virtual reality device, a gaming device, a set-top box, a vehicle-mounted terminal, or a smart TV. Based on the above operating systems, various applications can be run, such as an application for watching videos.

[0032] The client 6 can provide / configure a user access page for manipulating the service platform 2 or uploading an object, etc.

[0033] It should be noted that the above devices are exemplary, and in different scenarios or according to different requirements, the number and types of devices can be adjusted.

[0034] The technical solutions of the present application will be introduced below through multiple embodiments. It should be noted that these embodiments can be implemented in various different forms and should not be construed as being limited only to the embodiments described herein.

[0035] Embodiment 1 Figure 2 A flowchart of a video comment display method according to Embodiment 1 of the present application is schematically shown. It should be noted that the execution subject of the video comment display method in the embodiments of the present application can be a client or a service platform.

[0036] As Figure 2 shown, the video comment display method can include steps S200 to S204, where: Step S200: Segment the target video to obtain video segments of the target video.

[0037] Step S202: Obtain comments of the target video and determine segmented comments corresponding to each video segment based on the comments of the target video.

[0038] Step S204: When playing the target video segment of the target video, display the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video.

[0039] The video comment display method provided in this embodiment segments the target video to obtain video segments of the target video, obtains comments of the target video, determines segmented comments corresponding to each video segment based on the comments of the target video, and displays the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video when playing the target video segment of the target video. This allows users to conveniently view the comments corresponding to the video segments when watching the video, thereby effectively improving the user experience.

[0040] The following will Figure 2 be elaborated in detail on each step in steps S200 to S204 and optional other steps.

[0041] Step S200 , segment the target video to obtain video segments of the target video.

[0042] When segmenting the target video, it can be segmented manually or automatically. When segmenting manually, it can be that a human determines the paragraphs included in the target video and manually marks information such as the start time and end time corresponding to each paragraph. When segmenting automatically, it can be to analyze the content of the target video, determine the segmentation points according to the analysis results, and then segment the target video according to the segmentation points. Some exemplary solutions are given below.

[0043] In an alternative embodiment, as Figure 3 shown, step S200 may include: Step S300, display a segmentation editing interface of the target video based on a preset instruction.

[0044] Step S302, segment the target video based on an input instruction to the segmentation editing interface and generate target information of the segmentation, to obtain video segments of the target video, where the target information includes at least some information of the ID, segmentation start time, segmentation end time, and segmentation description of the target video.

[0045] The segmentation editing interface can be an interface for marking the start time and end time of the segmentation and adding a segmentation description. The preset instruction can be received through a specific control. For example, a "manual segmentation" control can be displayed on a relevant page of the target video, and when the user clicks this control, it is determined that the preset instruction is received, and then the segmentation editing interface is displayed. Of course, the preset instruction can also be in other ways, such as instructions different from ordinary playback instructions such as long pressing or swiping on the target video.

[0046] Specifically, the input instruction can be monitored on the relevant page of the target video. When a preset instruction is received, the segmented editing interface of the target video is displayed on the current page or redirected to a specific page. Then, the user or the creator of the target video can perform segmentation operations on the target video on the segmented editing interface. For example, the start time and end time of each segment can be marked by dragging the time axis of the target video or entering a timestamp. After determining a segment, a description of the current segment (such as "battle scene", "dialogue paragraph") can be entered; alternatively, after determining each segment, the description of each segment can be entered. After the user's operation, the target information of the segments can be generated to obtain the video segments of the target video. The target information includes at least some of the ID of the target video (such as video name or video platform number, etc.), segment start time, segment end time, and segment description. The target information can be stored on the service platform, such as stored in a certain database and associated with the target video. The service platform can generate a segmented index of the target video to facilitate the search or other processing of the video segments of the target video.

[0047] In this embodiment, by displaying the segmented editing interface of the target video based on a preset instruction, segmenting the target video based on the input instruction on the segmented editing interface, and generating the target information of the segments to obtain the video segments of the target video, where the target information includes at least some of the ID of the target video, segment start time, segment end time, and segment description, it is convenient to manually segment the video.

[0048] In an alternative embodiment, as Figure 4 shown, step S200 may include: Step S400, obtaining the target modality information of the target video, where the target modality information includes at least one of the frame images, audio, and text of the target video.

[0049] Step S402, analyzing the target modality information to determine the segmented feature information of the target video.

[0050] Step S404, segmenting the target video based on the segmented feature information to obtain the video segments of the target video.

