Bullet screen pushing method and video playing method

Abstract

The embodiment of the invention provides a video playing method and a bullet screen recommendation method, and the bullet screen pushing method comprises the steps: obtaining target recommended bullet screen content according to the current playing content of a target video and target object behavior data; and sending the target recommended bullet screen content to a client to enable the client to display the target recommended bullet screen content in a bullet screen recommendation area, and generating a target bullet screen after the target recommended bullet screen content in the bullet screen recommendation area is selected. According to the technical scheme of the embodiment of the invention, the interaction efficiency and the enthusiasm and efficiency of the user to send the bullet screen can be improved.

Description

Technical Field

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

[0002] With the rapid development of video technology, more and more users can watch various video programs through the Internet. In the process of watching video programs, users can interact with anchors or other users by sending bullet comments. The bullet comments refer to the subtitles that pop up and move in a predetermined direction when watching videos on the Internet. It is a kind of communication information. Bullet comments allow users to allow comments or feelings, but unlike ordinary video sharing websites that only display them in the dedicated comment area under the player, they will appear in real time on the video screen in the form of sliding subtitles to ensure that all viewers can notice them.

[0003] At present, the process of inputting barrage content on most multimedia platforms is relatively cumbersome and the interaction efficiency is low, which reduces the enthusiasm of users to participate in the interaction.

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

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

[0006] One aspect of an embodiment of the present application provides a bullet screen push method for a client, the method comprising: Obtain target recommended bullet screen content based on the current playback content of the target video and the target object behavior data; and The target recommended barrage content is sent to the client so that the client displays the target recommended barrage content in a barrage recommendation area, and the target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

[0007] Optionally, according to the current playback content of the target video and the target object behavior data, the target recommended bullet screen content is obtained, including: Determine the target text material based on the current playback content of the target video and the target object behavior data; Determining a target bullet screen display template from a plurality of preset bullet screen display templates according to the material type of the target text material; and The target text material is inserted into the target barrage display template to generate the recommended barrage content.

[0008] Optionally, the target text material is selected from a bullet screen database; The bullet screen database is constructed by the following operations: Get multiple historical bullet comment data; Classify and process the plurality of historical bullet comment data according to text type and / or sentiment tendency; The barrage database is constructed based on the classified multiple historical barrage data.

[0009] Optionally, the target text material is determined according to the current playback content of the target video and the target object behavior data, including: determining a preferred text type of a target object according to the object behavior data; According to the current playing content of the target video and the preferred text type, the target text material of the corresponding type is obtained from the bullet screen database.

[0010] Optionally, the material type includes an emotion type and / or a content type, and the multiple barrage display templates correspond to multiple emotion types and / or multiple content types; and determining the target barrage display template from the preset multiple barrage display templates according to the material type of the target text material includes: Determine the target bullet screen display template according to the emotion type and / or content type of the target text material; wherein: The emotion type and / or content type of the target text material is adapted to the emotion type and / or content type of the target barrage display template.

[0011] Optionally, the target bullet screen display template includes a plurality of placeholders; the target video is a live video in a target live broadcast room; and the target text material is inserted into the target bullet screen display template to generate the recommended bullet screen content, including: Obtaining parameters of the target live broadcast room; Determining the modifying text material according to the parameters; In the process of inserting the target text material into the target bullet screen display template, the modifying material is inserted into the placeholder.

[0012] Optionally, according to the current playback content of the target video and the target object behavior data, the target recommended bullet screen content is obtained, including: Determine a target clustering range of the target object according to the target object behavior data, where different clustering ranges correspond to different sets of recommended bullet comment content; The target recommended barrage content is selected from the recommended barrage content set corresponding to the target clustering range.

[0013] Optionally, the bullet screen sent to the client includes a preset bullet screen; and the bullet screen push method further includes: Get feedback data from the client; The push priority of the preset barrage is adjusted according to the feedback data.

[0014] Another aspect of an embodiment of the present application provides a video playback method for a client, the method comprising: During the playback of the target video, a bullet screen recommendation area is displayed, wherein the bullet screen recommendation area includes target recommended bullet screen content; In response to the target recommended barrage content being selected, generating the target barrage; The target barrage is sent to the server so that the server forwards the target barrage to each of the clients for display.

[0015] Another aspect of an embodiment of the present application provides a video playback device for a client, the device comprising: A display module, used to display a bullet screen recommendation area during the playback of a target video, wherein the bullet screen recommendation area includes target recommended bullet screen content; A generating module, configured to generate the target barrage in response to the target recommended barrage content being selected; The sending module is used to send the target barrage to the server so that the server forwards the target barrage to each of the clients for display.

[0016] Another aspect of an embodiment of the present application provides a bullet screen push device for a server, the device comprising: An acquisition module, used to acquire target recommended bullet screen content according to the current playback content of the target video and the target object behavior data; and The sending module is used to send the target recommended barrage content to the client so that the client displays the target recommended barrage content in the barrage recommendation area. The target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

[0017] Another aspect of an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein: the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0018] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0019] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the method described above when executed by a processor.

