Video processing method and device based on live broadcast, equipment, medium and program product

Abstract

The invention provides a live broadcast-based video processing method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps that a video generation control corresponding to a target scene is displayed in a live broadcast recording interface, and the video generation control is used for generating a target video corresponding to a target event according to historical live broadcast data of the target scene; in response to a trigger operation for the video generation control, when live broadcast data corresponding to a target event exists in the historical live broadcast data, determining a video clip corresponding to the target event and live broadcast interaction information associated with the video clip, and combining the video clip with the live broadcast interaction information to generate a live broadcast interaction result; and generating a target video corresponding to the target event. Through the method and the device, the video of the target event can be quickly generated, the video generation process is simplified, and the man-machine interaction efficiency is improved.

Description

Technical Field

[0001] The present application relates to Internet technology, and in particular to a video processing method, device, equipment, medium and program product based on live broadcast. Background Art

[0002] With the development of Internet technology and live broadcast technology, more and more live broadcast platforms or scene applications can broadcast target scenes (such as games, ball games, etc.), and can record the entire live broadcast process to obtain the live broadcast video corresponding to the target scene. Taking the target scene as a game as an example, when the game is broadcast live through a live broadcast platform or the game's own live broadcast application, the live broadcast process can be recorded through the screen recording function of the mobile phone or the screen recording function in the game to obtain a complete recording video of the game.

[0003] Since the above-mentioned screen recording function can only obtain the entire game video material, but this kind of game video material is often relatively long, if the user only wants to view or edit some wonderful video clips, he can only repeatedly drag the progress bar of the recorded video to find the corresponding wonderful clips to view or edit. The operation is complicated and the human-computer interaction efficiency is low. Summary of the invention

[0004] The embodiments of the present application provide a video processing method, device, electronic device, computer-readable storage medium and computer program product based on live broadcast, which can quickly generate videos of target events, simplify the video generation process, and improve the efficiency of human-computer interaction.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] The embodiment of the present application provides a video processing method based on live broadcast, including:

[0007] Displaying a video generation control corresponding to the target scene in the live broadcast recording interface, wherein the video generation control is used to generate a video corresponding to the target event based on the historical live broadcast data of the target scene;

[0008] In response to a trigger operation on the video generation control, when there is live broadcast data corresponding to the target event in the historical live broadcast data, the video clip corresponding to the target event and the live broadcast interaction information associated with the video clip are determined, and the video clip is combined with the live broadcast interaction information to generate a target video corresponding to the target event.

[0009] The embodiment of the present application provides a video processing device based on live broadcast, including:

[0010] A control display module, used to display a video generation control corresponding to a target scene in a live broadcast recording interface, wherein the video generation control is used to generate a video corresponding to a target event based on historical live broadcast data of the target scene;

[0011] A video generation module is used to respond to a trigger operation on the video generation control. When there is live broadcast data corresponding to the target event in the historical live broadcast data, determine the video segment corresponding to the target event and the live broadcast interaction information associated with the video segment, and combine the video segment with the live broadcast interaction information to generate a target video corresponding to the target event.

[0012] In the above scheme, after the target video corresponding to the target event is generated, the device also includes: a video preview module, which is used to respond to the preview operation on the target video, play the video content of the video clip in the preview interface of the target video, and display the live interactive information that is associated with the video content during the playback of the video content.

[0013] In the above scheme, the video generation module is also used to display at least one video template for selection in response to a trigger operation on the video generation control; in response to a selection operation on a target video template, when there is live broadcast data corresponding to the target event indicated by the target video template in the historical live broadcast data, the live broadcast data is nested into the target video template to generate a video clip corresponding to the target event.

[0014] In the above scheme, the video generation module is also used to embed the live broadcast data into the target video template to generate a pre-processed segment; in response to the video parameter editing operation, the video editing parameters are displayed in the target video template, and the video editing parameters include at least one of the following: subtitles, special effects, sound effects, and textures; in response to the video editing operation, the pre-processed segment is edited according to the video editing parameters to obtain the video segment corresponding to the target event.