[0051] Among them, the frame image of the target video is visual modality information, the audio is auditory modality information, and the text is text modality information, which can specifically be text-based information such as subtitles, titles, and captions. When analyzing the frame image, computer vision technology can be used to analyze the frame image to identify the scene transition information contained in the frame image, and the scene transition information is used as the segmentation feature information of the visual modality. When analyzing the audio, speech recognition can be performed on the audio first, and information related to segmentation, such as topic transition and keyword occurrence, can be determined based on the results of the speech recognition, and these related information is used as the segmentation feature information of the auditory modality. Or, the audio can be directly analyzed to determine the change information in the audio, and the change information is used as the segmentation feature information of the auditory modality, where the change information is, for example, information related to sound changes such as the background music changing from soothing to tense, the end of a conversation, or the start of a transition music. When analyzing the text, context analysis can be performed on the text, and change information such as semantic conversion, transition, and the start of a new chapter can be determined based on the analysis results, and these change information are used as the segmentation feature information of the text modality.

[0052] After obtaining the segmentation feature information, the target video can be segmented according to the timestamps corresponding to these segmentation feature information to obtain video segments of the target video. When there is only segmentation feature information of one modality, segmentation can be performed according to the segmentation feature information of this modality. When there is segmentation feature information of two or more modalities, the segmentation feature information can be combined for segmentation. For example, the scene transition information (visual modality) can be combined with the change information of the audio (auditory modality) for segmentation to further improve the accuracy of segmentation.

[0053] In this embodiment, by obtaining the target modality information of the target video, analyzing the target modality information to determine the segmentation feature information of the target video, and segmenting the target video based on the segmentation feature information to obtain video segments of the target video, several modalities of information of the video can be analyzed as needed, and video segmentation can be performed according to the analysis results, realizing automatic segmentation of the video. At the same time, the segmentation feature information of multiple modalities can be combined for segmentation to improve the accuracy of video segmentation.

[0054] In an alternative embodiment, in step S402 above, analyzing the target modality information to determine the segmentation feature information of the target video, as Figure 5 shown, may further include: Step S500, performing image analysis on the frame image of the target video to obtain the scene transition information in the frame image.

[0055] Step S502, performing speech recognition on the audio of the target video to obtain the audio recognition text, and analyzing the audio recognition text to obtain audio analysis information.

[0056] Step S504: Analyze the text of the target video to obtain text analysis information.

[0057] Step S506: Determine the segmentation feature information based on the scene transition information, audio analysis information, and / or subtitle analysis information.

[0058] When performing image analysis on the frame images of the target video, methods such as object detection, image classification, or video frame difference method can be used to determine the scene transition information in the frame images. Among them, the object detection method can be to use an object detection algorithm based on deep learning to detect various target objects in the frame image, and determine the scene transition information by the changes of key objects. For example, if the objects in the frame image change from a scene containing a car and a street to a scene containing indoor furniture, it can be determined that a scene transition has occurred. The image classification method can be to classify the frame image through models such as convolutional neural networks (such as indoor scene, outdoor scene, urban scene, wild scene, etc.), and determine the scene transition information by the changes in the classification results of the frame image. For example, if the classification of the frame image changes from an urban scene to a wild scene, it can be determined that a scene transition has occurred. The video frame difference method can be to calculate the inter-frame difference between adjacent frame images, and determine the scene transition information based on the inter-frame difference. For example, if the change in the color histogram of adjacent frame images exceeds a threshold, it is determined that a scene transition has occurred.

[0059] When analyzing the audio of the target video, speech recognition can be performed on the audio to obtain audio recognition text, and then natural language processing technology can be used to analyze the topic transition, key events, and semantic coherence in the audio recognition text to obtain audio analysis information. Among them, topic transition can detect the topics in the audio recognition text and obtain audio analysis information based on the topic transition. For example, if it is detected that the topic in the audio recognition text changes from current affairs to weather, it can be used as audio analysis information. Key events can be to obtain audio analysis information by detecting key events in the audio recognition text. For example, if key events such as "Now the meeting starts" and "The meeting ends here" are extracted from the audio recognition text, these key events can be used as audio analysis information. Semantic coherence can analyze the semantic similarity in the audio recognition text, judge whether there is segmentation based on the semantic similarity, and obtain audio analysis information based on the change information of the semantic similarity. For example, if the semantic similarity between the current text segment and the previous text is low, it can be determined that there is a change in semantic similarity, and the information about the change in similarity can be used as audio analysis information.