[0020] The above technical solution adopted in the embodiment of the present application may have the following advantages: According to the current playback content of the target video and the target object behavior data, the target recommended barrage content is intelligently generated and pushed to the client. The client displays the barrage recommendation area while playing the target video (such as a live video). The barrage recommendation area includes target recommended barrage content (such as "The host is great!" and / or "Where can I buy this?", etc.). In response to the target recommended barrage content being selected, the target barrage is generated. The target barrage is sent to the server so that the server forwards the target barrage to each client for display. It can be seen that the user no longer needs to manually enter the barrage content. You only need to select the target recommended barrage content to display it in the form of a barrage on each client, thereby improving the interaction efficiency and the user's enthusiasm and efficiency in sending barrages. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0022] Figure 1 The following schematically shows an operating environment diagram of a video playback method according to Embodiment 1 of the present application; Figure 2 A flowchart of a video playback method according to Embodiment 1 of the present application is schematically shown; Figure 3 Schematically shows Figure 2 Flow chart of sub-steps of step S200; Figure 4 Schematically shows Figure 2 Flow chart of sub-steps of step S202; Figure 5 The flowchart of the bullet screen push method according to the second embodiment of the present application is schematically shown; Figure 6 Schematically shows Figure 5 Flow chart of sub-steps of step S500; Figure 7Schematically shows Figure 5 Flow chart of sub-steps of step S500; Figure 8 Schematically shows Figure 6 Flow chart of sub-steps of step S600; Fig. 9 Schematically shows Figure 5 Flow chart of sub-steps of step S502; Fig.10 The following schematically shows a newly added flow chart of the bullet screen push method according to the second embodiment of the present application; Fig.11 The following schematically shows an exemplary application flow chart of the present application; Fig.12 The following schematically shows a recommended bullet screen display diagram of an exemplary client of the present application; Fig.13 A block diagram schematically shows a video playback device according to Embodiment 3 of the present application; and Fig.14 A block diagram of a bullet screen push device according to a fourth embodiment of the present application is schematically shown; Fig.15 The hardware architecture diagram of the computer device according to the fifth embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0024] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0025] In the description of the present application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed, but are only used to facilitate the description of the present application and to distinguish each step, and therefore should not be understood as a limitation on the present application.

[0026] First, the following terms are explained: Danmu refers to subtitles, pictures, etc. that pop up and move in a predetermined direction when watching a video on the Internet. There is no fixed word for Danmu in English yet, and it is usually called: comment, danmaku, barrage, bullet screen, bullet-screen comment, etc. Danmu allows viewers to comment or feel the video, but unlike ordinary video sharing websites that only display comments in the dedicated comment area under the player, it will appear in real time on the video screen in the form of sliding subtitles to ensure that all viewers can notice it. Danmu can be managed by the Danmu system. Some Danmu systems can use CSS (CascadingStyle Sheets, Cascading Style Sheets) or JavaScript language to provide specific Danmu forms, such as the appearance or disappearance of Danmu in a specific position, control the speed of Danmu pop-up, Danmu position, etc. In addition, the Danmu that appears fixed at the bottom or top of the screen will also be used as subtitles for videos without subtitles.

[0027] For example, the data structure of a bullet comment can be as follows: { The time of emission in the video is in seconds; Types of barrages; The size of the barrage text; The color of the barrage text; Date the comment was created; The class name of the bullet comment; The user ID that created the bullet comment; Barrage logo; Barrage content (e.g., text, images, controls); The duration of the barrage; Whether the bullet screen has a border; The color of the bullet screen border; The interline style of the bullet comment; } Secondly, in order to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the relevant technologies are described below: With the rapid development of video technology, more and more users can watch various video programs through the Internet. In the process of watching video programs, users can interact with anchors or other users by sending bullet comments. The bullet comments refer to the subtitles that pop up and move in a predetermined direction when watching videos on the Internet. It is a kind of communication information. Bullet comments allow users to allow comments or feelings, but unlike ordinary video sharing websites that only display them in the dedicated comment area under the player, they will appear in real time on the video screen in the form of sliding subtitles to ensure that all viewers can notice them.

[0028] However, the applicant understands that when users watch live broadcasts, manually inputting bullet screen content is time-consuming and labor-intensive. Especially in the case of frequent interactions, it is difficult to maintain the smoothness of the interaction. This complex interaction process reduces the user's enthusiasm for participating in the interaction.

[0029] To this end, the embodiments of the present application provide a video playback method and a bullet screen push method technical solution to overcome the above problems, as described below for details.

[0030] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0031] like Figure 1 As shown, the operating environment diagram includes: Figure 1 As shown, the environmental application schematic diagram includes: a service platform 2 and a client.

[0032] The service platform 2 can be connected to the client terminals ( 4A, 4B, ..., 4N) via a network.

[0033] The service platform 2 can provide various content and bullet screen services for the client. For example, the bullet screen is sent to the client via the network. The network includes various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices and / or the like. The network may include physical links, such as coaxial cable links, twisted pair cable links, optical fiber links, combinations thereof, etc. The network may include wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0034] The service platform 2 may be a single server, a server cluster or a cloud computing service center, which is used to provide various services. For example: The service platform 2 may provide content services. The content services may be configured to provide content such as video, audio, text data, or a combination thereof. The content may include content streams (e.g., video streams, audio streams, information streams), content files (e.g., video files, audio files, text files), and / or other data.

[0035] The service platform 2 can be configured to manage messages for various content items. Users can browse content and access different content items to view comments for specific content, such as comments posted by other users for the specific content. Comments from users associated with a specific content item can be output to other users who view the specific content item. For example, all users who access a content item (e.g., a video) can view comments associated with the content item. The input comment content can be output in real time or near real time.

[0036] The service platform 2 may be configured to receive a plurality of messages. The plurality of messages may include a plurality of bullet comments associated with the content.

