Bullet screen processing method and device, equipment, storage medium and computer program product

Abstract

The invention relates to a bullet screen processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: displaying a video playing picture of a target video; detecting a bullet screen triggering operation used for displaying redundant bullet screens in the video playing picture; after the bullet screen triggering operation is detected, redundant bullet screens are displayed on the video playing picture in an overlapping mode, the redundant bullet screens are used for shielding the video playing picture, and the bullet screen content of the redundant bullet screens is matched with the picture content of the video playing picture. By adopting the method, the requirement that the user can shield the video picture at any time can be met, and meanwhile, the user can not influence the plot understanding of the video, so that the video watching experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a bullet comment processing method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of computer technology and video technology, various video playback platforms have appeared on the market to meet people's daily video viewing needs. People can watch videos through video playback platforms, and can also express interactive information on the videos being played. These interactive information can be displayed on the video being played in the form of barrage.

[0003] In some cases, users may need to actively block or obstruct the video screen. For example, some videos may contain some thriller clips, and users may experience discomfort when watching these clips. In related technologies, users may actively block or obstruct the video screen by opening the barrage, and may skip some video clips by fast-forwarding.

[0004] However, some videos have a small number of viewers and may not have video comments, which cannot meet the user's need to actively block videos at any time. Directly skipping some video clips may affect the user's understanding of the plot, resulting in a poor user experience. The above method cannot meet the user's need to block the video screen at any time without affecting the user's video viewing experience, resulting in a poor user experience. Summary of the invention

[0005] Based on this, it is necessary to provide a barrage processing method, device, computer equipment, computer-readable storage medium and computer program product to address the above-mentioned technical problems. The method can meet the user's needs to block the video screen at any time without affecting the user's understanding of the video plot, thereby improving the user's video viewing experience.

[0006] In a first aspect, the present application provides a method for processing bullet comments. The method comprises:

[0007] Display the video playback screen of the target video;

[0008] Detecting a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen;

[0009] After the bullet screen triggering operation is detected, a redundant bullet screen is superimposed and displayed on the video playback screen, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0010] In a second aspect, the present application also provides a bullet screen processing device. The device comprises:

[0011] A video screen display module, used to display the video playback screen of the target video;

[0012] A detection module, used to detect a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen;

[0013] The barrage display module is used to overlay and display redundant barrage on the video playback screen after detecting the barrage trigger operation, wherein the redundant barrage is used to cover the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen.

[0014] In one embodiment, the apparatus further comprises:

[0015] A request module, configured to obtain the current playback progress of the target video after detecting the bullet screen triggering operation, generate a redundant bullet screen generation request according to the current playback progress, and obtain at least one redundant bullet screen according to the redundant bullet screen request;

[0016] The bullet screen display module is further used to overlay and display the at least one redundant bullet screen on the video playback screen.

[0017] In one embodiment, the request module is further used to send the redundant barrage generation request to the server, so that the server obtains the video frame after the current playback progress from the video frame of the target video, obtains description information about the video playback screen according to the obtained video frame, and generates at least one redundant barrage according to the description information;

[0018] The device also includes:

[0019] A receiving module is used to receive the at least one redundant barrage fed back by the server.

[0020] In one embodiment, the detection module is further used to detect a bullet screen canceling operation for canceling display of redundant bullet screens in the video playback screen after detecting the bullet screen triggering operation;

[0021] The request module is also used to execute the following steps every preset time if the barrage cancellation operation is not detected: obtaining the current playback progress of the target video, generating a redundant barrage generation request according to the current playback progress, and obtaining at least one redundant barrage according to the redundant barrage request; and superimposing and displaying the at least one redundant barrage on the video playback screen.

[0022] In one embodiment, the barrage display module is further used to cancel the redundant barrage displayed on the video playback screen after detecting the barrage cancellation operation.

[0023] In one embodiment, the apparatus further comprises:

[0024] A placeholder bullet screen download module is used to obtain the video information and prefabricated bullet screen package of the target video when starting video playback;

[0025] The barrage display module is also used to overlay and display a placeholder barrage on the video playback screen based on the video information and the prefabricated barrage package after sending the redundant barrage generation request to the server and before receiving the at least one redundant barrage fed back by the server, wherein the placeholder barrage is used to block the video playback screen; and to cancel the overlay display of the placeholder barrage on the video playback screen after receiving the at least one redundant barrage fed back by the server.

[0026] In one embodiment, the barrage display module is also used to display the historical barrage in a first style on the video playback screen when there is a historical barrage corresponding to the video playback screen, and the historical barrage does not block the video playback screen; the barrage display module is also used to display the redundant barrage in a second style on the video playback screen; wherein the second style is different from the first style.

[0027] In one embodiment, the detection module is also used to detect an erasing operation on the redundant barrage; when the erasing operation is detected, an erasing area corresponding to the erasing operation is determined in the video playback screen; the barrage display module is also used to hide the redundant barrage located in the erasing area.

[0028] In one embodiment, the bullet screen display module is further used to determine the arrangement position on the video playback screen; and display each of the redundant bullet screens at the corresponding arrangement position in a manner changing from a small-size style to a large-size style.

[0029] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0030] Display the video playback screen of the target video;

[0031] Detecting a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen;

[0032] After the bullet screen triggering operation is detected, a redundant bullet screen is superimposed and displayed on the video playback screen, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0034] Display the video playback screen of the target video;

[0035] Detecting a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen;

[0036] After the bullet screen triggering operation is detected, a redundant bullet screen is superimposed and displayed on the video playback screen, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0037] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0038] Display the video playback screen of the target video;

[0039] Detecting a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen;

[0040] After the bullet screen triggering operation is detected, a redundant bullet screen is superimposed and displayed on the video playback screen, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0041] The above-mentioned barrage processing method, device, computer equipment, storage medium and computer program product display the video playback screen of the target video, detect the barrage trigger operation for displaying redundant barrage in the video playback screen, and after detecting the barrage trigger operation, superimpose and display the redundant barrage on the video playback screen. The redundant barrage is used to block the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen. This method can allow the user to actively trigger the barrage trigger operation of displaying redundant barrage in the video playback screen at any time during the process of watching the target video, thereby displaying redundant barrage in the video playback screen during the process of playing the target video to block the video playback screen at any time. In addition, since the barrage content of the redundant barrage matches the screen content of the video playback screen, even if the redundant barrage blocks the video playback screen, the user's understanding of the plot of the video will not be affected, thereby improving the user's video viewing experience.

[0042] In a sixth aspect, the present application provides a method for processing bullet comments. The method comprises:

[0043] A redundant bullet screen generation request sent by a receiving terminal when playing a target video;

[0044] Obtaining the current playback progress of the target video according to the redundant bullet screen generation request;

[0045] Acquire the video frames after the current playback progress from the video frames of the target video;

[0046] Determine description information about a video playback screen of the target video according to the video frame;

[0047] At least one redundant bullet screen generated according to the description information is fed back to the terminal, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0048] In a seventh aspect, the present application also provides a bullet comment processing device. The device comprises:

[0049] A receiving module, used for receiving a redundant barrage generation request sent by a terminal when playing a target video;

[0050] A progress acquisition module, used to acquire the current playback progress of the target video according to the redundant barrage generation request;

[0051] A video frame acquisition module, used to acquire video frames after the current playback progress from the video frames of the target video;

[0052] A description information determination module, used to determine description information about the video playback screen of the target video according to the video frame;

[0053] A feedback module is used to feed back to the terminal at least one redundant bullet screen generated according to the description information, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0054] In one embodiment, the redundant barrage generation request is generated by the terminal according to the video identifier and current playback progress of the target video after the terminal detects a barrage trigger operation for displaying redundant barrage in the video playback screen.

[0055] In one embodiment, the video frame acquisition module is further used to acquire a video frame sequence corresponding to the target video; and acquire at least one video frame located after the current playback progress from the video frame sequence.

