Video submission topic processing method and device based on barrage content and computing device

Abstract

The embodiment of the application discloses a video contribution topic processing method and device based on bullet screen content and a computing device, wherein the method comprises the following steps: acquiring the number of newly added bullet screens of a plurality of videos in a preset period, and screening target videos from the plurality of videos according to the number of newly added bullet screens; extracting the video title of the target video and the bullet screen content of the newly added bullet screens of the target video in the preset period; processing the video title and the bullet screen content by using a trained language generation model to generate video contribution topic information; determining a contribution push script corresponding to the video contribution topic information, and pushing the contribution push script to a first target push user, so that the first target push user performs video contribution according to the contribution push script. The application efficiently realizes accurate determination of a hot topic, and pushes the contribution push script corresponding to the hot topic to the user through the message push capability, thereby effectively improving the enthusiasm of the user in participating in video contribution.

Description

Technical Field

[0001] This application relates to the field of Internet technology, specifically to a method, apparatus, and computing device for processing video submission topics based on bullet screen content. Background Technology

[0002] Video platforms frequently host video submission events, which include video submission topics around which users can create and submit videos. However, in current technology, these topics are usually written by operations staff and may not be of interest to a broad range of users, thus affecting user participation and making it difficult to attract users to create videos. Summary of the Invention

[0003] In view of the above problems, this application proposes a method, apparatus, computing device and computer storage medium for processing video submission topics based on bullet screen content, in order to solve the following problems: the video submission topics obtained by the existing methods cannot well meet the interests of the majority of users, affecting the enthusiasm of users to participate in video submissions.

[0004] According to one aspect of the embodiments of this application, a method for processing video submission topics based on bullet screen content is provided, including:

[0005] Get the number of new bullet comments for multiple videos within a preset time period, and filter the target video from multiple videos based on the number of new bullet comments;

[0006] Extract the video title of the target video and the bullet comments added to the target video within a preset time period;

[0007] The trained language generation model is used to process video titles and bullet comments to generate video submission topic information;

[0008] Determine the submission push text corresponding to the video submission topic information and push it to the first target users so that they can submit videos based on the submission push text.

[0009] Furthermore, the target video selected from multiple videos based on the number of newly added bullet comments further includes:

[0010] Multiple videos are sorted in descending order of the number of new comments, and the videos with the highest number of comments are selected as the target videos.

[0011] Furthermore, the corresponding push notification text for video submissions will include:

[0012] The video submission topic title and keywords from the video submission topic information are concatenated into the submission page link, and the submission page link and / or the image recognition code corresponding to the submission page link are used as the submission entry information;

[0013] Add the submission entry information to the text to generate a submission push notification text that corresponds to the video submission topic information.

[0014] Furthermore, before pushing the message to the first target user, the method also includes:

[0015] Users who have pre-defined interactive behaviors with the target video are selected from multiple users as the primary target users for push notifications.

[0016] Furthermore, after pushing the message to the first target user, the method also includes:

[0017] Receive submitted videos from any of the first target users;

[0018] The submitted video is pushed to the second target user, who is then invited to interact with the video.

[0019] Furthermore, the method also includes:

[0020] Remove the users who submitted the video from the first target users to obtain the second target users.

[0021] Furthermore, after inviting the second target user to interact with the submitted video, the method also includes:

[0022] Obtain interactive behavior data of the second target users regarding the submitted videos;

[0023] Based on interaction data, submitted videos that meet preset criteria are selected and displayed on the platform page.

[0024] According to another aspect of the embodiments of this application, a video submission topic processing device based on bullet screen content is provided, including:

[0025] The filtering module is suitable for obtaining the number of new bullet comments in multiple videos within a preset time period, and filtering the target video from multiple videos based on the number of new bullet comments;

[0026] The extraction module is suitable for extracting the video title of the target video and the bullet comments added to the target video within a preset time period;

[0027] The generation module is suitable for using a trained language generation model to process video titles and bullet screen content to generate video submission topic information;

[0028] The copywriting determination module is suitable for determining the submission push copy that corresponds to the video submission topic information;

[0029] The push module is suitable for pushing submission push text to the first target push users, so that the first target push users can submit videos based on the submission push text.

[0030] According to another aspect of the embodiments of this application, a computing device is provided, including: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;

[0031] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-mentioned video submission topic processing method based on bullet screen content.