[0060] When analyzing the text of the target video, the above text analysis method can be adopted to obtain text analysis information. Of course, in addition to the above analysis method, since the text of the target video can include information such as titles, chapters, punctuation marks, etc., these additional information can also be combined to obtain text analysis information. For example, text analysis information can be obtained based on "Chapter 2: The Adventure Journey".

[0061] In this embodiment, by performing image analysis on the frame images of the target video to obtain scene transition information in the frame images, performing speech recognition on the audio of the target video to obtain audio recognition text, and analyzing the audio recognition text to obtain audio analysis information, and analyzing the text of the target video to obtain text analysis information, and determining segmentation feature information based on the scene transition information, audio analysis information, and / or text analysis information, the analysis of multiple modalities of the video can be realized, thereby improving the accuracy of video segmentation.

[0062] In an alternative embodiment, as Figure 6 shown, the video comment display method of the embodiments of the present application may further include: Step S600, receiving an adjustment instruction for the video segment, where the adjustment instruction is used to merge or split the video segment.

[0063] Step S602, in the case of receiving the adjustment instruction, adjusting the video segment according to the adjustment instruction to obtain an adjusted video segment.

[0064] The adjustment instruction may be to display an adjustment control on a relevant page of the target video, and after the user clicks the control, it is determined that the adjustment instruction is received. Of course, the adjustment instruction may also be in other forms of instructions, which are not specifically limited here.

[0065] Specifically, the user or the creator of the target video can input an adjustment instruction for the video segment of the target video. In the case of receiving the input adjustment instruction, the video segment is split or merged according to the adjustment instruction to obtain an adjusted video segment of the target video. For example, if the user believes that video segment A should actually contain two segments, the segmentation point of video segment A can be marked and then split into two segments according to this segmentation point; for another example, if the user believes that video segment B and video segment C should actually be one segment, then video segment B and video segment C can be merged to obtain one video segment.

[0066] In practical applications, the adjustments made by the user to the video segment can be recorded, and then the method of automatic video segmentation can be optimized according to the record, so as to continuously improve the accuracy of automatic segmentation.

[0067] In this embodiment, by receiving an adjustment instruction for a video clip and adjusting the video clip according to the adjustment instruction, an adjusted video clip is obtained, and the video segments can be adjusted as needed, further improving the accuracy of video segmentation.

[0068] Step S202 , obtain the comments of the target video, and determine the segmented comments corresponding to each video clip based on the comments of the target video.

[0069] Specifically, the comments corresponding to the target video can be obtained from the comment database according to the ID of the target video, and then the comments of the target video are matched according to the content of the video clips of the target video, and the segmented comments corresponding to each video clip are determined according to the matching degree.

[0070] In an alternative embodiment, in step S202, the segmented comments corresponding to each video clip are determined based on the comments of the target video, as Figure 7 shown, may include: Step S700, generate a segmented description for each video clip based on the target modality information.

[0071] Step S702, analyze and extract the keywords of the comments of the target video based on natural language processing methods.

[0072] Step S704, determine the comments corresponding to each video clip as the corresponding segmented comments through semantic similarity based on the keywords and the segmented description.

[0073] Specifically, the target modality information can be divided according to the video clips to determine the target modality information corresponding to each video clip, and then, a segmented description for each video clip is generated according to the target modality information. For example, the text modality information corresponding to each video clip can be input into a large language model, and the large language model is used to generate a segmented description for each video clip; for another example, the audio modality information corresponding to each video clip can be speech-recognized and converted into text, and then a segmented description is generated according to the converted text using the large language model. Of course, two or more types of modality information can also be combined to generate a segmented description, further improving the accuracy of the segmented description. For the comments of the target video, natural language processing methods can be used for analysis to extract the keywords of the comments; after obtaining the segmented descriptions of each video clip and the keywords of the comments, the semantic similarity between the keywords of the comments and the segmented descriptions of each video clip can be calculated, and the video clip with the highest semantic similarity is used as the video clip corresponding to the comment. After performing the same operation on all comments, the segmented comments corresponding to each video clip can be determined.