[0056] In one embodiment, the description information determination module is also used to perform image detection on the acquired video frame to obtain object information in the video playback screen; perform semantic understanding on the acquired video frame to obtain semantic information of the video playback screen; perform character recognition on the acquired video frame to obtain text content of the video playback screen.

[0057] In one embodiment, the apparatus further comprises:

[0058] A model calling module is used to obtain the video type and prompt text template of the target video; fill the prompt text template according to the video type, the description information and the specified number of barrages to obtain the prompt text; and generate redundant barrages of the specified number of barrages according to the prompt text through a large language model.

[0059] In an eighth aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0060] A redundant bullet screen generation request sent by a receiving terminal when playing a target video;

[0061] Obtaining the current playback progress of the target video according to the redundant bullet screen generation request;

[0062] Acquire the video frames after the current playback progress from the video frames of the target video;

[0063] Determine description information about a video playback screen of the target video according to the video frame;

[0064] At least one redundant bullet screen generated according to the description information is fed back to the terminal, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0065] In a ninth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0066] A redundant bullet screen generation request sent by a receiving terminal when playing a target video;

[0067] Obtaining the current playback progress of the target video according to the redundant bullet screen generation request;

[0068] Acquire the video frames after the current playback progress from the video frames of the target video;

[0069] Determine description information about a video playback screen of the target video according to the video frame;

[0070] At least one redundant bullet screen generated according to the description information is fed back to the terminal, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0071] In a tenth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0072] A redundant bullet screen generation request sent by a receiving terminal when playing a target video;

[0073] Obtaining the current playback progress of the target video according to the redundant bullet screen generation request;

[0074] Acquire the video frames after the current playback progress from the video frames of the target video;

[0075] Determine description information about a video playback screen of the target video according to the video frame;

[0076] At least one redundant bullet screen generated according to the description information is fed back to the terminal, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0077] The above-mentioned barrage processing method, device, computer equipment, storage medium and computer program product, the receiving terminal generates and sends a redundant barrage generation request according to the barrage triggering operation of the user at any time while watching the target video. After receiving the redundant barrage generation request, the current playback progress of the target video is obtained according to the redundant barrage generation request, the video screen related to the current playback progress of the target video is image understood, and the description information about the video playback screen of the target video is obtained, and then at least one redundant barrage corresponding to the current playback progress is automatically generated according to the description information to ensure the relevance of the redundant barrage to the currently played video content, and the redundant barrage is fed back to the terminal. The terminal can immediately display the generated redundant barrages related to the video content on the video playback screen, and can help the user actively block the video playback screen at any time. In addition, since the barrage content of the redundant barrage matches the screen content of the video playback screen, even if the redundant barrage blocks the video playback screen, the user's understanding of the plot of the video will not be affected, thereby improving the user's video viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1A diagram showing an application environment of a bullet screen processing method in an embodiment;

[0079] Figure 2 Schematic diagram of a process of processing a bullet screen in one embodiment;

[0080] Figure 3 A schematic diagram of a framework for generating redundant bullet comments in one embodiment;

[0081] Figure 4 A schematic diagram of an interface for overlaying and displaying redundant bullet comments on a video playback screen in an embodiment;

[0082] Figure 5 A schematic diagram of an interface for overlaying and displaying placeholder bullet comments on a video playback screen in an embodiment;

[0083] Figure 6 A schematic diagram of a process of displaying redundant bullet comments in a detailed embodiment;

[0084] Figure 7 A schematic diagram of a flow chart of a bullet screen processing method in another embodiment;

[0085] Figure 8 is a structural block diagram of a bullet screen processing device in one embodiment;

[0086] Fig. 9 is a structural block diagram of a bullet screen processing device in another embodiment;

[0087] Fig.10 is an internal structure diagram of a computer device in one embodiment;

[0088] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solution 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 used to limit the present application.

[0090] When users play videos through video clients on a daily basis, some videos may contain thriller, violence and other clips. Users may have uncomfortable reactions when watching these clips. Some users will try to block the video screen by turning on the video barrage, and some users may skip some video clips by fast forwarding. However, in the related art, the barrage function for videos is relatively simple. Users who watch videos can only turn on or off the barrage function. After turning on the barrage function, the video barrage (or historical barrage) sent by previous users for the currently playing video will appear on the video playback screen. It is understandable that some videos, especially thriller and violent videos, have fewer viewers, and there may be no users who have sent video barrages for the video clips. Even if the user turns on the barrage function, there is no video barrage displayed on the screen, which cannot meet the user's active shielding needs at any time. Directly skipping some video clips may affect the user's understanding of the plot, resulting in a poor user video viewing experience.

[0091] That is, the related technology cannot meet the user's demand for being able to block the video screen at any time without affecting the user's video viewing experience, and the user experience is poor.

[0092] The barrage processing method provided in the embodiment of the present application displays redundant barrage in the video playback screen during the playback of the target video to block the video playback screen at any time. In addition, since the barrage content of the redundant barrage matches the screen content of the video playback screen, even if the redundant barrage blocks the video playback screen, the user's understanding of the video plot will not be affected, thereby improving the user's video viewing experience.

[0093] The bullet screen processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other servers. Optionally, a video client is installed and run on the terminal 102, and the video client can support the function of video playback. The video client can be a live video client, a video playback client, or a web version of a video player. The video-related functions of the video client can provide corresponding computing services and storage services through the video server. In an embodiment of the present application, the server 104 at least supports the automatic generation of redundant barrages. Optionally, the server 104 can be an independent server, which is independent of the video server. Optionally, the server 104 can also be integrated on the video server.

[0094] In one embodiment, terminal 102 plays a target video and displays a video playback screen of the target video. During the process of playing the target video, a barrage trigger operation for displaying redundant barrages in the video playback screen is detected. After detecting the barrage trigger operation, a redundant barrage is superimposed and displayed on the video playback screen. The redundant barrage is used to cover the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen.

[0095] In one embodiment, the server 104 receives a redundant barrage generation request sent by the terminal 102 when playing a target video, obtains the current playback progress of the target video according to the redundant barrage generation request, obtains the video frame after the current playback progress from the video frame of the target video, determines the description information about the video playback screen of the target video according to the video frame, and feeds back to the terminal 102 at least one redundant barrage generated according to the description information, wherein the redundant barrage is used to cover the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen.

[0096] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0097] In one embodiment, Figure 2 As shown, a bullet screen processing method is provided, and the method is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0098] Step 202: Display the video playback screen of the target video.

[0099] The target video is the video currently being played by the terminal. The video playback screen is the video screen of the target video displayed on the screen of the terminal. It can be understood that during the process of the terminal playing the target video, the video playback screen changes with the playback progress.

[0100] Step 204, detecting a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen.

[0101] Specifically, during the process of playing the target video, the terminal can detect a bullet screen trigger operation for displaying redundant bullet screens in the video playback screen. Redundant bullet screens are bullet screens different from the historical bullet screens of the video. The redundant bullet screens in the embodiments of the present application are video bullet screens dedicated to blocking the video playback screen.

[0102] In the embodiment of the present application, the barrage trigger operation for displaying redundant barrage and the trigger operation for displaying historical barrage of the video are different trigger operations.

[0103] Exemplarily, the terminal may set a control for turning on or off the video barrage function in the video playback interface, and the video barrage function may be turned on or off by triggering the control. When the video barrage function is turned on, the terminal detects a trigger operation for displaying the historical barrage of the video. At this time, the terminal may pull the historical barrage of the currently playing video from the server, that is, the comment information sent by users in the past for the video, and display the pulled historical barrage in the video playback screen of the currently playing video to enhance the fun and interactivity of video viewing. When the video barrage function is turned off, the terminal detects a trigger operation for canceling the display of the historical barrage of the video. At this time, the terminal no longer displays the historical barrage of the currently playing video in the video playback screen, and presents the user with a complete video playback screen.