[0032] According to another aspect of the embodiments of this application, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, the executable instruction causing a processor to perform operations corresponding to the above-described video submission topic processing method based on bullet screen content.

[0033] According to the video submission topic processing method, apparatus, computing device, and computer storage medium based on bullet screen content provided in the embodiments of this application, the target video with high attention can be conveniently selected from multiple videos based on the number of newly added bullet screens; by utilizing the semantic understanding capability of the language generation model, the video title and bullet screen content are processed to automatically generate video submission topic information, thereby determining the corresponding submission push text, which efficiently and accurately determines the hot topics, and pushes the submission push text corresponding to the hot topics to users through message push capability, effectively improving users' enthusiasm for participating in video submissions, stimulating users' passion for video creation, and attracting users to focus on hot topics for video creation.

[0034] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of the embodiments of this application are described below. Attached Figure Description

[0035] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0036] Figure 1A flowchart illustrating a video submission topic processing method based on bullet screen content according to an embodiment of this application is shown;

[0037] Figure 2 A flowchart illustrating a video submission topic processing method based on bullet screen content according to another embodiment of this application is shown;

[0038] Figure 3 A structural block diagram of a video submission topic processing apparatus based on bullet screen content according to an embodiment of this application is shown;

[0039] Figure 4 A schematic diagram of the structure of a computing device according to an embodiment of this application is shown. Detailed Implementation

[0040] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0041] First, the terms and concepts involved in one or more embodiments of this application will be explained.

[0042] Bullet comments: These are comments and other content displayed on the screen in a scrolling manner during video playback.

[0043] AIGC (Artificial Intelligence Generated Content) refers to generative artificial intelligence, a technique based on generative adversarial networks, large pre-trained models, and other AI methods. It learns from and recognizes existing data to generate relevant content with appropriate generalization capabilities. Through training models and learning from large amounts of data, AIGC can generate relevant content based on input conditions or guidance.

[0044] NLP (Natural Language Processing) is a discipline that uses computer technology to analyze, understand, and process natural language. It uses computers as a powerful tool for language research, quantitatively studies language information with the support of computers, and provides language descriptions that can be used by both humans and computers.

[0045] Figure 1 A flowchart illustrating a video submission topic processing method based on bullet screen content according to an embodiment of this application is shown, such as... Figure 1 As shown, the method includes the following steps:

[0046] Step S101: Obtain the number of new bullet comments for multiple videos within a preset time period, and select the target video from the multiple videos based on the number of new bullet comments.

[0047] Video platforms contain a large number of videos, and users can send comments and thoughts via bullet comments (danmu) while watching. Bullet comments effectively reflect the content that users are interested in. In this embodiment, the number of new bullet comments within a preset time period is used to identify videos with high engagement within that time period. Specifically, the number of new bullet comments for multiple videos within the preset time period can be counted, and the video with the most new bullet comments can be selected as the target video, i.e., the video with high engagement within that preset time period.

[0048] Step S102: Extract the video title of the target video and the bullet comments added to the target video within a preset time period.

[0049] The content users focus on changes over time, while bullet comments (danmu) are highly immediate and timely, effectively reflecting the content users are interested in when sending them. Therefore, after selecting the target video, the video title and newly added bullet comments within a preset time period can be extracted to reflect the content users are interested in during that period, thus generating video submission topic information.

[0050] Step S103: Use the trained language generation model to process the video title and bullet screen content to generate video submission topic information.

[0051] In this embodiment, AIGC technology is used to automatically generate video submission topic information based on the video title and bullet screen content. Specifically, the video title and bullet screen content extracted in step S102 can be input into a trained language generation model for processing. The language generation model performs semantic understanding and analysis on the video title and bullet screen content to generate video submission topic information. The video submission topic information may include a video submission topic title and topic keywords.

[0052] Step S104: Determine the submission push text corresponding to the video submission topic information and push it to the first target push user so that the first target push user can submit the video according to the submission push text.

[0053] Based on the video submission topic information, determine the corresponding submission push text. This text includes submission entry information and the text itself. Specifically, the submission entry information may be a submission page link and / or a corresponding image recognition code. The submission push text is then sent to the primary target users. These users can easily access the submission page corresponding to the video submission topic information by using the submission entry information in the push text, such as by triggering the submission page link or scanning the image recognition code, to upload their video and complete the submission.