[0037] The service platform 2 may be configured to process multiple messages, for example, various processing operations such as message storage, message filtering, and message push. Among them, message storage is used to store multiple messages in a data storage such as a database. Message filtering may include rejecting or marking messages that match the filtering criteria. Among them, the filtering criteria may specify terms and / or phrases, such as profanity, hate speech, indecent language, etc. The filtering criteria may specify characters, such as symbols, fonts, etc. The filtering criteria may specify languages, computer-readable code patterns, etc.

[0038] The service platform 2 can perform natural language processing, topic recognition, pattern recognition, artificial intelligence, etc. to automatically determine the characteristics of the message and / or group the message. As an example, frequently occurring phrases or patterns can be identified as topics. As another example, a database of topics associated with the content can be maintained. Topics can include genres (e.g., action, drama, comedy), personalities (e.g., actors, actresses, directors), languages, etc. Messages can be grouped based on the characteristics of the client device and / or the user sending the message. Demographics, interests, history, and / or the like can be stored for multiple users to determine potential groupings of messages. For example, the bullet screens uploaded by each user can be screened, filtered, sorted, and personalized push, etc.

[0039] The service platform 2 may provide a bullet screen service, which is configured to allow users to comment and / or share comments (i.e. bullet screens) associated with the content. The bullet screens are presented on the same screen together with the content. The bullet screens may be displayed in an overlay above the content and may have animation effects. For example, the bullet screens may scroll (e.g., from right to left, from left to right, from top to bottom, ...), and the animation effect may be implemented based on the transition property of CSS3.

[0040] The client (4A, 4B, ..., 4N) may be configured to access the content and services of the service platform 2. The client (4A, 4B, ..., 4N) may include an electronic device carrying or connected to a display panel, such as a mobile device, a tablet device, a laptop computer, a workstation, a virtual reality device, a gaming device, a digital streaming device, a vehicle client, a smart TV, a set-top box, etc., and may also include a virtualized computing instance. The virtualized computing instance may include a virtual machine, such as a simulation of a computer system, an operating system, a server, etc.

[0041] The client (4A, 4B, ..., 4N) may be associated with one or more users. A single user may also use one or more of the clients (4A, 4B, ..., 4N) to access the service platform 2. The client (4A, 4B, ..., 4N) may travel to various locations and use different networks to access the service platform 2.

[0042] The client (4A, 4B, ..., 4N) may include multiple client programs, such as a video APP, a live broadcast APP or a mini program with a built-in bullet screen system. In this embodiment, the video and other contents provided by the service platform 2 may be presented through the client program, and the bullet screen system may present the bullet screen contents in a specific manner.

[0043] The client (4A, 4B, ..., 4N) may include an interface, which may include a touch pad, a touch screen, a mouse, a keyboard or other sensing elements. For example, the input element may be configured to receive user instructions, and the user instructions may enable the client (4A, 4B, ..., 4N) to perform various operations, such as inputting bullet comments, etc.

[0044] It should be noted that the above devices are exemplary, and the number and type of devices are adjustable in different scenarios or according to different needs.

[0045] Embodiment 1 This method embodiment can be executed in a client. In the following, the client is taken as the execution subject of this process.

[0046] Figure 2 The flowchart of the video playback method according to the first embodiment of the present application is schematically shown.

[0047] like Figure 2 As shown, the video playback method may include steps S200 to S204, wherein: Step S200, during the process of playing the target video, displaying a bullet screen recommendation area, wherein the bullet screen recommendation area includes target recommended bullet screen content; Step S202, in response to the target recommended barrage content being selected, generating the target barrage; Step S204, sending the target barrage to the server, so that the server forwards the target barrage to each of the clients for display.

[0048] The video playback method provided in this embodiment displays a barrage recommendation area during the process of playing a target video (such as a live video). The barrage recommendation area includes target recommended barrage content (such as, "The host is great!" and / or "Where can I buy this?", etc.). In response to the target recommended barrage content being selected, a target barrage is generated. The target barrage is sent to the server so that the server forwards the target barrage to each client for display. It can be seen that in the embodiment of the present application, the user no longer needs to manually enter the barrage content. It only needs to select the target recommended barrage content, and it can be displayed in the form of a barrage on each client, thereby improving the interaction efficiency and the user's enthusiasm and efficiency in sending barrages.

[0049] The following combination Figure 2 , each step in steps S200~S204 and other optional steps are explained in detail.

[0050] Step S200, During the playback of the target video, a bullet screen recommendation area is displayed, and the bullet screen recommendation area includes target recommended bullet screen content.

[0051] Exemplarily, the target video may be a live video, a recorded video, or the like.

[0052] The target recommendation barrage content can be of various types, such as positive feedback (such as "The host is great!"), negative feedback (such as "The picture quality is a bit laggy"), and inquiries (such as "Where can I buy this?").

[0053] The bullet chat recommendation area can be located in a corner of the screen (such as the upper right corner or the lower left corner, etc.) to ensure that it is convenient for users to make selections and operations without affecting the user's viewing experience.

[0054] In some embodiments, in order to enrich the recommended barrage content, multimedia elements such as emoticons, GIF animations, short video clips, etc. can be added to each recommended barrage content.

[0055] The bullet screen recommendation area can be displayed in various ways such as floating windows, shortcut buttons, pop-up windows, etc.

[0056] In some embodiments, the recommended bullet screen content may be displayed in a variety of forms such as a scrolling list, a drop-down menu, a floating button, etc.

[0057] In an optional embodiment, if Figure 3 As shown, step S200 may include: Step S300, displaying recommended controls; and Step S302, in response to triggering the recommendation control, displaying the bullet screen recommendation area in a pop-up window.