[0104] Exemplarily, the bullet screen triggering operation for displaying redundant bullet screens in the video playback screen may be a shaking operation on the terminal. Then, during the playback of the target video, the terminal may monitor the motion data of the terminal through its own sensors such as an accelerometer, an inertial sensor, a gyroscope, etc., thereby detecting whether a shaking operation is generated for the terminal. If a shaking operation is detected for the terminal, it is considered that the bullet screen triggering operation for displaying redundant bullet screens in the video playback screen is triggered. Optionally, if a shaking operation is detected for the terminal again, it is considered that the bullet screen cancelling operation for cancelling the display of redundant bullet screens in the video playback screen is triggered.

[0105] Exemplarily, the terminal may also set a control for turning on or off the redundant bullet screen function in the video playback interface. By triggering the control, the redundant bullet screen function may be turned on or off. When the redundant bullet screen function is turned on, the terminal detects a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen. Optionally, when the redundant bullet screen function is turned off, the terminal detects a bullet screen canceling operation for canceling the display of redundant bullet screens in the video playback screen.

[0106] Of course, the bullet screen trigger operation for displaying redundant bullet screens in the video playback screen can be set according to actual needs, or it can be other operations, such as clicking the screen multiple times, placing the screen face down, etc. as bullet screen trigger operations.

[0107] Step 206, after detecting the bullet screen triggering operation, a redundant bullet screen is superimposed and displayed on the video playback screen, the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0108] After detecting the bullet screen triggering operation, the terminal can obtain redundant bullet screens for covering the video playback screen, the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen, and the obtained redundant bullet screen is superimposed and displayed on the video playback screen.

[0109] The above-mentioned barrage processing method displays the video playback screen of the target video, detects the barrage trigger operation for displaying redundant barrage in the video playback screen, and after detecting the barrage trigger operation, superimposes and displays the redundant barrage on the video playback screen, and the redundant barrage is used to block the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen. This method allows the user to actively trigger the barrage trigger operation of displaying redundant barrage in the video playback screen at any time during the process of watching the target video, thereby displaying redundant barrage in the video playback screen during the process of playing the target video to block the video playback screen at any time. In addition, since the barrage content of the redundant barrage matches the screen content of the video playback screen, even if the redundant barrage blocks the video playback screen, the user's understanding of the plot of the video will not be affected, thereby improving the user's video viewing experience.

[0110] In one embodiment, the terminal can obtain video frames related to the playback progress from the video frames of the target video based on the playback progress of the target video when the barrage trigger operation is detected, call the image processing model to perform image understanding on the obtained video frames, and generate redundant barrages that match the picture content of the video playback screen.

[0111] In one embodiment, in order to reduce the running load on the terminal, the terminal may also generate a redundant barrage generation request based on the playback progress of the target video when the barrage trigger operation is detected, and obtain redundant barrages that match the screen content of the video playback screen from the server based on the redundant barrage generation request.

[0112] This embodiment is described by taking the example of a terminal side initiating a request, a server side generating redundant bullet screens, and a terminal side displaying redundant bullet screens.

[0113] That is, after detecting the barrage trigger operation, redundant barrage is superimposed and displayed on the video playback screen, including: after detecting the barrage trigger operation, obtaining the current playback progress of the target video; generating a redundant barrage generation request according to the current playback progress; obtaining at least one redundant barrage according to the redundant barrage request; and superimposing and displaying the at least one redundant barrage on the video playback screen.

[0114] Optionally, obtaining at least one redundant barrage according to the redundant barrage request includes: sending a redundant barrage generation request to the server, so that the server obtains the video frame after the current playback progress from the video frame of the target video, obtaining description information about the video playback screen according to the obtained video frame, and generating at least one redundant barrage according to the description information; receiving at least one redundant barrage fed back by the server.

[0115] Specifically, after detecting the bullet screen triggering operation, the terminal generates a redundant bullet screen generation request according to the playback progress of the target video and the video ID of the target video when the bullet screen triggering operation is detected, and sends the redundant bullet screen generation request to the server. The request parameters of the redundant bullet screen generation request include the current playback progress, and may also include video information such as the video ID or the episode ID. After receiving the redundant bullet screen generation request, the server obtains the current playback progress from the redundant bullet screen generation request, obtains the video frame after the current playback progress from the video frame of the target video, calls the image processing model to obtain the description information about the video playback screen according to the obtained video frame, calls the large language model to generate at least one redundant bullet screen according to the description information, and feeds back the generated redundant bullet screen to the terminal. After receiving the redundant bullet screen, the terminal immediately overlays and displays the received redundant bullet screen on the video playback screen.

[0116] In one embodiment, the method also includes: after detecting the barrage triggering operation, detecting the barrage canceling operation for canceling the display of redundant barrage in the video playback screen; if the barrage canceling operation is not detected, performing the following steps every preset time interval: obtaining the current playback progress of the target video, generating a redundant barrage generation request according to the current playback progress, obtaining at least one redundant barrage according to the redundant barrage request, and displaying the at least one redundant barrage on the video playback screen.

[0117] Optionally, the terminal can send a redundant barrage generation request to the server, so that the server obtains the video frame after the current playback progress from the video frame of the target video, obtains description information about the video playback screen based on the obtained video frame, generates at least one redundant barrage based on the description information, and receives at least one redundant barrage feedback from the server.

[0118] That is to say, after detecting the bullet screen triggering operation, if the terminal does not detect the bullet screen canceling operation, it can continuously send new redundant bullet screen generation requests to the server as the current playback progress changes. For example, the terminal can send new redundant bullet screen generation requests at fixed intervals (such as 5 seconds) according to the updated current playback progress, so as to ensure the diversity of the redundant bullet screen displayed on the video playback screen and its matching with the video playback screen.

[0119] In one embodiment, the method further includes: if a bullet screen cancelling operation is detected, then after the bullet screen cancelling operation is detected, cancelling the superimposed display of redundant bullet screens on the video playback screen.

[0120] The following is a detailed description of the process of the server generating redundant bullet comments.

[0121] In one embodiment, the server may obtain a video frame sequence corresponding to the target video, and obtain at least one video frame located after the current playback progress from the video frame sequence.

[0122] Among them, the video frame after the current playback progress is the video frame related to the current playback screen. The video frame after the current playback progress can be N video frames after the current playback progress, such as N key frames, and the key frame is an I frame, an intra-frame coded frame. N can be set according to actual needs, for example, it can be 5. The video frame after the current playback progress can be a key frame within M seconds after the current playback progress, and M can be set according to actual needs, for example, it can be 3.

[0123] In one embodiment, the server can perform image detection on the acquired video frames to obtain object information in the video playback screen, perform semantic understanding on the acquired video frames to obtain semantic information of the video playback screen, perform character recognition on the acquired video frames to obtain text content of the video playback screen. These object information, semantic information, and text content can all be used as description information of the video playback screen.

[0124] The description information of the video playback screen is the text content used to describe the video screen. The description information is generated based on the video playback screen. For example, the server can call the image detection model to obtain object information in the video playback screen according to the video frame, such as "a lady" and "fist". The server can call the image semantic understanding model to obtain semantic information of the video playback screen according to the video frame, such as "a lady raised her fist". The server can call the character recognition model to obtain the text content of the video playback screen according to the video frame, such as subtitles. If the subtitles are not recognized, the server can also obtain audio synchronized with the video playback screen, perform speech recognition on the audio, and use the recognized speech content as one of the description information of the video playback screen. Among them, the above-mentioned image detection model and image semantic understanding model can be replaced by a large language model.

[0125] In one embodiment, the server can obtain the video type and prompt text template of the target video; fill in the prompt text template according to the video type, description information and the specified number of barrages to obtain the prompt text; and generate redundant barrages with a specified number of barrages according to the prompt text through a large language model.