[0015] In the above scheme, the video generation module is also used to display an interactive control for obtaining live interactive information in the target video template; in response to a trigger operation on the interactive control, obtain the live interactive information associated with the video clip, and display the live interactive information in the information editing area in the target video template; wherein the display position of the live interactive information in the information editing area corresponds to the time period of the video clip corresponding to the live interactive information; in response to a determination operation on the live interactive information, combine the video clip and the live interactive information in the target video template to generate a target video corresponding to the target event.

[0016] In the above scheme, the video generation module is also used to display an information filtering condition setting interface in response to a trigger operation on the interactive control; to display the set information filtering conditions in response to a filtering condition setting operation triggered based on the information filtering condition setting interface; and to obtain live interactive information that meets the information filtering conditions and has an associated relationship with the video clip in response to a live interactive information acquisition operation.

[0017] In the above scheme, after the live broadcast interaction information is displayed in the information editing area in the target video template, the device also includes: an information editing module, which is used to edit the live broadcast interaction information displayed in the information editing area in response to the information editing operation, and obtain the edited live broadcast interaction information, so as to combine the edited live broadcast interaction information with the video clip.

[0018] In the above scheme, the video generation module is also used to respond to the trigger operation of the video generation control, display the playback interface of the historical live video corresponding to the target scene, and display event indication information and clip controls in the playback interface; wherein the event indication information is used to indicate that there is live data corresponding to the target event in the historical live data corresponding to the historical live video, and the clip control is used to clip at least one video clip from the historical live video; in response to the video clip operation triggered based on the clip control, the video clip corresponding to the target event is clipped from the historical live video.

[0019] In the above scheme, the video generation module is also used to obtain influencing parameters for influencing the editing priority of the target events when the number of the target events is at least two, wherein the influencing parameters include at least one of the following: virtual character data associated with the target event, the event type to which the target event belongs, and historical editing data corresponding to the target event; based on the influencing parameters, the editing priority of each of the target events is determined, and in the playback interface, the display style corresponding to the editing priority is used to display the event indication information corresponding to each of the target events.

[0020] In the above scheme, the video generation module is also used to display corresponding editing controls at the associated positions of each event indication information in the playback interface, and there is a one-to-one correspondence between the editing controls and the target events; in response to the video editing operation triggered based on the selected editing control, a video clip corresponding to the target event corresponding to the selected editing control is edited from the historical live video.

[0021] In the above scheme, the video generation module is also used for, when the number of the target events is multiple, the clip control corresponds to the multiple target events; in response to the trigger operation of the clip control, controlling the event indication information corresponding to each of the target events to be in an operable state; in response to the event indication information selection operation, clipping from the historical live video a video clip corresponding to the target event corresponding to the selected event indication information.

[0022] In the above scheme, the video generation module is also used to obtain influencing parameters for influencing the selection priority of the live interactive information when there are multiple live interactive information associated with the video clip; wherein the influencing parameters include at least one of the following: the correlation between the live interactive information and the video clip, the account data of the interactive account corresponding to the live interactive information, and the category of the live interactive information; based on the influencing parameters, the selection priority of each of the live interactive information is determined, and the live interactive information with a selection priority higher than the priority threshold is obtained from the multiple live interactive information.

[0023] In the above scheme, the video generation module is also used to combine each of the video clips with the associated live interactive information to generate corresponding multiple combined videos when the number of the video clips corresponding to the target event is multiple and the multiple video clips are discontinuous; and splice the multiple combined videos to generate a target video corresponding to the target event.

[0024] In the above scheme, the video generation module is also used to combine the video clips corresponding to each type of target event with the associated live interactive information when there are multiple types of target events, so as to generate target videos corresponding to each type of target event; the device also includes: a video generation module, which is used to splice the target videos corresponding to each type of target event according to the order in which each type of target event appears in the live broadcast of the target scene, so as to generate a video corresponding to the target scene.