[0058] Exemplarily, the recommendation control may be in various forms such as a button, an icon or a link, etc. The recommendation control may be accompanied by prompting texts such as "recommended bullet screen" and "hot bullet screen" to prompt the user to perform human-computer interaction.

[0059] In some embodiments, the recommendation control can be configured at the bottom, side, or top navigation bar of the target page to reduce interference to the user. (It should be noted that the target video is played on the target page) In some embodiments, the pop-up window may include multiple classification labels, such as "positive feedback", "negative feedback", "inquiry", etc., so that users can select the recommended barrage content they want by clicking on these labels.

[0060] Step S202 , in response to the target recommended barrage content being selected, the target barrage is generated.

[0061] In an optional embodiment, the bullet screen recommendation area is configured with multiple sending controls, such as Figure 4 As shown, step S202 may include: Step S400, displaying a plurality of recommended bullet-screen content in the bullet-screen recommendation area, with one sending control corresponding to one recommended bullet-screen content; Step S402, in response to triggering a target sending control corresponding to the target recommended barrage content, generating the target barrage.

[0062] Exemplarily, a sending control, such as a button, icon or link, may be configured next to or below each recommended bullet screen content. When a user browses the recommended bullet screen content, the sending control corresponding to the target recommended bullet screen content may be triggered by clicking, touching or other interactive methods.

[0063] In this embodiment, for ease of understanding, Fig.12 By configuring multiple sending controls in the barrage recommendation area, users can select and send the corresponding recommended barrage content with one click, thereby improving the efficiency and convenience of users sending barrages.

[0064] Step S204 , sending the target barrage to the server so that the server forwards the target barrage to each of the clients for display.

[0065] In some embodiments, the target barrage can be sent to the public chat area of ​​the third-party platform through various standardized interfaces such as REST API (Representational State Transfer Application Programming Interface, an application programming interface designed based on the representational state transfer principle) and GRPC (GRPC Remote Procedure Calls, a high-performance remote procedure call protocol), so that the recommended barrage (i.e., the target barrage) and the ordinary barrage can be displayed indistinguishably.

[0066] In an optional embodiment, the video playback method may further include: in response to a closing operation on the recommendation control, closing and hiding the recommendation control.

[0067] Users can choose to turn off the recommendation controls to reduce obstruction of the target video, thereby improving the user's viewing experience.

[0068] In an optional embodiment, the target video is played in a target page, and the target page is also configured with a setting control. The video playing method may also include: when the recommendation control is in a closed or hidden state, in response to the triggering of the setting control, popping up the recommendation control.

[0069] In some embodiments, if the user has not interacted with the recommendation control for more than a preset time (e.g., ten minutes, two hours), the user may be reminded through a pop-up window or the like whether to re-enable the recommendation control to improve the user experience.

[0070] After the user closes the recommendation control, the recommendation control can be popped up again through the setting control on the target page, so that the user can freely set it according to his or her needs.

[0071] In an optional embodiment, the video playback method may further include: In response to any one of the multiple sending controls being triggered, hiding the bullet screen recommendation area.

[0072] Users can choose to display or hide the barrage recommendation area to increase interactivity and controllability and improve user experience.

[0073] Embodiment 2 This method embodiment can be executed in a server. Below, the server is used as the execution subject of this process.

[0074] It should be noted that the technical details and technical effects of this embodiment can be referred to in Example 1.

[0075] Figure 5The flowchart of the bullet screen push method according to the second embodiment of the present application is schematically shown.

[0076] like Figure 5 As shown, the bullet screen push method may include steps S500 to S502, wherein: Step S500, obtaining target recommended bullet screen content according to the current playback content of the target video and the target object behavior data; and Step S502, sending the target recommended barrage content to the client, so that the client displays the target recommended barrage content in a barrage recommendation area, and the target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

[0077] The following combination Figure 5 , each step in steps S500~S502 and other optional steps are explained in detail.

[0078] Step S500 , according to the current playback content of the target video and the target object behavior data, obtain the target recommended barrage content.

[0079] Exemplarily, the currently playing content may be a failure scene in a game competition, a host dancing scene in an entertainment live broadcast, or other content.

[0080] The target object (such as the user, for ease of understanding, the target object will be referred to as the user in the following) behavior data includes user ID, barrage content, barrage sending frequency, barrage content type, likes, comments, gift giving and other behavior data.

[0081] User behavior data can be collected in a lightweight manner through logs, tracking points, etc. Specifically, tracking points can be set at user interaction nodes (such as bullet message sending buttons, like buttons, comment areas, etc.) to collect user behavior data by monitoring these events. It should be noted that the collection of the above user behavior data is anonymized data with the user's consent.

[0082] In some embodiments, the user behavior data may be transmitted to a preprocessing module for processing. The processing includes removing duplicate data, filtering abnormal data (such as extreme value filtering), format standardization, etc. Then, the preprocessed user behavior data is stored in a server or a local behavior database. In some embodiments, the user behavior data may be backed up regularly to ensure the security and integrity of the user behavior data as much as possible.

[0083] The user behavior data can be transmitted to the data analysis module for analysis. Specifically, the user behavior data is deeply analyzed through a machine learning algorithm to extract the user's interest preferences and interaction habits, so as to be used to assist in the subsequent generation of personalized recommended bullet content. In some embodiments, the user behavior data can be processed in parallel through a big data platform such as Hadoop or Spark, thereby improving the speed and efficiency of data analysis.

[0084] The target recommended barrage content may be one barrage content or multiple barrage contents. For example, the target recommended barrage content may be "The host is great!", "The host did a good job", "I like you", etc.