[0126] The prompt text template is a template data preset for generating redundant bullet comments, which can be customized according to actual needs, and the present application embodiment does not limit this. For example, the prompt text template is:

[0127] Generate Z bullet comments with a length not exceeding Y words for a video of type X. The description information of the video is: CCC, DDD, EEE, ...

[0128] The description information may include the above-mentioned object information, semantic information, text content, etc.

[0129] Optionally, the prompt text may also include basic information of the video, such as the cast, video tags, video style, etc. An example of a prompt text template is:

[0130] Generate Z bullet comments with a length not exceeding Y words for a video of type X. The description information of the video is: CCC, DDD, EEE, ...

[0131] Generate Z comments with a length not exceeding Y words for a video of type X. The basic information of the video is: A, B, C, ...

[0132] The server fills in the prompt text template according to the video type, description information and the specified number of bullet comments to obtain the prompt text. The large language model is a deep learning model trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. Redundant bullet comments can be generated through the artificial intelligence content generation (AIGC) capability of the large language model. Among them, content generation capabilities such as AI text continuation, text to image, AI host, etc. are all applications of artificial intelligence content generation. The large language model can handle a variety of natural language tasks, such as text classification, question and answer, dialogue, etc. The server inputs the generated prompt text into the large language model, and the large language model will output the corresponding redundant bullet comments according to the prompt text.

[0133] In this embodiment, by calling the large language model to generate redundant barrage according to the prompt text, the reasoning and understanding capabilities of the large language model are utilized to ensure that the generated redundant barrage is dynamically changeable as the understanding capability of the large language model increases, and to ensure that the generated redundant barrage matches the video playback screen.

[0134] In one embodiment, after obtaining the description information about the video playback screen, the server can also directly feed back the description information as redundant bullet comments to the terminal. The terminal can directly overlay and display the description information on the video playback screen.

[0135] like Figure 3 FIG. 1 is a schematic diagram of a framework for generating redundant bullet comments in an embodiment. Figure 3 , the client on the terminal detects the shaking gesture and initiates a request to the server. The server extracts the video frame and the synchronized audio according to the current playback progress, performs image detection, image semantic understanding, image character recognition, etc. on the video frame, and performs speech recognition on the audio to obtain the spoken content, thereby obtaining the description information. In addition, the server can also obtain the basic information of the video, such as the video type, the starring lineup, the video tag, the frequency style and other information, fill in the prompt text template according to the description information and the basic information of the video, construct the prompt text, and then input it into the large language model. The redundant bullet screen list is output through the large language model and fed back to the terminal, and the terminal displays the redundant bullet screen.

[0136] For example, the server performs image detection on the video frame and obtains the object information of "lady" and "fist"; the semantic information obtained by semantic understanding of the video frame is "a lady raised her fist", and the text content obtained by character recognition on the video frame is "movie analysis" and "exciting plot". The basic video information of the video includes "lady", "movie" and "plot". The prompt text is generated based on this information and input into the large language model to automatically generate a list of redundant bullet comments for the video at the current playback progress:

[0137] "Fist", "Inspiring", "A lady determined to achieve her dream", "Movie analysis", "Firm eyes", "High morale", etc.

[0138] After receiving the redundant bullet comments list, the terminal immediately displays these redundant bullet comments on the screen.

[0139] like Figure 4 FIG. 1 is a schematic diagram of an interface for superimposing redundant bullet comments on a video playback screen in an embodiment. Figure 4 ,according to Figure 4 From the before-and-after comparison of the two interface pictures, it can be seen that by superimposing a large number of redundant barrages, the video playback screen can be blocked. The barrage content of the redundant barrages matches the video screen, and the user's understanding of the video plot will not be affected, thereby improving the user's video viewing experience.

[0140] In one embodiment, the method also includes: when starting video playback, obtaining video information and a pre-made barrage package of the target video; after sending a redundant barrage generation request to the server, and before receiving at least one redundant barrage feedback from the server, the method also includes: based on the video information and the pre-made barrage package, superimposing and displaying a placeholder barrage on the video playback screen, wherein the placeholder barrage is used to block the video playback screen.

[0141] Optionally, after receiving at least one redundant bullet comment fed back by the server, the method further includes: canceling the display of the placeholder bullet comment superimposed on the video playback screen.

[0142] Optionally, after receiving at least one redundant bullet screen fed back by the server, the terminal may also overlay and display the placeholder bullet screen and at least one redundant bullet screen on the video playback screen. There may be a situation where the bullet screens block each other. The terminal may also set corresponding display priorities for different types of bullet screens, wherein the display priority of the redundant bullet screen may be higher than the display priority of the placeholder bullet screen, to ensure that the redundant bullet screen is seen first, and the bullet screen content of the redundant bullet screen matches the screen content of the blocked video playback screen. Being seen first can avoid affecting the user's understanding of the plot of the blocked video playback screen.

[0143] It can be understood that in an embodiment where redundant barrages are requested on the terminal side and generated on the server side, there may be no barrages displayed on the screen during the period from detecting the barrage triggering operation to receiving the redundant barrages. In this embodiment, in order to solve this problem and improve the user's video viewing experience, placeholder barrages are used to block the video playback screen.

[0144] Placeholder barrage is used to block the video playback screen, and redundant barrage is also used to block the video playback screen. In the embodiment of the present application, the difference between placeholder barrage and redundant barrage is that the placeholder barrage is preset, and the redundant barrage is generated in real time. The placeholder barrage can be a simple basic information of the video, such as the name of the leading actor, the content summary, the video tag, etc. The placeholder barrage can also be a preset barrage package, and the content of the preset barrage package can be configured by yourself. For the same video, the preset barrage packages corresponding to different video playback screens can be the same, that is, the content of the preset barrage package does not change with the change of the playback progress. For the same video, the preset barrage packages corresponding to different video playback screens may also be different. For example, the barrage content of the preset barrage package is a plot summary of the current playback progress, an evaluation of the actors in the current video playback screen, an interpretation of the current plot, etc. It should be noted that in this case, the update frequency of the barrage content of the preset barrage package is low. For example, a preset barrage package is generated every M video screens, for example, one preset barrage package corresponds to every 10 seconds of playback time. Then it can be understood that redundant barrages can be generated instantly in response to any user's request, and different redundant barrages can be generated at any time to ensure the diversity, immediacy and high matching of the redundant barrages with the current video screen, and there is no need to consider the differences in screen blocking requirements of different users. Any user can use redundant barrages to block the video screen anytime and anywhere.

[0145] In one embodiment, the terminal can download the placeholder barrage of the target video from the server when entering the video playback page of the target video, that is, when starting the video playback, the placeholder barrage is downloaded. This can ensure that when the barrage trigger operation for displaying redundant barrage in the video playback screen is detected to be triggered, the placeholder barrage can be displayed on the screen as soon as possible, and the placeholder barrage is used to block the video playback screen, thereby instantly meeting the user's shielding needs and improving the user's video viewing experience.

[0146] like Figure 5 As shown in FIG. 1 , a schematic diagram of an interface for superimposing a placeholder bullet screen on a video playback screen in one embodiment. Taking the placeholder bullet screen as the name of the current starring actor as an example, refer to Figure 5 In the above figure, if the user shakes the phone at 06:10, the bullet screen triggering operation for displaying redundant bullet screens in the video playback screen is triggered, and the terminal will display the current starring name in the video playback screen to cover the video playback screen.

[0147] In this embodiment, after the terminal initiates a redundant bullet screen request and before receiving redundant bullet screen feedback from the server, the terminal can obtain a placeholder bullet screen to promptly respond to the user's demand for blocking the current video playback screen.

[0148] In one embodiment, the method also includes: when there is a historical barrage corresponding to the video playback screen, the historical barrage is superimposed and displayed on the video playback screen in a first style, and the historical barrage does not block the video playback screen; superimposed and displayed redundant barrage on the video playback screen, including: superimposed and displayed redundant barrage on the video playback screen in a second style; wherein the second style is different from the first style.