[0054] According to the video submission topic processing method based on bullet screen content provided in the embodiments of this application, the target video with high attention can be easily selected from multiple videos based on the number of newly added bullet screens. By utilizing the semantic understanding capability of the language generation model, the video title and bullet screen content are processed to automatically generate video submission topic information, thereby determining the corresponding submission push copy. This efficiently and accurately identifies hot topics, and pushes the submission push copy corresponding to the hot topics to users through message push capability, effectively improving users' enthusiasm for participating in video submissions, stimulating users' passion for video creation, and attracting users to focus on hot topics for video creation.

[0055] Figure 2 A flowchart illustrating a video submission topic processing method based on bullet screen content according to another embodiment of this application is shown, such as... Figure 2 As shown, the method includes the following steps:

[0056] Step S201: Obtain the number of new bullet comments for multiple videos within a preset time period, and select the target video from the multiple videos based on the number of new bullet comments.

[0057] In video community channels of video platforms, users can create and upload videos, which can then be watched, commented on, and used by other users, thereby generating community activity. To further enhance community activity, video submission activities can be launched. Considering that the number of new bullet comments (danmaku) for a video within a preset time period can reflect the level of attention each user pays to that video within that period, the more bullet comments a video receives, the higher the level of attention from users. In this embodiment, the number of new bullet comments is used to quickly filter target videos. Those skilled in the art can set the preset time period according to actual needs. For example, the preset time period can be set to several days or several hours.

[0058] Specifically, at preset time intervals, the number of new bullet comments (danmaku) for multiple videos within the current preset time interval can be counted. The videos are then sorted in descending order of the number of new bullet comments, and the top-ranked videos (a preset number) are selected as target videos. Those skilled in the art can set the preset number according to actual needs, such as 10. This processing method allows for the convenient filtering of videos with high attention within a preset time interval, enabling the extraction of relevant content for generating video submission topic information.

[0059] Step S202: Extract the video title of the target video and the bullet comments added to the target video within a preset time period.

[0060] If there are multiple target videos, for each target video, the video title and the content of any new bullet comments added to that target video within a preset time period can be extracted to generate the corresponding video submission topic information. There is a corresponding relationship between the target videos and the video submission topic information.

[0061] Step S203: Use the trained language generation model to process the video title and bullet screen content to generate video submission topic information.

[0062] The video title and bullet comments are typically in natural language, allowing for convenient semantic understanding and analysis using a trained language generation model. Specifically, topic generation instructions can be constructed based on the video submission topic generation requirements. These instructions can be data describing the needs of generating the video submission topic, such as defining the specific tasks, scope, and purpose of the language generation model. These instructions, which can be recognized and executed by the language generation model, can be in natural language or similar formats. The topic generation instructions, the target video's title, and the target video's bullet comments are then provided to the trained language generation model. The model responds to the topic generation instructions by performing semantic understanding and analysis on the video title and bullet comments, automatically generating the video submission topic information.

[0063] Language generation models can be generative large-scale language models, such as GPT (Generative Pre-Trained Transformer), BERT (Bidirectional Encoder Representation from Transformers), or ERNIE (Enhanced Representation through Knowledge Integration). Essentially, a language generation model is a generative model that trains a neural network structure using a large amount of language data to obtain an AI (Artificial Intelligence) model. This language generation model possesses natural language processing (NLP) capabilities, can effectively understand natural language, and output relevant results that conform to natural language instructions.

[0064] Step S204: Concatenate the video submission topic title and topic keywords from the video submission topic information into the submission page link, and use the submission page link and / or the image recognition code corresponding to the submission page link as the submission entry information.

[0065] The video submission topic information may include the video submission topic title and topic keywords. Specifically, topic keywords can be used as tags, and these tags, along with the video submission topic title, can be appended to the submission page link.

[0066] For example, if a target video's title is "2023 *** Concert Full Record," a language generation model processes the video title and the newly added comments within a preset time period. The resulting video submission topic title is "*** Concert," and the topic keywords include song title 1, song title 2, song title 3, and song title 4. Assume the basic format of the submission page link is:

[0067] bilibili: / / uper / center_plus? relation_from=center_plus&tab_index=2? topic_id=[]&topic_name=[]&tags=[];

[0068] When concatenating the links, you can enter the topic ID corresponding to the video submission topic title in the topic_id field; enter the video submission topic title in the topic_name field, i.e., *** Concert; and enter topic keywords in the tags field, i.e., song name 1, song name 2, song name 3, and song name 4. After completing the above topic-related field entries, you will get the concatenated submission page link.