[0085] In an optional embodiment, if Figure 6 As shown, step S500 may include: Step S600, determining a target clustering range of the target object according to the target object behavior data, where different clustering ranges correspond to different sets of recommended bullet comment content; Step S602: Select the target recommended barrage content from the recommended barrage content set corresponding to the target clustering range.

[0086] Exemplarily, user behavior data can be processed by collaborative filtering to calculate the similarity of each user. For example: User A sent comments such as "This is really good" and "So cute". User B sent comments such as "So funny" and "So interesting". User C sent comments such as "I like this" and "Very good". Assuming that the similarity calculation result between user A and user B is 0.8, it means that their interests are similar. Therefore, when recommending a certain bullet comment content to user A, if it is believed that B may also like it, then this recommended bullet comment content can also be recommended to B.

[0087] In an optional embodiment, if Figure 7 As shown, step S500 may include: Step S700, determining a target text material according to the current playing content of the target video and the target object behavior data; Step S702, determining a target bullet screen display template from a plurality of preset bullet screen display templates according to the material type of the target text material; and Step S704: insert the target text material into the target barrage display template to generate the recommended barrage content.

[0088] For example, the current playing content of the target video can be analyzed by video content analysis technology (such as image recognition, voice recognition, etc.), so as to extract various key information such as keywords, themes, characters, emotions, etc.

[0089] The target text material can be a keyword or a phrase, etc. According to the material type of the target text material (such as emotional type, length, etc.), the target barrage display template that matches the target text material is screened out from the preset barrage display template library through a matching algorithm, and then the target text material is inserted into the target barrage display template to generate recommended barrage content. One material type can correspond to multiple barrage display templates, so that multiple recommended barrage contents can be generated. For example, positive feedback: "I like this content very much", "Great! This live broadcast is really interesting!". Negative feedback: "I don't like this content very much", "It feels nothing new, I hope it will be better next time." Inquiry: "Where can I buy this?", "Can you talk more about this topic?".

[0090] In this embodiment, the target text material is determined by combining the current playback content of the target video with the user behavior data. Then the target text material is inserted into the corresponding bullet screen display template to generate personalized recommended bullet screen content, so that the target bullet screen can be generated based on the recommended bullet screen content and forwarded to each client for display. It can be seen that this embodiment can not only generate bullet screen recommendation content of the user's preferred type, but also improve the user experience. And there is no need to manually enter the bullet screen content, thereby improving the efficiency and enthusiasm of users to send bullet screens.

[0091] In an optional embodiment, the target text material is selected from a bullet screen database; The bullet screen database is constructed by the following operations: Get multiple historical bullet comment data; Classify and process the plurality of historical bullet comment data according to text type and / or sentiment tendency; The barrage database is constructed based on the classified multiple historical barrage data.

[0092] Exemplarily, historical barrage data refers to all barrage information sent by users during the past playback of the target video (for example, during live broadcast). Historical barrage data includes barrage content such as "This level is so difficult" and "So funny!" sent by users, sending time, user ID (i.e. sender ID) and context information (such as live broadcast theme, user interaction information, etc.).

[0093] In some embodiments, the collected historical barrage data can be preprocessed. For example, irrelevant or repeated historical barrage data can be removed, missing values ​​can be processed, etc. Specifically, the processed historical barrage data can be recorded in a hash table, and when the same historical barrage data is encountered again, the same historical barrage data can be removed, thereby improving the efficiency of processing historical barrage data. A group of keywords (such as advertisements, meaningless characters, etc.) can be set to check the historical barrage data, filter out the historical barrage data containing these keywords, and thus remove irrelevant historical barrage data.

[0094] The collected historical barrage data can be formed into logs and stored in a dedicated relational database (such as MySQL, etc.) to improve the efficiency of data query and analysis.

[0095] The barrage content in the collected historical barrage data can be segmented and POS tagged for subsequent analysis. For example, the sample barrage content is "This level is too difficult, does anyone have a good strategy?". The barrage content is segmented, and the segmentation results are "this", "off", "too", "difficult", ",", "everyone", "have", "no", "good", "of", "strategy", "?". Then, the part of speech is marked for each word, and the part of speech marking is "this" (demonstrative pronoun), "off" (noun), "too" (adverb), "difficult" (adjective), "of" (particle), "," (punctuation mark), "everyone" (noun), "have" (verb), "no" (verb), "good" (adjective), "of" (particle), "strategy" (noun), "?" (punctuation mark). Part of speech tagging can help identify nouns and verbs so that keywords can be extracted more accurately.

[0096] Based on the word segmentation and part-of-speech tagging of historical bullet comments, the TF-IDF algorithm can be used to extract keywords from historical bullet comments. Phrases can be extracted based on the N-gram model, for example, "too difficult" can be extracted from "this level is too difficult". The sentiment dictionary can be used to identify the sentiment in the bullet comments and determine its sentiment tendency (positive, negative, neutral). For example, there are the following bullet comments: "This anchor is really good!", "I don't think it's interesting.", "Today's content is okay". In the process of sentiment recognition, the first bullet comment is marked as "positive" sentiment. The second bullet comment is marked as "negative" sentiment. The third bullet comment is marked as "neutral" sentiment.

[0097] These historical comments can be classified into different types (such as greetings, comments, humor, reminders, notifications, positive feedback, negative feedback, etc.) according to different text types and / or emotional tendencies through machine learning models (such as support vector machines, random forests) or deep learning models (such as convolutional neural networks, recurrent neural networks).