[0149] As mentioned above, historical barrages are video barrages sent by previous users for the currently playing video that will appear on the video playback screen after the user turns on the barrage function. When the user turns on the barrage function and there are historical barrages corresponding to the video playback screen, the terminal can superimpose and display the historical barrages on the video playback screen in a first style. It can be understood that these historical barrages usually cannot affect the user's viewing of the video screen when they are displayed, so the historical barrages do not block the video playback screen. If the terminal detects that the barrage trigger operation for displaying redundant barrages in the video playback screen is triggered at this time, the terminal can superimpose and display the redundant barrages on the video playback screen in a second style different from the first style after receiving the redundant barrages fed back by the server.

[0150] Optionally, the display color of the redundant bullet comments is different from the display color of the historical bullet comments, and the redundant bullet comments and the historical bullet comments can be distinguished by elements such as color, border, background color, etc. The terminal can add a border and background color to the redundant bullet comments when displaying the redundant bullet comments.

[0151] Optionally, the display animation of the redundant bullet comments is different from the display animation of the historical bullet comments. The display animation effect of the historical bullet comments usually moves in from the left area of ​​the video playback screen, gradually moves to the right area of ​​the video playback screen, and then moves out of the screen. Exemplarily, the redundant bullet comments "emerge" from the screen to distinguish them from the display animation of the historical bullet comments.

[0152] In this embodiment,

[0153] In one embodiment, redundant bullet comments are superimposed and displayed on a video playback screen, including: determining an arrangement position on the video playback screen; after placing redundant bullet comments in a small-sized style at the arrangement position, displaying each redundant bullet comment at the corresponding arrangement position, changing from a small-sized style to a large-sized style.

[0154] Exemplarily, the terminal can first arrange the redundant bullet screen at a certain point on the screen. At this time, the size of the redundant bullet screen is 0, and the user cannot see it. Then the terminal displays the redundant bullet screen slowly and becomes the same size as the historical bullet screen, achieving the effect of emergence. Since there is no limit on the time of being on the screen, after the terminal obtains the data of the redundant bullet screen, it can determine the arrangement position on the video playback screen according to the size of the screen, so as to realize the instant screen of the redundant bullet screen. For example, the terminal divides the screen size into 10 rows horizontally and 20 columns vertically, and 200 vertical and horizontal intersections are 200 arrangement positions. The terminal can place 200 redundant bullet screens on these 200 vertical and horizontal intersections. At this time, the size of the redundant bullet screen is 0. The terminal can allow this batch of redundant bullet screens to execute the animation of modifying its own size, so as to achieve the effect of the redundant bullet screen changing from small to large. After the redundant bullet screen stays on the screen for a period of time (for example, 3 seconds), the first batch of redundant bullet screens will gradually shrink until the size is 0 and disappears on the screen.

[0155] When the terminal detects that the bullet screen cancel operation for canceling redundant bullet screens is triggered, the terminal will also obtain the second batch of redundant bullet screens. When the first batch of redundant bullet screens disappear, the size of the second batch of redundant bullet screens is 0. Similarly, an animation of modifying its own size is executed to achieve the effect of redundant bullet screens changing from small to large, so as to ensure that the video screen is continuously blocked. The arrangement position of the second batch of bullet screens can remain unchanged or change. For example, the screen size can be divided into 12 rows horizontally and 18 rows vertically, so as to re-determine several arrangement positions on the video playback screen.

[0156] In one embodiment, the method further includes: detecting an erasing operation on redundant bullet comments; when an erasing operation is detected, determining an erasing area corresponding to the erasing operation in the video playback screen; and hiding the redundant bullet comments located in the erasing area.

[0157] As mentioned above, the redundant bullet screen will be displayed in a way that blocks the current video playback screen to ensure that the user will not clearly see the current video playback screen. Considering that some users may want to erase part of the blocked redundant bullet screen, in order to achieve this effect, a bullet screen erasing function is introduced. In this embodiment, when the terminal detects an erasing operation for the redundant bullet screen, the redundant bullet screen located in the erasing area is hidden. Exemplarily, the erasing operation for the redundant bullet screen can be a sliding operation triggered on the screen. The user can slide the screen with a finger, and the redundant bullet screen in the area passed will be hidden, revealing the video playback screen. When the user slides the screen with a finger, the terminal can detect the coordinate position touched by the user's finger, and hide the redundant bullet screen at the arrangement position corresponding to the coordinate position. It can be understood that only when the redundant bullet screen is displayed in the video playback screen, the terminal will respond to the erasing operation for the redundant bullet screen and hide the redundant bullet screen corresponding to the erased area.

[0158] like Figure 6 FIG. 1 is a flow chart of displaying redundant bullet comments in a detailed embodiment. Figure 6 After the terminal requests the redundant barrage data, it can determine whether to end the display of the redundant barrage according to whether the barrage cancellation operation is detected. If so, cancel the display of the redundant barrage and play the video normally. If not, prepare to obtain the next batch of redundant barrage data and obtain the configuration style of the redundant barrage, such as color, border, etc., and then generate the arrangement position of the current barrage according to the screen size. Then, the redundant barrage emergence animation can be displayed. After the emergence animation ends, the redundant barrage is displayed normally (that is, the emergence animation is completed), and then it is determined whether the display time of the redundant barrage reaches the preset time. If so, hide the current batch of redundant barrages. If not, continue to display the redundant barrage normally, and return to continue to determine whether to end the display of the redundant barrage.

[0159] The barrage processing method provided in the embodiment of the present application can automatically analyze the video content and generate redundant barrages related to the video content based on AIGC technology, and cover the entire screen with these redundant barrages, thereby blocking the video playback area and helping users to actively block the segments they want to block. Because the redundant barrages are related to the video content, they will not affect the video playback progress and will not affect the user's acquisition of key video content, thereby improving the user's video viewing experience.

[0160] In one embodiment, Figure 7 As shown, a bullet screen processing method is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, and the following steps are included:

[0161] Step 702: receiving a redundant barrage generation request sent by the terminal when playing the target video.

[0162] The target video is the video currently being played by the terminal.

[0163] In one embodiment, the redundant bullet screen generation request is generated by the terminal according to the video ID and current playback progress of the target video after the terminal detects the bullet screen trigger operation for displaying redundant bullet screen in the video playback screen. It can be understood that during the process of the terminal playing the target video, the video playback screen changes with the playback progress.

[0164] Specifically, during the process of playing the target video, the terminal can detect a bullet screen trigger operation for displaying redundant bullet screens in the video playback screen. Redundant bullet screens are bullet screens that are different from the historical bullet screens of the video. The redundant bullet screens in the embodiments of the present application are video bullet screens that are specifically used to block the video playback screen. The bullet screen trigger operation for displaying redundant bullet screens is different from the trigger operation for displaying the historical bullet screens of the video.

[0165] Exemplarily, the bullet screen triggering operation for displaying redundant bullet screens in the video playback screen may be a shaking operation on the terminal. Then, during the playback of the target video, the terminal may monitor the motion data of the terminal through its own sensors such as an accelerometer, an inertial sensor, a gyroscope, etc., thereby detecting whether a shaking operation is generated for the terminal. If a shaking operation is detected for the terminal, it is considered that the bullet screen triggering operation for displaying redundant bullet screens in the video playback screen is triggered. Optionally, if a shaking operation is detected for the terminal again, it is considered that the bullet screen cancelling operation for cancelling the display of redundant bullet screens in the video playback screen is triggered.

[0166] Exemplarily, the terminal may also set a control for turning on or off the redundant bullet screen function in the video playback interface. By triggering the control, the redundant bullet screen function may be turned on or off. When the redundant bullet screen function is turned on, the terminal detects a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen. Optionally, when the redundant bullet screen function is turned off, the terminal detects a bullet screen canceling operation for canceling the display of redundant bullet screens in the video playback screen.