[0025] In the above scheme, the video generation module is also used to combine the video clips corresponding to each type of target event with the associated live interactive information to generate multiple combined videos corresponding to each type of target event when there are multiple video clips corresponding to each type of target event; and to splice the multiple combined videos corresponding to each type of target event to generate target videos corresponding to each type of target event.

[0026] In the above scheme, before determining the video segment corresponding to the target event, the device also includes: a live data screening module, which is used to match the component data of the target event with the historical live data, and when the matching degree between the historical live data and the component data exceeds the matching degree threshold, it is determined that there is live data corresponding to the target event in the historical live data; or, when the historical live data contains a target sentence for describing the target event, and the number of occurrences of the target sentence reaches the number threshold, it is determined that there is live data corresponding to the target event in the historical live data; or, when the historical live data includes live interactive data for the target scene, event recognition is performed on the live interactive data to obtain a corresponding recognition event, and when the recognition event is successfully compared with the target event, it is determined that there is live data corresponding to the target event in the historical live data.

[0027] An embodiment of the present application provides an electronic device, including:

[0028] A memory for storing computer executable instructions or computer programs;

[0029] The processor is used to implement the live broadcast-based video processing method provided in the embodiment of the present application when executing the computer executable instructions or computer programs stored in the memory.

[0030] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions or a computer program for implementing a live broadcast-based video processing method provided in an embodiment of the present application when executed by a processor.

[0031] An embodiment of the present application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, the live broadcast-based video processing method provided in the embodiment of the present application is implemented.

[0032] The embodiments of the present application have the following beneficial effects:

[0033] By applying the embodiments of the present application, when it is necessary to generate a video corresponding to a target event, the user does not need to drag the progress bar of the recorded video to find the video clip corresponding to the target event for editing. The video clip and live interactive information corresponding to the target event can be automatically obtained through the video generation control, and the target video corresponding to the target event can be quickly generated, which simplifies the video editing operation process and improves the efficiency of human-computer interaction. In addition, since the live interactive information associated with the video clip is integrated into the generated target video, the live interactive information can better restore the live scene, enrich the composition content of the target video, meet the diversified information acquisition needs, and improve the user's viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 1 is a schematic diagram of the architecture of a live-broadcast-based video processing system 100 provided in an embodiment of the present application;

[0035] Figure 2 is a schematic diagram of the structure of an electronic device 500 provided in an embodiment of the present application;

[0036] Figure 3 It is a flowchart of a video processing method based on live broadcast provided in an embodiment of the present application;

[0037] Figure 4 is a schematic diagram of a live broadcast recording of a target scene provided in an embodiment of the present application;

[0038] Figure 5 is a schematic diagram of video editing provided by an embodiment of the present application;

[0039] Figure 6 is a schematic diagram of video editing provided by an embodiment of the present application;

[0040] Figure 7 is a schematic diagram of video editing provided by an embodiment of the present application;

[0041] Figure 8 It is a schematic diagram of screening live interactive information provided by an embodiment of the present application;

[0042] Fig. 9 is a schematic diagram of video editing provided by an embodiment of the present application;

[0043] Fig.10 is a schematic diagram of video editing provided by an embodiment of the present application;

[0044] Fig.11 is a schematic diagram of video editing provided by an embodiment of the present application;

[0045] Fig.12 It is a schematic diagram of video playback provided in an embodiment of the present application;

[0046] Fig.13 This is a schematic diagram of video sharing provided in an embodiment of the present application;

[0047] Fig.14 It is a flowchart of a live broadcast-based video processing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0049] It is understandable that in the embodiments of the present application, when data related to user information (such as user trigger operations, account data of interactive accounts, etc.) is involved, when the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0050] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0052] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0053] 1) Client: an application running in the terminal to provide various services, such as video playback client, instant messaging client, game client, live broadcast client, etc.