[0069] After completing the link assembly, the submission page link can be used as the submission entry information, and / or a corresponding image recognition code can be generated based on the submission page link. The image recognition code can be in the form of a QR code or barcode, and then the image recognition code can be used as the submission entry information.

[0070] Step S205: Add the submission entry information to the text and generate the submission push text corresponding to the video submission topic information.

[0071] The copy text can be written by operations staff, matched from multiple copy text templates in a database, or automatically generated using NLP technology. Add the submission entry information to the copy text. Additionally, add the video submission topic title to the copy text so users understand the topic. After adding the above, the submission push notification text corresponding to the video submission topic information will be generated.

[0072] For example, a copy text might read, "[], the familiar melody is playing, does it evoke memories? Others are sharing their thoughts on watching []! Come and show everyone your creation~", where "[]" is used to add the video submission topic title, and the submission entry information can be added after the last character of the copy text.

[0073] Step S206: Push the submission copy to the first target user.

[0074] To achieve precise and effective push notifications, in this embodiment, the determination of the first target user can be achieved by selecting users who have pre-defined interactive behaviors with the target video from among multiple users. These selected users are more interested in and pay more attention to the video submission topic information corresponding to the target video. These users can be designated as the first target users, and the submission notification text can be pushed to them. This can more accurately stimulate users' enthusiasm for video creation and effectively improve their participation in video submissions. There may be a corresponding relationship between the first target users and the video submission topic information.

[0075] The preset interactive behaviors can include one or more of the following: watching, commenting, sharing, liking, etc. For example, users who have watched the target video within the preset time period or who have sent comments while watching the target video can be selected as the primary target users for push notifications.

[0076] To improve user experience and prevent users from becoming annoyed by push notifications, deduplication can be performed when sending them to users, limiting the number of push notifications sent to the primary target user within a certain period. For example, the number of push notifications could be limited to once.

[0077] Step S207: Receive a submitted video sent by any first target push user, push the submitted video to the second target push user, and invite the second target push user to interact with the submitted video.

[0078] After receiving the submission push notification, any user targeted by the first target can access the submission page corresponding to the video submission topic through the submission entry information in the submission push notification. Specifically, if the submission entry information includes a submission page link, the user can access the submission page by clicking the link; if the submission entry information includes an image recognition code, the user can access the submission page by scanning the image recognition code.

[0079] Because the submission page link includes topic keywords as tags, these keywords are displayed and automatically selected by default on the submission page. The first target user can also add other topic keywords and select a video to submit. The submission page also includes a publish control or a confirm submission control. When the first target user triggers the publish control or confirm submission control, the submitted video and the video submission topic information (such as topic ID, video submission topic title, topic keywords, etc.) carried in the submission page link are sent to the server. In step S207, the server receives the submitted video and video submission topic information sent by any first target user, identifies the topic based on the video submission topic information, categorizes the submitted video according to the topic, and then pushes the submitted video to the second target user, inviting the second target user to interact with the submitted video, such as sending bullet comments or leaving comments.

[0080] The second target user and the first target user can be the same user group or different user groups; this is not limited here. Optionally, considering that the first target user is a user who pays close attention to and is interested in the video submission topic information corresponding to the target video, when determining the corresponding second target user for a certain video submission, the submitter of that video can be removed from the first target user group to obtain the second target user, thus avoiding having one's own submitted video pushed to oneself. In other words, the first target user who sent the video (i.e., the submitter) is removed from the first target user group, and the remaining first target users are designated as second target users, to whom the video is pushed, inviting them to interact such as sending bullet comments and making comments.

[0081] Step S208: Obtain the interaction behavior data of the second target user regarding the submitted video, and based on the interaction behavior data, filter out the submitted videos that meet the preset conditions and display them on the platform page.

[0082] The preset criteria can be a few of the top-ranked metrics such as the number of bullet comments, the number of comments, the number of plays, or the playback duration. For each video submission topic, videos meeting the preset criteria are selected from multiple submissions and displayed on the platform's homepage or community channel pages. This increases the exposure and attention of the selected videos, further enhancing user participation in video submissions, stimulating their enthusiasm for video creation, and encouraging more interactive users to participate in video submissions. This creates a virtuous cycle, promoting better community development.