[0167] Of course, the bullet screen trigger operation for displaying redundant bullet screens in the video playback screen can be set according to actual needs, or it can be other operations, such as clicking the screen multiple times, placing the screen face down, etc. as bullet screen trigger operations.

[0168] Specifically, after detecting the barrage trigger operation, the terminal generates a redundant barrage generation request based on the playback progress of the target video and the video identifier of the target video when the barrage trigger operation is detected, and sends the redundant barrage generation request to the server. The request parameters of the redundant barrage generation request include the current playback progress and may also include video information such as video identifier or episode identifier.

[0169] After detecting the bullet screen triggering operation, if the terminal does not detect the bullet screen canceling operation, it can continuously send new redundant bullet screen generation requests to the server as the current playback progress changes. For example, the terminal can send new redundant bullet screen generation requests at fixed intervals (such as 5 seconds) according to the updated current playback progress, so as to ensure the diversity of redundant bullet screens displayed on the video playback screen and their matching with the video playback screen.

[0170] Step 704, obtaining the current playback progress of the target video according to the redundant barrage generation request.

[0171] After receiving the redundant bullet screen generation request, the server obtains the current playback progress from the redundant bullet screen generation request.

[0172] Step 706: Obtain the video frames after the current playback progress from the video frames of the target video.

[0173] In one embodiment, obtaining video frames after the current playback progress from video frames of the target video includes: obtaining a video frame sequence corresponding to the target video; and obtaining at least one video frame after the current playback progress from the video frame sequence.

[0174] Among them, the video frame after the current playback progress is the video frame related to the current playback screen. The video frame after the current playback progress can be N video frames after the current playback progress, such as N key frames, and the key frame is an I frame, an intra-frame coded frame. N can be set according to actual needs, for example, it can be 5. The video frame after the current playback progress can be a key frame within M seconds after the current playback progress, and M can be set according to actual needs, for example, it can be 3.

[0175] Step 708: Determine description information about the video playback screen of the target video according to the video frame.

[0176] In one embodiment, descriptive information about a video playback screen of a target video is determined based on a video frame, including: performing image detection on the acquired video frame to obtain object information in the video playback screen; performing semantic understanding on the acquired video frame to obtain semantic information of the video playback screen; performing character recognition on the acquired video frame to obtain text content of the video playback screen.

[0177] The description information of the video playback screen is the text content used to describe the video screen. The description information is generated based on the video playback screen. For example, the server can call the image detection model to obtain object information in the video playback screen according to the video frame, such as "a lady" and "fist". The server can call the image semantic understanding model to obtain semantic information of the video playback screen according to the video frame, such as "a lady raised her fist". The server can call the character recognition model to obtain the text content of the video playback screen according to the video frame, such as subtitles. If the subtitles are not recognized, the server can also obtain audio synchronized with the video playback screen, perform speech recognition on the audio, and use the recognized speech content as one of the description information of the video playback screen. Among them, the above-mentioned image detection model and image semantic understanding model can be replaced by a large language model.

[0178] Step 710: Feedback to the terminal at least one redundant bullet screen generated according to the description information, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0179] In one embodiment, the step of generating at least one redundant barrage based on the description information includes: obtaining the video type and prompt text template of the target video; filling the prompt text template according to the video type, description information and the specified number of barrages to obtain the prompt text; and generating a specified number of redundant barrages based on the prompt text through a large language model.

[0180] In one embodiment, the server can obtain the video type and prompt text template of the target video; fill in the prompt text template according to the video type, description information and the specified number of barrages to obtain the prompt text; and generate redundant barrages with a specified number of barrages according to the prompt text through a large language model.

[0181] The prompt text template is a template data preset for generating redundant bullet comments, which can be customized according to actual needs, and the present application embodiment does not limit this. For example, the prompt text template is:

[0182] Generate Z bullet comments with a length not exceeding Y words for a video of type X. The description information of the video is: CCC, DDD, EEE, ...

[0183] The description information may include the above-mentioned object information, semantic information, text content, etc.

[0184] Optionally, the prompt text may also include basic information of the video, such as the cast, video tags, video style, etc. An example of a prompt text template is:

[0185] Generate Z bullet comments with a length not exceeding Y words for a video of type X. The description information of the video is: CCC, DDD, EEE, ...

[0186] Generate Z comments with a length not exceeding Y words for a video of type X. The basic information of the video is: A, B, C, ...

[0187] The server fills in the prompt text template according to the video type, description information and the specified number of bullet comments to obtain the prompt text. The large language model is a deep learning model trained with a large amount of text data that can generate natural language text or understand the meaning of language text. Redundant bullet comments can be generated through the artificial intelligence content generation (AI Generated Content, AIGC) capability of the large language model. Content generation capabilities such as AI text continuation, text to image, AI host, etc. are all applications of artificial intelligence content generation. The large language model can handle a variety of natural language tasks, such as text classification, question and answer, dialogue, etc. The server inputs the generated prompt text into the large language model, and the large language model will output the corresponding redundant bullet comments according to the prompt text.

[0188] In this embodiment, by calling the large language model to generate redundant barrage according to the prompt text, the reasoning and understanding capabilities of the large language model are utilized to ensure that the generated redundant barrage is dynamically changeable as the understanding capability of the large language model increases, and to ensure that the generated redundant barrage matches the video playback screen.

[0189] The above-mentioned barrage processing method generates and sends a redundant barrage generation request according to the barrage triggering operation of the user at any time while watching the target video. After receiving the redundant barrage generation request, the current playback progress of the target video is obtained according to the redundant barrage generation request, and the video screen related to the current playback progress of the target video is image understood to obtain description information about the video playback screen of the target video, and then at least one redundant barrage corresponding to the current playback progress is automatically generated according to the description information to ensure the relevance of the redundant barrage to the currently played video content, and then the redundant barrage is fed back to the terminal. The terminal can immediately display the generated redundant barrages related to the video content on the video playback screen, and can help the user actively block the video playback screen at any time. In addition, since the barrage content of the redundant barrage matches the screen content of the video playback screen, even if the redundant barrage blocks the video playback screen, the user's understanding of the plot of the video will not be affected, thereby improving the user's video viewing experience.

[0190] In a specific embodiment, the bullet screen processing method includes the following steps:

[0191] 1. The terminal enters the video playback page of the target video and downloads the placeholder bullet screen from the server at the same time;

[0192] 2. The terminal plays the target video and displays the video playback screen of the target video;

[0193] 3. The terminal detects the bullet screen trigger operation for displaying redundant bullet screens in the video playback screen;

[0194] 4. After detecting the bullet screen triggering operation, the terminal obtains the current playback progress of the target video, generates a redundant bullet screen generation request according to the current playback progress and the video ID of the target video, and sends the redundant bullet screen generation request to the server;

[0195] 5. After detecting the bullet screen triggering operation, the terminal detects the bullet screen canceling operation for canceling the display of redundant bullet screens in the video playback screen. If the bullet screen canceling operation is not detected, a redundant bullet screen generation request is sent to the server once every preset time according to the current playback progress and the video ID of the target video;

[0196] 6. After sending a redundant bullet screen generation request to the server and before receiving at least one redundant bullet screen fed back by the server, the terminal overlays and displays a placeholder bullet screen on the video playback screen, and the placeholder bullet screen is used to cover the video playback screen;

[0197] 7. The server receives a redundant barrage generation request, and in response to the redundant barrage generation request, obtains a video frame sequence corresponding to the target video, obtains at least one video frame located after the current playback progress from the video frame sequence, performs image detection on the obtained video frame, obtains object information in the video playback screen, performs semantic understanding on the obtained video frame, obtains semantic information of the video playback screen, performs character recognition on the obtained video frame, obtains text content of the video playback screen, and uses the above object information, semantic information, and text content as description information about the video playback screen;

[0198] 8. The server obtains the video type and prompt text template of the target video, fills the prompt text template according to the video type, description information and the specified number of bullet screens, obtains the prompt text, and generates the specified number of redundant bullet screens according to the prompt text through the large language model;

[0199] 9. The server feeds back the generated redundant comments to the terminal;

[0200] 10. The terminal determines the arrangement position on the video playback screen, and displays each redundant bullet comment at the corresponding arrangement position in a changed form from a small-size style to a large-size style;

[0201] 11. The terminal detects an erasing operation on redundant bullet comments. When an erasing operation is detected, an erasing area corresponding to the erasing operation is determined in the video playback screen, and the redundant bullet comments located in the erasing area are hidden.