[0098] In some embodiments, the historical playback content can be converted into text, and the text can be associated with the barrage data sent by the user at this time (i.e., the corresponding historical barrage data) as additional information. Then, it is recorded in the barrage database. For example, when the playback content of the historical video is a failure scene in a game competition, the barrage content sent by the user may focus on the comments on this event (i.e., the playback content). The additional information can be used to identify the user's emotional response and focus on specific events, which helps to summarize what types of barrage content users tend to send when various events such as "failure scenes in game competitions" occur.

[0099] In this embodiment, a barrage database can be constructed by collecting and classifying historical barrage data, so as to facilitate the subsequent selection of target text materials of the required type from the barrage database to generate barrage recommendation content, thereby improving the efficiency of generating recommended barrage content.

[0100] In an optional embodiment, if Figure 8 As shown, step S700 may include: Step S800, determining the preferred text type of the target object according to the object behavior data; Step S802, according to the current playing content of the target video and the preferred text type, obtain the corresponding type of target text material from the bullet screen database.

[0101] Exemplarily, the preferred text type can be an emotional tendency type. For example, positive emotions (such as joy, excitement, touching, etc.), negative emotions (such as sadness, anger, disappointment, etc.) neutral emotions (such as statements, questions, discussions, etc.). The preferred text type can also be a content theme type. For example, entertainment and leisure (such as funny, humorous, complaining, etc.), professional knowledge (such as popular science, analysis, evaluation, etc.). The preferred text type can also be an interactive demand type. For example, seeking resonance (such as resonant sentences, common topics, etc.), asking questions and answering (such as asking questions, answering replies, etc.), social sharing (such as sharing experiences, recommending Amway, etc. The preferred text type can also be various other types.

[0102] The target text material may be one or more than one. For example, the target text material may be "very difficult", "good", "not so good", etc.

[0103] In this embodiment, target text materials of corresponding types are obtained from the bullet screen database according to the user's preferred text type (eg, positive feedback, etc.), and these target text materials are subsequently used to generate personalized bullet screen recommendation content.

[0104] In an optional embodiment, the material type includes an emotion type and / or a content type, and the multiple bullet screen display templates correspond to multiple emotion types and / or multiple content types; step S702 may include: Determine the target bullet screen display template according to the emotion type and / or content type of the target text material; wherein: The emotion type and / or content type of the target text material is adapted to the emotion type and / or content type of the target barrage display template.

[0105] For example, when the target text material has a positive emotion type, a bullet screen display template of a corresponding emotion type is determined, thereby generating bullet screen recommendation content of a positive emotion type, such as "The host is great!".

[0106] In an optional embodiment, if Fig. 9 As shown, the target bullet screen display template includes multiple placeholders; the target video is a live video in the target live broadcast room; Step S704 may include: Step S900, obtaining parameters of the target live broadcast room; Step S902, determining the modifying text material according to the parameters; Step S904: in the process of inserting the target text material into the target bullet screen display template, insert the modifying material into the placeholder.

[0107] Exemplarily, the parameters of the target live broadcast room may be the theme of the live broadcast room, the host's style, user interaction (such as likes, comments, gift giving, etc.), the atmosphere of the live broadcast room (such as festival celebrations, special events, etc.), etc.

[0108] The decorative text material can be the host nickname, the audience nickname, etc. The decorative material can also be professional vocabulary, buzzwords, and Internet memes related to the theme and content of the live broadcast room. For example, in a game live broadcast, decorative text materials related to game characters, skills, equipment, etc. can be generated. The decorative material can also be various other types of text materials.

[0109] When the client requests recommended barrage content, the host nickname, live room theme and other content of the target live room can be sent to the server.

[0110] When the server calls a bullet screen display template with placeholders, the host's nickname, live broadcast room theme, etc. can dynamically replace the placeholders in the bullet screen display template to generate complete recommended bullet screen content. For example, "I like this content very much, thank you {host's nickname}!", "I don't like this content very much, {problem description}.", "Where can I buy {product name}?", etc.

[0111] In this embodiment, the modifying text materials are determined by obtaining the parameters of the target live broadcast room, and these modifying text materials are inserted into the barrage display template with placeholders together with the target text materials to generate complete recommended barrage content, thereby enriching the recommended barrage content.

[0112] Step S502 , the target recommended barrage content is sent to the client, so that the client displays the target recommended barrage content in the barrage recommendation area, and the target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

[0113] Exemplarily, the bullet comment recommendation area may be displayed at an edge of the screen (left edge, right edge, etc.), or other areas.

[0114] The bullet chat recommendation area may be a pop-up window (floating window) or other inframe page, etc., and the bullet chat recommendation area may be presented in a list or other forms.

[0115] In an optional embodiment, if Fig.10 As shown, the bullet screen sent to the client includes a preset bullet screen; the bullet screen push method may also include: Step S1000, obtaining feedback data from the client; Step S1002: adjusting the push priority of the preset bullet screen according to the feedback data.

[0116] Exemplarily, the content of the preset barrage can be various types of barrage content, such as emotional expression barrage (such as "I like the host's smile", "Come on, the host is the best!", etc.), interactive guidance barrage (such as "Come and vote!", "Who wants to see my talent show?", etc.), holiday blessing barrage (such as "Happy New Year!", "Happy birthday, host!", etc.).

[0117] The push priority of the preset bullet comments can be adjusted based on the feedback data. For example, if the user's feedback on the preset bullet comment "This anchor is awesome!" is relatively positive, but the feedback on the preset bullet comment "Everyone, vote!" is relatively poor, the recommendation frequency of "This anchor is awesome!" can be increased based on the rule engine, while the recommendation frequency of "Everyone, vote!" can be reduced.