[0054] 2) In response, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or have a set delay. Unless otherwise specified, there is no restriction on the order of execution of the multiple operations executed.

[0055] The embodiments of the present application provide a video processing method, device, electronic device, computer-readable storage medium and computer program product based on live broadcast, which can quickly generate videos of target events, simplify the video generation process, and improve the efficiency of human-computer interaction. The exemplary application of the electronic device provided by the embodiments of the present application is described below. The electronic device provided by the embodiments of the present application can be implemented as various types of user terminals such as laptops, tablet computers, desktop computers, set-top boxes, mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), smart phones, smart speakers, smart watches, smart TVs, and vehicle-mounted terminals, and can also be implemented as servers. Below, an exemplary application when the electronic device is implemented as a terminal will be described.

[0056] See also Figure 1 , Figure 1It is an architectural diagram of a live broadcast-based video processing system 100 provided in an embodiment of the present application. To support an exemplary application, a terminal (terminal 400-1 and terminal 400-2 are shown as examples) is connected to a server 200 via a network 300. The network 300 may be a wide area network or a local area network, or a combination of the two.

[0057] In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a car terminal, etc., but is not limited to this. The terminal is provided with a client with a live broadcast function, such as a video playback client, an instant messaging client, a game client, a live broadcast client, etc. The server 200 is a background server corresponding to the client, which can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The terminal and the server can be directly or indirectly connected by wired or wireless communication, which is not limited in the embodiments of the present application.

[0058] In actual applications, when a user views the live broadcast information corresponding to the target scene through a client in a terminal, a video generation control corresponding to the target scene is displayed in a live broadcast recording interface, wherein the video generation control is used to generate a target video corresponding to a target event based on historical live broadcast data of the target scene; in response to a trigger operation on the video generation control, a video generation request for the target event is sent to the server 200; based on the video generation request, when the server 200 determines that there is live broadcast data corresponding to the target event in the historical live broadcast data, it obtains a video clip corresponding to the target event and live broadcast interaction information associated with the video clip, combines the video clip with the live broadcast interaction information, generates a target video corresponding to the target event, and returns the generated target video to the terminal; after receiving the target video, a preview control for previewing a target example is displayed in the live broadcast recording interface (such as updating the video generation control to a preview control), and in response to a preview operation on the target video triggered based on the preview control, in the preview interface of the target video, the video content of the video clip is played, and during the playback of the video content, the live broadcast interaction information associated with the video content is displayed.

[0059] See also Figure 2 , Figure 2 is a schematic diagram of the structure of an electronic device 500 provided in an embodiment of the present application, taking the electronic device 500 as Figure 1 For example, the terminal in Figure 2The electronic device 500 shown includes: at least one processor 510, a memory 550, at least one network interface 520 and a user interface 530. The various components in the electronic device 500 are coupled together via a bus system 540. It is understood that the bus system 540 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 540 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 540 is not described in detail. Figure 2 Various buses are labeled as bus system 540 .

[0060] The processor 510 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0061] The memory 550 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 550 described in the embodiment of the present application is intended to include any suitable type of memory. The memory 550 optionally includes one or more storage devices that are physically far away from the processor 510.

[0062] In some embodiments, the memory 550 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0063] The operating system 551 includes system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic businesses and processing hardware-based tasks; a network communication module 552 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 520. Exemplary network interfaces 520 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.

[0064] In some embodiments, the xx device provided in the embodiment of the present application can be implemented in software, and the live broadcast-based video processing device provided in the embodiment of the present application can be provided as various software embodiments, including various forms including applications, software, software modules, scripts or codes. Figure 2A live broadcast-based video processing device 555 stored in a memory 550 is shown, which may be software in the form of a program or plug-in, and includes a series of modules, including a control display module 5551 and a video generation module 5552. These modules are logical, and therefore may be arbitrarily combined or further split according to the functions implemented. The functions of each module will be described below.