[0202] Examples of application scenarios in which the present invention can be implemented are as follows:

[0203] The user enters the playback page of the target video through the video client, and then downloads the placeholder bullet screen of the target video. The terminal also starts to play the target video. During the playback of the target video, the user can turn on the video bullet screen through the video bullet screen function of the video client. At this time, the historical bullet screen of the video, that is, the comment information sent by the user to the video in the past, will be displayed on the video playback screen. During the playback of the target video, the user can shake the terminal to trigger the display of redundant bullet screens on the video playback screen. Before the terminal receives the redundant bullet screen fed back by the server, the terminal can display the placeholder bullet screen of the target video on the video playback screen. When the terminal receives the redundant bullet screen, it can display the redundant bullet screen on the video playback screen in an emerging manner and in a style different from the historical bullet screen. The placeholder bullet screen can be automatically canceled. Then, batches of redundant bullet screens will continue to be displayed, and the video playback screen will continue to be blocked, but the user can understand the key content of the video at this time through the redundant bullet screen related to the video screen. Then, the user can shake the terminal again to trigger the cancellation of the display of redundant bullet screens on the video playback screen. At this time, the redundant bullet screen will no longer be displayed, and only the historical bullet screen will continue to be displayed.

[0204] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0205] Based on the same inventive concept, the embodiment of the present application also provides a barrage processing device for implementing the barrage processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more barrage processing device embodiments provided below can refer to the limitations of the barrage processing method above, and will not be repeated here.

[0206] In one embodiment, Figure 8 As shown, a bullet screen processing device 800 is provided, including: a video screen display module 802, a video screen display module 802 and a bullet screen display module 806, wherein:

[0207] The video screen display module 802 is used to display the video playback screen of the target video;

[0208] A detection module 804, used to detect a bullet screen triggering operation for displaying redundant bullet screens in a video playback screen;

[0209] The barrage display module 806 is used to overlay and display redundant barrage on the video playback screen after detecting a barrage trigger operation. The redundant barrage is used to cover the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen.

[0210] In one embodiment, the bullet screen processing device 800 further includes:

[0211] A request module, used to obtain the current playback progress of the target video after detecting the bullet screen triggering operation, generate a redundant bullet screen generation request according to the current playback progress, and obtain at least one redundant bullet screen according to the redundant bullet screen request;

[0212] The bullet comment display module 806 is also used to overlay and display at least one redundant bullet comment on the video playback screen.

[0213] In one embodiment, the request module is further used to send a redundant bullet comment generation request to the server, so that the server obtains a video frame after the current playback progress from the video frame of the target video, obtains description information about the video playback screen according to the obtained video frame, and generates at least one redundant bullet comment according to the description information;

[0214] The bullet screen processing device 800 further includes:

[0215] The receiving module is used to receive at least one redundant comment fed back by the server.

[0216] In one embodiment, the detection module 804 is further used to detect a bullet screen cancel operation for canceling the display of redundant bullet screens in the video playback screen after detecting the bullet screen trigger operation;

[0217] The request module is also used to execute the following steps at preset time intervals if no barrage cancellation operation is detected: obtaining the current playback progress of the target video, generating a redundant barrage generation request according to the current playback progress, and obtaining at least one redundant barrage according to the redundant barrage request.

[0218] Optionally, the request module is also used to send a redundant barrage generation request to the server, so that the server obtains the video frame after the current playback progress from the video frame of the target video, obtains description information about the video playback screen based on the obtained video frame, and generates at least one redundant barrage based on the description information.

[0219] In one embodiment, the bullet screen display module 806 is further used to cancel the redundant bullet screen superimposed on the video playback screen after a bullet screen cancel operation is detected.

[0220] In one embodiment, the bullet screen processing device 800 further includes:

[0221] The placeholder bullet screen download module is used to obtain the video information and prefabricated bullet screen package of the target video when starting video playback;

[0222] The barrage display module 806 is also used to superimpose and display a placeholder barrage on the video playback screen according to the video information and the prefabricated barrage package after sending a redundant barrage generation request to the server and before receiving at least one redundant barrage feedback from the server, and the placeholder barrage is used to block the video playback screen; and to cancel the superimposition and display of the placeholder barrage on the video playback screen after receiving at least one redundant barrage feedback from the server.

[0223] In one embodiment, the barrage display module 806 is also used to display historical barrages in a first style on the video playback screen when there are historical barrages corresponding to the video playback screen, and the historical barrages do not block the video playback screen; the barrage display module is also used to display redundant barrages in a second style on the video playback screen; wherein the second style is different from the first style.

[0224] In one embodiment, the detection module 804 is also used to detect the erasing operation on redundant barrages; when the erasing operation is detected, the erasing area corresponding to the erasing operation is determined in the video playback screen; the barrage display module is also used to hide the redundant barrages located in the erasing area.

[0225] In one embodiment, the bullet screen display module 806 is also used to determine the arrangement position on the video playback screen; and to display each redundant bullet screen at the corresponding arrangement position in a manner changing from a small-size style to a large-size style.

[0226] The above-mentioned barrage processing device 800 displays the video playback screen of the target video, detects the barrage trigger operation for displaying redundant barrages in the video playback screen, and after detecting the barrage trigger operation, superimposes and displays redundant barrages on the video playback screen. The redundant barrages are used to block the video playback screen, and the barrage content of the redundant barrages matches the screen content of the video playback screen. This method allows the user to actively trigger the barrage trigger operation of displaying redundant barrages in the video playback screen at any time during the process of watching the target video. Therefore, during the process of playing the target video, redundant barrages are displayed in the video playback screen to block the video playback screen at any time. In addition, since the barrage content of the redundant barrages matches the screen content of the video playback screen, even if the redundant barrages block the video playback screen, the user's understanding of the plot of the video will not be affected, thereby improving the user's video viewing experience.

[0227] In one embodiment, Fig. 9 As shown, a bullet screen processing device 900 is provided, including: a receiving module 902, a progress acquisition module 904, a video frame acquisition module 906, a description information determination module 908 and a feedback module 910, wherein:

[0228] The receiving module 902 is used to receive a redundant barrage generation request sent by the terminal when playing the target video;

[0229] The progress acquisition module 904 is used to acquire the current playback progress of the target video according to the redundant barrage generation request;

[0230] The video frame acquisition module 906 is used to acquire the video frames after the current playback progress from the video frames of the target video;

[0231] A description information determination module 908, configured to determine description information about a video playback screen of a target video according to a video frame;

[0232] The feedback module 910 is used to feed back to the terminal at least one redundant bullet screen generated according to the description information, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

[0233] In one embodiment, the redundant bullet screen generation request is generated by the terminal according to the video identifier and current playback progress of the target video after the terminal detects a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen.

[0234] In one embodiment, the video frame acquisition module 906 is further used to acquire a video frame sequence corresponding to the target video; and acquire at least one video frame located after the current playback progress from the video frame sequence.

[0235] In one embodiment, the description information determination module 908 is also used to perform image detection on the acquired video frames to obtain object information in the video playback screen; perform semantic understanding on the acquired video frames to obtain semantic information of the video playback screen; perform character recognition on the acquired video frames to obtain text content of the video playback screen.