[0083] According to the video submission topic processing method based on bullet screen content provided in this application embodiment, the method can conveniently filter out target videos with high attention from multiple videos based on the number of newly added bullet screens; by utilizing the semantic understanding capability of the language generation model, the video title and bullet screen content are processed to automatically generate video submission topic information, eliminating the need for operators to write topics and efficiently achieving accurate identification of hot topics; by concatenating the video submission topic information into the submission page link, the submission entry information is determined, and the submission entry information is added to the text, realizing the automated generation of submission push text; and highly attention-grabbing hot topics are selected. The push notifications for submissions related to the topic were sent to users who followed the topic, achieving precise targeting and effectively improving the effectiveness of the push. This allowed for a more targeted approach to motivate users to create videos, boosting community activity through trending topics and attracting users to actively participate in video submissions. Users were also invited to send comments or send bullet comments to the video submissions, enriching the videos available to them. In addition, high-quality submitted videos were selected and displayed on the platform page, leveraging the topic's popularity to give submitted videos and video creators higher exposure and attention, further enhancing users' enthusiasm for participating in video submissions.

[0084] Figure 3 A structural block diagram of a video submission topic processing apparatus based on bullet screen content according to an embodiment of this application is shown, such as... Figure 3 As shown, the device includes: a filtering module 310, an extraction module 320, a generation module 330, a text determination module 340, and a push module 350.

[0085] The filtering module 310 is suitable for: obtaining the number of new bullet comments in multiple videos within a preset time period, and filtering the target video from multiple videos based on the number of new bullet comments.

[0086] The extraction module 320 is suitable for: extracting the video title of the target video and the bullet comments added to the target video within a preset time period.

[0087] The generation module 330 is suitable for: using a trained language generation model to process video titles and bullet screen content to generate video submission topic information.

[0088] The copywriting determination module 340 is suitable for: determining the submission push copy corresponding to the video submission topic information.

[0089] The push module 350 is suitable for: pushing the submission push text to the first target push user, so that the first target push user can submit the video based on the submission push text.

[0090] Optionally, the filtering module 310 is further adapted to: sort multiple videos in descending order of the number of newly added bullet comments, and filter out a preset number of videos that rank first from the sorted results as target videos.

[0091] Optionally, the copywriting determination module 340 is further adapted to: concatenate the video submission topic title and topic keywords from the video submission topic information into the submission page link, and use the submission page link and / or the image recognition code corresponding to the submission page link as submission entry information; add the submission entry information to the copywriting text to generate submission push copy corresponding to the video submission topic information.

[0092] Optionally, the filtering module 310 is further adapted to: select users who have a preset interactive behavior with the target video from multiple users as the first target push users.

[0093] Optionally, the device further includes a receiving module 360, adapted to receive a submitted video sent by any of the first target push users. The push module 350 is further adapted to: push the submitted video to a second target push user and invite the second target push user to interact with the submitted video.

[0094] Optionally, the filtering module 310 is further adapted to: remove the users who submitted the videos from the first target push users to obtain the second target push users.

[0095] Optionally, the filtering module 310 is further adapted to: obtain the interaction behavior data of the second target push user regarding the submitted video; and based on the interaction behavior data, filter out the submitted videos that meet the preset conditions and display them on the platform page.

[0096] The descriptions of the above modules refer to the corresponding descriptions in the method embodiments, and will not be repeated here.

[0097] According to the video submission topic processing device based on bullet screen content provided in this application embodiment, it can conveniently filter out target videos with high attention from multiple videos based on the number of newly added bullet screens; it utilizes the semantic understanding capability of the language generation model to process the video title and bullet screen content, automatically generating video submission topic information, eliminating the need for operators to write topics, and efficiently achieving accurate identification of hot topics; by concatenating the video submission topic information into the submission page link, the submission entry information is determined, and the submission entry information is added to the text, realizing the automated generation of submission push text; and it can identify highly attention-grabbing hot topics. The push notifications for submissions related to the topic were sent to users who followed the topic, achieving precise targeting and effectively improving the effectiveness of the push. This allowed for a more targeted approach to motivate users to create videos, boosting community activity through trending topics and attracting users to actively participate in video submissions. Users were also invited to send comments or send bullet comments to the video submissions, enriching the videos available to them. In addition, high-quality submitted videos were selected and displayed on the platform page, leveraging the topic's popularity to give submitted videos and video creators higher exposure and attention, further enhancing users' enthusiasm for participating in video submissions.