[0074] In practical applications, a channel for user feedback can also be provided, allowing users to provide feedback on irrelevant segmented comments in the video clip. Then, the segmented comments can be adjusted based on the feedback, so that the segmented comments corresponding to each video clip are more accurate. The method for automatically determining segmented comments can also be optimized according to the adjustment, thereby improving the accuracy of subsequent automatic determination of segmented comments. Additionally, in the case of manual segmentation, the segmented descriptions input manually can be matched with the keywords of the comments to determine the segmented comments corresponding to each video clip.

[0075] In this embodiment, by generating segmented descriptions for each video clip based on the target modal information, analyzing and extracting the keywords of the comments of the target video based on natural language processing methods, and determining the segmented comments corresponding to each video clip through semantic similarity based on the keywords and segmented descriptions, the segmented comments of each video clip can be effectively determined, and the efficiency of obtaining segmented comments can be improved.

[0076] Step S204 , when playing the target video clip of the target video, display the segmented comments corresponding to the target video clip in a predetermined area of the playback interface of the target video.

[0077] Among them, the target video clip can be any video clip of the target video. The predetermined area can be an area on the side, above, or below the playback interface of the target video. When displaying the segmented comments in the predetermined area, in order not to block the video content, the playback screen can be adjusted adaptively. The predetermined area can be turned on or off by default, and the user can turn it off or on according to needs. The following provides some exemplary solutions.

[0078] In an alternative embodiment, in step S204, displaying the segmented comments corresponding to the target video clip in a predetermined area of the playback interface of the target video, as Figure 8 shown, may include: Step S800, display the segmented comments corresponding to the target video clip in the target video playback interface using a sidebar, and adjust the playback screen of the target video so that the playback screen does not overlap with the sidebar.

[0079] Step S802, when receiving a close instruction for the sidebar, close the sidebar and restore the playback screen to its original size.

[0080] Specifically, when playing to the target video segment of the target video, the segmented comments corresponding to the target video can be displayed in the form of a sidebar by default or according to the user's instruction, and the playback screen of the target video can be adjusted so that the playback screen does not overlap with the sidebar, so that the display of the sidebar will not block the video content. For example, when playing to the target video segment D, if the user wants to view the segmented comments of the video segment D and the playback interface provides a control for opening the sidebar, the user can click on the control to open the sidebar. After opening the sidebar, the segmented comments corresponding to the video segment D can be loaded and displayed in the sidebar; at the same time, the video playback screen is reduced, and the reduced video playback screen does not overlap with the sidebar at least. When the sidebar is displayed, it can be monitored whether a close instruction for the sidebar is received. If the close instruction is received, the sidebar is closed and the playback screen is restored to its original size. For example, the sidebar can include a close control. If the user clicks on the control, it is determined that the close instruction is received. At this time, the sidebar is closed, and after closing the sidebar, the playback screen is restored to its original size.

[0081] In this embodiment, by using a sidebar to display the segmented comments corresponding to the target video segment on the playback interface of the target video, and adjusting the target video playback screen so that the playback screen does not overlap with the sidebar, and closing the sidebar and restoring the playback screen to its original size when a close instruction for the sidebar is received, it is convenient for the user to view the segmented comments through the sidebar while avoiding blocking the playback content.

[0082] In an alternative embodiment, as Figure 9 shown, the video comment display method provided by the embodiment of the present application may further include: Step S900, display the comments and segmented comments of the target video in different areas at the bottom of the target video. The segmented comments correspond to a target time interval, and the target time interval is the time interval of the video segment corresponding to the segmented comments.

[0083] Step S902, when a selection instruction for a target segmented comment is received, jump to the video segment corresponding to the target segmented comment, where the target segmented comment is any segmented comment.

[0084] Specifically, the comments (ordinary comments) and segmented comments of the target video can be displayed in different areas at the bottom of the target video in forms such as left - right, up - down, etc. For example, the left area is for the ordinary comments of the video, and the right area is for the segmented comments of the video. Among them, each segmented comment corresponds to the time interval of the video segment. Specifically, the segmented comments can be divided according to the time interval of the video segment, and the segmented comments of the same video segment are placed together, so that it is convenient for users to view the segmented comments of the same video segment when viewing the segmented comments at the bottom. In addition, the ordinary comments and segmented comments can be distinguished by tags or colors. For example, the area corresponding to the ordinary comments can be marked as "Ordinary Comment Area", and the area corresponding to the segmented comments can be marked as "Segmented Comment Area". The area corresponding to the segmented comments can be set accordingly to allow users to input selection instructions for the segmented comments. When the user selects a target segmented comment (any segmented comment), the video segment corresponding to the target segmented comment can be jumped to according to the user's selection instruction. For example, if the user inputs a selection instruction for segmented comment A, the corresponding video segment is determined according to the time area corresponding to segmented comment A, and then the corresponding video segment is jumped to. Among them, the selection instruction can be instructions such as clicking, double - clicking, and long - pressing on the segmented comment, and no specific limitation is made here.