[0236] In one embodiment, the bullet screen processing device 900 further includes:

[0237] The model calling module is used to obtain the video type and prompt text template of the target video; fill the prompt text template according to the video type, description information and the specified number of barrages to obtain the prompt text; and generate redundant barrages with a specified number of barrages according to the prompt text through a large language model.

[0238] The above-mentioned barrage processing 900 generates and sends a redundant barrage generation request according to the barrage triggering operation of the user at any time while watching the target video. After receiving the redundant barrage generation request, the current playback progress of the target video is obtained according to the redundant barrage generation request, and the video screen related to the current playback progress of the target video is image understood to obtain description information about the video playback screen of the target video, and then at least one redundant barrage corresponding to the current playback progress is automatically generated according to the description information to ensure the relevance of the redundant barrage to the currently played video content, and then the redundant barrage is fed back to the terminal. The terminal can immediately display the generated redundant barrages related to the video content on the video playback screen, and can help the user actively block the video playback screen at any time. In addition, since the barrage content of the redundant barrage matches the screen content of the video playback screen, even if the redundant barrage blocks the video playback screen, the user's understanding of the plot of the video will not be affected, thereby improving the user's video viewing experience.

[0239] Each module in the above-mentioned bullet screen processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0240] In one embodiment, a computer device is provided, which may be Figure 1 The internal structure diagram of the server 104 in FIG. 1 may be as follows: Fig.10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video data, video barrage data or a large language model. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a barrage processing method is implemented.

[0241] In one embodiment, a computer device is provided, which may be Figure 1 The terminal 102 in FIG. 1 may have an internal structure as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless method can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a barrage processing method is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0242] Those skilled in the art will understand that Fig.10 , Fig.11The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0243] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the barrage processing method provided in the embodiment of the present application are implemented.

[0244] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the barrage processing method provided in the embodiment of the present application are implemented.

[0245] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the barrage processing method provided in an embodiment of the present application.

[0246] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0247] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0248] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0249] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing barrage, characterized in that: The method comprises: Display the video playback screen of the target video; Detecting a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen; After the bullet screen triggering operation is detected, a redundant bullet screen is superimposed and displayed on the video playback screen, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

2. The method according to claim 1, characterized in that After the bullet screen triggering operation is detected, redundant bullet screens are superimposed and displayed on the video playback screen, including: After detecting the bullet screen triggering operation, obtaining the current playback progress of the target video; Generate a redundant bullet screen generation request according to the current playback progress; Acquire at least one redundant bullet comment according to the redundant bullet comment generation request; The at least one redundant comment is displayed superimposed on the video playback screen.

3. The method according to claim 2, characterized in that The method further comprises: After detecting the bullet screen triggering operation, detecting a bullet screen canceling operation for canceling display of redundant bullet screens in the video playback screen; If the bullet screen cancelling operation is not detected, the following steps are performed at preset intervals: Obtaining the current playback progress of the target video, generating a redundant bullet screen generation request according to the current playback progress, and obtaining at least one redundant bullet screen according to the redundant bullet screen request; The at least one redundant comment is displayed superimposed on the video playback screen.

4. The method according to claim 2 or 3, characterized in that: The obtaining at least one redundant bullet comment according to the redundant bullet comment generation request includes: Sending the redundant bullet comment generation request to the server, so that the server obtains a video frame after the current playback progress from the video frame of the target video, obtains description information about the video playback screen according to the obtained video frame, and generates at least one redundant bullet comment according to the description information; Receive the at least one redundant barrage fed back by the server.

5. The method according to claim 3, characterized in that: The method further comprises: If the barrage cancelling operation is detected, then after the barrage cancelling operation is detected, the redundant barrage displayed superimposed on the video playback screen is canceled.

6. The method according to claim 4, characterized in that The method further comprises: When starting video playback, obtain the video information and prefabricated bullet comment package of the target video; After sending the redundant barrage generation request to the server and before receiving the at least one redundant barrage fed back by the server, the method further includes: According to the video information and the prefabricated bullet screen package, a placeholder bullet screen is superimposed and displayed on the video playback screen, and the placeholder bullet screen is used to cover the video playback screen; After receiving the at least one redundant comment fed back by the server, the method further includes: Cancel the overlay display of the placeholder bullet screen on the video playback screen.

7. The method according to claim 1, characterized in that The method further comprises: When there is a historical bullet comment corresponding to the video playback screen, the historical bullet comment is displayed in a first style on the video playback screen, and the historical bullet comment does not block the video playback screen; The superimposing and displaying redundant bullet comments on the video playback screen includes: Overlaying and displaying the redundant bullet comments in a second style on the video playback screen; The second style is different from the first style.

8. The method according to claim 1, characterized in that The method further comprises: Detecting an erasing operation on the redundant barrage; When the erasing operation is detected, determining an erasing area corresponding to the erasing operation in the video playback screen; Hide the redundant bullet comments located in the erase area.

9. The method according to any one of claims 1-3, 5, 7, and 8, characterized in that: The superimposing and displaying redundant bullet comments on the video playback screen includes: Determining the arrangement position on the video playback screen; Display each of the redundant bullet comments at the corresponding arrangement position changes from a small-size style to a large-size style.

10. A method for generating a bullet comment, characterized in that: The method comprises: A redundant bullet screen generation request sent by a receiving terminal when playing a target video; Obtaining the current playback progress of the target video according to the redundant bullet screen generation request; Acquire the video frames after the current playback progress from the video frames of the target video; Determine description information about a video playback screen of the target video according to the video frame; At least one redundant bullet screen generated according to the description information is fed back to the terminal, where the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

11. The method according to claim 10, characterized in that The redundant barrage generation request is generated by the terminal according to the video identifier and current playback progress of the target video after the terminal detects a barrage trigger operation for displaying redundant barrages in the video playback screen.

12. The method according to claim 10, characterized in that The acquiring the video frame after the current playback progress from the video frame of the target video includes: Obtaining a video frame sequence corresponding to the target video; At least one video frame located after the current playback progress is obtained from the video frame sequence.

13. The method according to claim 10, characterized in that The determining, according to the video frame, description information about the video playback screen of the target video includes: Performing image detection on the acquired video frame to obtain object information in the video playback screen; Performing semantic understanding on the acquired video frame to obtain semantic information of the video playback screen; Character recognition is performed on the acquired video frame to obtain text content of the video playback screen.

14. The method according to any one of claims 10 to 13, characterized in that The step of generating at least one redundant comment according to the description information comprises: Obtain the video type and prompt text template of the target video; Fill the prompt text template according to the video type, the description information and the specified number of bullet comments to obtain a prompt text; Generate the specified number of redundant bullet comments according to the prompt text through a large language model.

15. A bullet comment processing device, characterized in that: The device comprises: A video screen display module, used to display the video playback screen of the target video; A detection module, used to detect a bullet screen triggering operation for displaying redundant bullet screens in the video playback screen; The barrage display module is used to overlay and display redundant barrage on the video playback screen after detecting the barrage trigger operation, wherein the redundant barrage is used to cover the video playback screen, and the barrage content of the redundant barrage matches the screen content of the video playback screen.

16. A bullet comment processing device, characterized in that: The device comprises: A receiving module, used for receiving a redundant barrage generation request sent by a terminal when playing a target video; A progress acquisition module, used to acquire the current playback progress of the target video according to the redundant barrage generation request; A video frame acquisition module, used to acquire video frames after the current playback progress from the video frames of the target video; A description information determination module, used to determine description information about the video playback screen of the target video according to the video frame; A feedback module is used to feed back to the terminal at least one redundant bullet screen generated according to the description information, wherein the redundant bullet screen is used to cover the video playback screen, and the bullet screen content of the redundant bullet screen matches the screen content of the video playback screen.

17. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 14 are implemented.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

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

Images