[0118] In some embodiments, the model for pushing recommended bullet-chat content can be regularly trained and updated through machine learning platforms such as TensorFlow. In some embodiments, the model for pushing recommended bullet-chat content can be incrementally learned through feedback data, and model parameters can be adjusted to make the pushed recommended bullet-chat content more closely aligned with the audience's interest changes.

[0119] In order to make this application easier to understand, the following Fig.11An exemplary application is provided.

[0120] In step S11, the client sends the user behavior data (ie, the target object behavior data) and the current live content (ie, the current playing content of the target video) to the server.

[0121] Step S12, the server obtains target text materials that match the current live content and user preferences from a pre-created bullet screen database based on the current live content and user behavior data.

[0122] Step S13, the server determines a target barrage display template of a corresponding type from a plurality of preset barrage display templates according to the material type of the target text material.

[0123] In step S14, the server inserts the target text material into the target barrage display template to generate recommended barrage content (for example, "The host is great").

[0124] Step S15, the server sends the recommended barrage content to the client.

[0125] Step S16, when the user selects the recommended barrage content, generate the target barrage.

[0126] Step S17, the client sends the target barrage to the server.

[0127] Step S18, the server forwards the target bullet screen to each client for display.

[0128] Embodiment 3 Fig.13 The block diagram of the video playback device according to the third embodiment of the present application is schematically shown. The device is used for a client. The device can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Fig.13 As shown, the device 1300 may include: a display module 1310, a generation module 1320, and a sending module 1330, wherein: The display module 1310 is used to display a bullet screen recommendation area during the playback of a target video, wherein the bullet screen recommendation area includes target recommended bullet screen content; A generating module 1320, configured to generate the target barrage in response to the target recommended barrage content being selected; The sending module 1330 is used to send the target barrage to the server so that the server forwards the target barrage to each of the clients for display.

[0129] In an optional embodiment, displaying a bullet screen recommendation area includes: Display recommended controls; and In response to triggering the recommendation control, the bullet screen recommendation area is displayed in a pop-up window.

[0130] In an optional embodiment, the video playback device further includes: In response to a closing operation on the recommendation control, the recommendation control is closed and hidden.

[0131] In an optional embodiment, the target video is played in a target page, and the target page is further configured with a setting control; the video playback device further includes: When the recommendation control is in a closed or hidden state, the recommendation control pops up in response to the triggering of the setting control.

[0132] In an optional embodiment, the bullet screen recommendation area is configured with a plurality of sending controls; in response to the target recommended bullet screen content being selected, generating the target bullet screen includes: Displaying a plurality of recommended bullet-screen content in the bullet-screen recommendation area, with one sending control corresponding to one recommended bullet-screen content; In response to triggering a target sending control corresponding to the target recommended barrage content, the target barrage is generated.

[0133] In an optional embodiment, the video playback device further includes: In response to any one of the multiple sending controls being triggered, hiding the bullet screen recommendation area.

[0134] Embodiment 4 Fig.14 The block diagram of the bullet screen push device according to the fourth embodiment of the present application is schematically shown. The device is used in a server. The device can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Fig.14 As shown, the device 1400 may include: an acquisition module 1410 and a sending module 1420, wherein: The acquisition module 1410 is used to acquire target recommended bullet comment content according to the current playback content of the target video and the target object behavior data; and The sending module 1420 is used to send the target recommended barrage content to the client, so that the client displays the target recommended barrage content in the barrage recommendation area. The target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

[0135] In an optional embodiment, obtaining target recommended bullet screen content according to the current playback content of the target video and the target object behavior data includes: Determine the target text material based on the current playback content of the target video and the target object behavior data; Determining a target bullet screen display template from a plurality of preset bullet screen display templates according to the material type of the target text material; and The target text material is inserted into the target barrage display template to generate the recommended barrage content.

[0136] In an optional embodiment, the target text material is selected from a bullet screen database; The bullet screen database is constructed by the following operations: Get multiple historical bullet comment data; Classify and process the plurality of historical bullet comment data according to text type and / or sentiment tendency; The barrage database is constructed based on the classified multiple historical barrage data.

[0137] In an optional embodiment, the target text material is determined according to the current playing content of the target video and the target object behavior data, including: determining a preferred text type of a target object according to the object behavior data; According to the current playing content of the target video and the preferred text type, the target text material of the corresponding type is obtained from the bullet screen database.

[0138] In an optional embodiment, the material type includes an emotion type and / or a content type, and the multiple barrage display templates correspond to multiple emotion types and / or multiple content types; and determining the target barrage display template from the preset multiple barrage display templates according to the material type of the target text material includes: Determine the target bullet screen display template according to the emotion type and / or content type of the target text material; wherein: The emotion type and / or content type of the target text material is adapted to the emotion type and / or content type of the target barrage display template.

[0139] In an optional embodiment, it is characterized in that the target barrage display template includes a plurality of placeholders; the target video is a live video in a target live broadcast room; inserting the target text material into the target barrage display template to generate the recommended barrage content includes: Obtaining parameters of the target live broadcast room; Determining the modifying text material according to the parameters; In the process of inserting the target text material into the target bullet screen display template, the modifying material is inserted into the placeholder.

[0140] In an optional embodiment, the bullet screen sent to the client includes a preset bullet screen; and the bullet screen push device further includes: Get feedback data from the client; The push priority of the preset barrage is adjusted according to the feedback data.

[0141] In an optional embodiment, obtaining target recommended bullet screen content according to the current playback content of the target video and the target object behavior data includes: Determine a target clustering range of the target object according to the target object behavior data, where different clustering ranges correspond to different sets of recommended bullet comment content; The target recommended barrage content is selected from the recommended barrage content set corresponding to the target clustering range.