[0085] In this embodiment, by displaying the comments and segmented comments of the target video in different areas at the bottom of the target video, the segmented comments correspond to the time areas of the corresponding video segments. When a selection instruction for the segmented comment is received, the video segment corresponding to the segmented comment is jumped to, so that users can conveniently view the segmented comments in the bottom comment area and can jump to the corresponding video segment as needed, further improving the user experience.

[0086] Embodiment Two Figure 10 The block diagram of the video comment display device according to Embodiment Two 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 embodiments of the present application. The program modules referred to in the embodiments of the present application refer 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. As Figure 10 shown, the device 1000 may include: a segmentation module 1010, a determination module 1020, and a display module 1030, where: The segmentation module 1010 is used to segment the target video to obtain video segments of the target video; The determination module 1020 is used to obtain the comments of the target video and determine the segmented comments corresponding to each video segment based on the comments; A display module 1030, configured to display, in a predetermined area of a playback interface of the target video, a segmented comment corresponding to a target video segment when playing the target video segment.

[0087] In an alternative embodiment, the segmentation module 1010 is further configured to: Display a segmentation editing interface of the target video based on a preset instruction; Segment the target video based on an input instruction for the segmentation editing interface and generate segmented target information to obtain video segments of the target video, where the target information includes at least some of the ID, segmentation start time, segmentation end time, and segmentation description of the target video.

[0088] In an alternative embodiment, the segmentation module 1010 is further configured to: Obtain target modality information of the target video, where the target modality information includes at least one of frame images, audio, and text of the target video; Analyze the target modality information to determine segmentation feature information of the target video; Segment the target video based on the segmentation feature information to obtain video segments of the target video.

[0089] In an alternative embodiment, the segmentation module 1010 is further configured to: Perform image analysis on frame images of the target video to obtain scene transition information in the frame images; Perform speech recognition on the audio of the target video to obtain an audio recognition text, and analyze the audio recognition text to obtain audio analysis information; Analyze the text of the target video to obtain text analysis information; Determine the segmentation feature information based on the scene transition information, the audio analysis information, and / or the text analysis information.

[0090] In an alternative embodiment, the determination module 1020 is further configured to: Generate a segmentation description for each of the video segments based on the target modality information; Analyze and extract keywords of comments of the target video based on a natural language processing method; Determine a segmented comment corresponding to each of the video segments based on semantic similarity between the keywords and the segmentation description.

[0091] In an alternative embodiment, the apparatus 1000 is further configured to: Receive an adjustment instruction for the video segment, where the adjustment instruction is used to merge or split the video segment; Upon receiving the adjustment instruction, adjust the video clip according to the adjustment instruction to obtain an adjusted video clip.

[0092] In an alternative embodiment, the display module 1030 is further configured to: On the playback interface of the target video, display the segmented comments corresponding to the target video clip in a sidebar, and adjust the playback screen of the target video so that the playback screen does not overlap with the sidebar; Upon receiving a close instruction for the sidebar, close the sidebar and restore the playback screen to its original size.

[0093] In an alternative embodiment, the apparatus 1000 is further configured to: Display the comments of the target video and the segmented comments in different areas at the bottom of the target video, where the segmented comments correspond to a target time interval, and the target time interval is the time interval of the video clip corresponding to the segmented comments; Upon receiving a selection instruction for a target segmented comment, jump to the video clip corresponding to the target segmented comment, where the target segmented comment is any segmented comment.

[0094] Embodiment III Figure 11 Schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing the video comment display method according to Embodiment III of the present application. 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-mounted server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers). As Figure 11 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: The memory 10010 includes at least one type of computer-readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as the hard disk or 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, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 10000. Of course, the memory 10010 may also include both the internal storage module and the external storage device of the computer device 10000. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed on the computer device 10000, such as the program code of the video review display method. In addition, the memory 10010 can also be used to temporarily store various data that has been output or will be output.

[0095] In some embodiments, the processor 10020 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other chip. 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.