[0098] This application also provides a non-volatile computer storage medium storing at least one executable instruction that can execute the video submission topic processing method based on bullet screen content in any of the above method embodiments.

[0099] Figure 4 The diagram shows a structural schematic of a computing device according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the computing device.

[0100] like Figure 4 As shown, the computing device may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0101] in:

[0102] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.

[0103] Communication interface 404 is used to communicate with other network elements such as clients or other servers.

[0104] The processor 402 is used to execute program 410, specifically to execute the relevant steps in the above embodiment of the video submission topic processing method based on bullet screen content.

[0105] Specifically, program 410 may include program code that includes computer operation instructions.

[0106] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0107] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0108] Specifically, program 410 can be used to cause processor 402 to execute the video submission topic processing method based on bullet screen content in any of the above method embodiments. The specific implementation of each step in program 410 can be found in the corresponding descriptions of the steps and units in the above embodiments of video submission topic processing based on bullet screen content, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0109] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of this application are not directed to any particular programming language. It should be understood that the contents of the embodiments of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best implementation of the embodiments of this application.

[0110] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0111] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various inventive aspects, in the foregoing description of exemplary embodiments of the present application, various features of the present application embodiments are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach to disclosure should not be construed as reflecting an intention that the claimed embodiments of the present application require more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the present application.

[0112] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0113] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the embodiments of this application and form different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0114] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of this application. The embodiments of this application can also be implemented as device or apparatus programs (e.g., computer programs and computer program products) for performing part or all of the methods described herein. Such programs implementing the embodiments of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0115] It should be noted that the above embodiments are illustrative of the embodiments of this application and not limiting of the embodiments of this application, and those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of this application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A method for processing video submission topics based on bullet comments, comprising: The number of new bullet comments in multiple videos within a preset time period is obtained, and the target video is selected from the multiple videos based on the number of new bullet comments. Extract the video title of the target video and the bullet comments added to the target video within the preset time period; The trained language generation model is used to process the video title and the bullet screen content to generate video submission topic information; A submission push notification text corresponding to the video submission topic information is determined and pushed to the first target push user so that the first target push user can submit a video based on the submission push notification text.

2. The method according to claim 1, wherein the step of selecting the target video from multiple videos based on the number of newly added bullet comments further comprises: Multiple videos are sorted in descending order of the number of newly added bullet comments, and the videos with the highest number of bullet comments are selected as the target videos.

3. The method according to claim 1 or 2, wherein determining the submission push text corresponding to the video submission topic information further includes: The video submission topic title and topic keywords in the video submission topic information are concatenated into the submission page link, and the submission page link and / or the image recognition code corresponding to the submission page link are used as the submission entry information; Add the submission entry information to the text to generate a submission push text corresponding to the video submission topic information.

4. The method according to any one of claims 1-3, wherein before pushing to the first target push user, the method further comprises: Users who have pre-defined interactive behaviors with the target video are selected from multiple users as the first target push users.

5. The method according to any one of claims 1-4, wherein after the push is sent to the first target push user, the method further comprises: Receive submitted videos from any of the first target users; The submitted video is pushed to the second target user, who is then invited to interact with the submitted video.

6. The method according to claim 5, further comprising: The user who submitted the video is removed from the first target push users to obtain the second target push users.

7. The method according to claim 5 or 6, after inviting the second target user to interact with the submitted video, the method further includes: Obtain interactive behavior data of the second target user regarding the submitted video; Based on the interaction data, submitted videos that meet the preset conditions are selected and displayed on the platform page.

8. A device for processing video submission topics based on bullet screen content, comprising: The filtering module is adapted to obtain the number of new bullet comments in multiple videos within a preset time period, and filter the target video from the multiple videos based on the number of new bullet comments; The extraction module is adapted to extract the video title of the target video and the bullet comment content of the target video added within the preset time period; The generation module is adapted to use a trained language generation model to process the video title and the bullet screen content to generate video submission topic information; The copywriting determination module is suitable for determining the submission push copy corresponding to the video submission topic information; The push module is adapted to push the submission push text to the first target push user, so that the first target push user can submit a video based on the submission push text.

9. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the video submission topic processing method based on bullet screen content as described in any one of claims 1-7.

10. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the video submission topic processing method based on bullet screen content as described in any one of claims 1-7.

Images