[0142] Embodiment 5 Fig.15 The hardware architecture diagram of a computer device 10000 suitable for implementing the bullet screen push method and the video playback method according to the fifth embodiment of the present application is schematically shown. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers), etc. Fig.15 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them: The memory 10010 includes at least one type of computer-readable storage medium, and 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 disk, etc. In some embodiments, the memory 10010 can be an internal storage module of the computer device 10000, such as a hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 can also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10010 can also include both the internal storage module of the computer device 10000 and its external storage device. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed on the computer device 10000, such as the program code of the bullet screen push method and the video playback method, etc. In addition, the memory 10010 can also be used to temporarily store various data that have been output or will be output.

[0143] In some embodiments, the processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0144] The network interface 10030 may include a wireless network interface or a wired network interface, and the network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and to establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0145] It should be pointed out that Fig.15 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementing all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0146] In this embodiment, the barrage push method and video playback method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0147] Embodiment 6 An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the barrage push method and the video playback method in the embodiment are implemented.

[0148] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Of course, the computer-readable storage medium may also include both an internal storage unit of a computer device and an external storage device thereof. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on a computer device, such as the program code of the bullet screen push method and the video playback method in the embodiment. In addition, the computer-readable storage medium may also be used to temporarily store various types of data that have been output or are to be output.

[0149] Embodiment 7 An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0150] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by general-purpose computer devices, they can be concentrated on a single computer device, or distributed on a network composed of multiple computer devices, optionally, they can be implemented by executable program codes of computer devices, so that they can be stored in a storage device and executed by the computer device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0151] It should be noted that the above are only preferred embodiments of the present application, and the patent protection scope of the present application is not limited thereto. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A bullet screen push method, characterized in that: For a server, the method comprises: Obtain target recommended bullet screen content based on the current playback content of the target video and the target object behavior data; and The target recommended barrage content is sent to the client so that the client displays the target recommended barrage content in a barrage recommendation area, and the target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

2. The method according to claim 1, characterized in that According to the current playback content of the target video and the target object behavior data, the target recommended bullet content is obtained, including: Determine the target text material based on the current playback content of the target video and the target object behavior data; Determining a target bullet screen display template from a plurality of preset bullet screen display templates according to the material type of the target text material; and The target text material is inserted into the target barrage display template to generate the recommended barrage content.

3. The method according to claim 2, characterized in that The target text material is selected from a bullet screen database; The bullet screen database is constructed by the following operations: Get multiple historical bullet comment data; Classify and process the plurality of historical bullet comment data according to text type and / or sentiment tendency; The barrage database is constructed based on the classified multiple historical barrage data.

4. The method according to claim 3, characterized in that Determine the target text material based on the current playback content of the target video and the target object behavior data, including: determining a preferred text type of a target object according to the object behavior data; According to the current playing content of the target video and the preferred text type, the target text material of the corresponding type is obtained from the bullet screen database.

5. The method according to claim 3, characterized in that: The material type includes an emotion type and / or a content type, and the multiple bullet screen display templates correspond to multiple emotion types and / or multiple content types; The step of determining a target bullet screen display template from a plurality of preset bullet screen display templates according to the material type of the target text material includes: Determine the target bullet screen display template according to the emotion type and / or content type of the target text material; wherein: The emotion type and / or content type of the target text material is adapted to the emotion type and / or content type of the target barrage display template.

6. The method according to claim 2, characterized in that The target bullet screen display template includes a plurality of placeholders; the target video is a live video in the target live broadcast room; Inserting the target text material into the target bullet screen display template to generate the recommended bullet screen content includes: Obtaining parameters of the target live broadcast room; Determining the modifying text material according to the parameters; In the process of inserting the target text material into the target bullet screen display template, the modifying material is inserted into the placeholder.

7. The method according to claim 1, characterized in that According to the current playback content of the target video and the target object behavior data, the target recommended bullet content is obtained, including: Determine a target clustering range of the target object according to the target object behavior data, where different clustering ranges correspond to different sets of recommended bullet comment content; The target recommended barrage content is selected from the recommended barrage content set corresponding to the target clustering range.

8. The method according to any one of claims 1 to 7, characterized in that: The bullet screen sent to the client includes a preset bullet screen; the method further includes: Get feedback data from the client; The push priority of the preset barrage is adjusted according to the feedback data.

9. A video playback method, characterized in that: For a client, the method comprises: During the playback of the target video, a bullet screen recommendation area is displayed, wherein the bullet screen recommendation area includes target recommended bullet screen content; In response to the target recommended barrage content being selected, generating the target barrage; The target barrage is sent to the server so that the server forwards the target barrage to each of the clients for display.

10. A video playback device, characterized in that: For a client, the device comprises: A display module, used to display a bullet screen recommendation area during the playback of a target video, wherein the bullet screen recommendation area includes target recommended bullet screen content; A generating module, configured to generate the target barrage in response to the target recommended barrage content being selected; The sending module is used to send the target barrage to the server so that the server forwards the target barrage to each of the clients for display.

11. A bullet screen pushing device, characterized in that: For a server, the device comprises: An acquisition module, used to acquire target recommended bullet screen content according to the current playback content of the target video and the target object behavior data; and The sending module is used to send the target recommended barrage content to the client so that the client displays the target recommended barrage content in the barrage recommendation area. The target recommended barrage content in the barrage recommendation area generates a target barrage after being selected.

12. A computer device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 9 are implemented.

Images