[0096] The network interface 10030 may include a wireless network interface or a wired network interface, which 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 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 enterprise intranet (Intranet), the Internet, the Global System of Mobile communication (GSM for short), Wideband Code Division Multiple Access (WCDMA for short), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0097] It should be noted that Figure 11 Only the computer device with components 10010 - 10030 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0098] In this embodiment, the video comment display 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 the processor 10020) to complete the embodiments of the present application.

[0099] Embodiment 4 The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video comment display method in the embodiments are implemented.

[0100] In this embodiment, the computer-readable storage medium includes flash memory, hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), random access memories (RAM), static random access memories (SRAM), read-only memories (ROM), electrically erasable programmable read-only memories (EEPROM), programmable read-only memories (PROM), magnetic memories, magnetic disks, optical discs, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device. Of course, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is generally used to store the operating system installed on the computer device and various application software, such as the program code of the video comment display method in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various data that have been output or will be output.

[0101] Embodiment 5 The embodiment of the present application also provides a computer program product, including a computer program, which when executed by a processor implements the method in the above embodiment.

[0102] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the embodiments of the present application can be implemented by a general-purpose computer device. 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 program codes executable by the computer device. Thus, 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 here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0103] It should be noted that the above are only the preferred embodiments of the present application, and do not limit the patent protection scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for displaying video comments, characterized in that, The method includes: Segmenting the target video to obtain video segments of the target video; Obtaining comments of the target video and determining segmented comments corresponding to each of the video segments based on the comments; When playing a target video segment of the target video, displaying the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video.

2. The method according to claim 1, characterized in that, The segmenting the target video to obtain video segments of the target video includes: Displaying a segmentation editing interface of the target video based on a preset instruction; Segmenting the target video based on an input instruction for the segmentation editing interface and generating segmented target information, to obtain video segments of the target video, where the target information includes at least some information of the ID, segmentation start time, segmentation end time, and segmentation description of the target video.

3. The method according to claim 1, wherein The segmenting the target video to obtain video segments of the target video includes: Obtaining target modality information of the target video, where the target modality information includes at least one of frame images, audio, and text of the target video; Analyzing the target modality information to determine segmentation feature information of the target video; Segmenting the target video based on the segmentation feature information to obtain video segments of the target video.

4. The method according to claim 3, wherein The analyzing the target modality information to determine segmentation feature information of the target video includes: Performing image analysis on frame images of the target video to obtain scene transition information in the frame images; Performing speech recognition on the audio of the target video to obtain an audio recognition text, and analyzing the audio recognition text to obtain audio analysis information; Analyzing the text of the target video to obtain text analysis information; Determining the segmentation feature information based on the scene transition information, the audio analysis information, and / or the text analysis information.

5. The method according to claim 3, characterized in that The determining segmented comments corresponding to each of the video segments based on the comments includes: Generating segmentation descriptions for each of the video segments based on the target modality information; Analyzing and extracting keywords of the comments of the target video based on a natural language processing method; Determining segmented comments corresponding to each of the video segments through semantic similarity based on the keywords and the segmentation descriptions.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Receiving an adjustment instruction for the video segment, where the adjustment instruction is used to merge or split the video segment; When receiving the adjustment instruction, adjusting the video segment according to the adjustment instruction to obtain an adjusted video segment.

7. The method according to any one of claims 1-5, characterized in that, The displaying the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video includes: Displaying the segmented comments corresponding to the target video segment in a sidebar on the playback interface of the target video, and adjusting the playback screen of the target video so that the playback screen does not overlap with the sidebar; When receiving a close instruction for the sidebar, closing the sidebar and restoring the playback screen to its original size.

8. The method according to any one of claims 1-5, characterized in that, The method further includes: Display the comments of the target video and the segmented comments in different areas at the bottom of the target video, where the segmented comments correspond to target time intervals, and the target time intervals are the time intervals of the video segments corresponding to the segmented comments; When a selection instruction for a target segmented comment is received, jump to the video segment corresponding to the target segmented comment, and the target segmented comment is any one of the segmented comments.

9. A video comment display device, characterized in that The device includes: A segmentation module, configured to segment a target video to obtain video segments of the target video; A determination module, configured to obtain comments of the target video and determine segmented comments corresponding to each of the video segments based on the comments; A display module, configured to display the segmented comments corresponding to the target video segment in a predetermined area of the playback interface of the target video when playing the target video segment of the target video.

10. A computer device, characterized in that, Includes: 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 execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, Computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. 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 any one of claims 1 to 8 are implemented.

Images