[0065] In other embodiments, the device provided in the embodiments of the present application can be implemented in hardware. As an example, the device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the live broadcast-based video processing method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (Digital Signal Processor, DSP), programmable logic devices (Programmable Logic Device, PLD), complex programmable logic devices (Complex Programmable Logic Device, CPLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other electronic components.

[0066] In some embodiments, the terminal or server can implement the live video processing method based on live broadcast provided by the embodiment of the present application by running various computer executable instructions or computer programs. For example, computer executable instructions can be microprogram-level commands, machine instructions or software instructions. The computer program can be a native program or software module in the operating system; it can be a native application (APPlication, APP), that is, a program that needs to be installed in the operating system to run, such as a live broadcast APP, a game APP; it can also be a small program that can be embedded in any APP, that is, a program that can be run only by downloading it to a browser environment. In short, the above-mentioned computer executable instructions can be instructions in any form, and the above-mentioned computer program can be an application, module or plug-in in any form.

[0067] As mentioned above, the live video processing method provided in the embodiment of the present application can be implemented by various types of electronic devices, for example, Figure 1 The terminal in the command prompt can also be executed separately by Figure 1 The terminal and server 200 in the embodiment cooperate to execute. Figure 1 The example of the terminal alone executing the live video processing method provided in the embodiment of the present application is described. Figure 3 , Figure 3 is a flowchart of a video processing method based on live broadcast provided in an embodiment of the present application, which will be combined with Figure 3 The steps shown are explained.

[0068] Step 101: The terminal displays a video generation control corresponding to a target scene in a live broadcast recording interface.

[0069] In actual applications, a client with a live broadcast function is provided on the terminal. When the target scene is broadcast live through the client with a live broadcast function, the live broadcast record information and video generation controls corresponding to the current account are displayed in the live broadcast record interface. The live broadcast record information is used to indicate that the target scene has been broadcast live, and records relevant data such as the live broadcast time and the battle outcome of the target scene (such as victory or defeat). The video generation control is used to generate a video of the corresponding target event based on the historical live broadcast data of the target scene.

[0070] Among them, the historical live broadcast data can reflect the real-time live broadcast content of the target scene. For example, when the target scene is a game match, the historical live broadcast data can be the equipment data of virtual objects equipped with virtual props or virtual skills in the game during the live broadcast of the game, or the attack data of using the equipped virtual props or virtual skills to attack the enemy, or the special effects data of the attack effects displayed when attacking the enemy, or the scene data in the game scene (such as trees, mountains, obstacles, etc.), etc.; for example, when the target scene is a ball game, the historical live broadcast data can be the sports data of players participating in the ball game kicking and passing the ball on the field during the live broadcast of the ball game, or the equipment data such as jerseys or shoes worn by the players, etc.

[0071] If there are multiple live broadcasts corresponding to the target scene for the current account, the live broadcast record information and video generation controls corresponding to all live broadcasts within the target time period (which can be set according to actual needs, such as setting it to the last 7 days) can be displayed in the live broadcast record interface. The current account can understand the performance corresponding to each live broadcast based on the live broadcast record information, and can generate a video corresponding to the target event of a live broadcast through the video generation controls corresponding to the live broadcast according to needs.

[0072] See also Figure 4 , Figure 4It is a schematic diagram of the live broadcast record of the target scene provided in the embodiment of the present application. Taking the target scene as a game match as an example, the live broadcast record interface displays a list of game matches of all live broadcast sessions of the current account in the past 7 days, such as game match 1 corresponding to live broadcast session 1 and game match 2 corresponding to live broadcast session 2 (corresponding video generation control 402). The user corresponding to the current account can view the results of the game matches corresponding to each live broadcast session, such as the result of game match 1 being a victory and the result of game match 2 being a failure, and can generate a video of the target event corresponding to a certain live broadcast session through the video generation control corresponding to the live broadcast session as needed, such as generating a video of the target event in game match 1 through the video generation control 401 corresponding to live broadcast session 1; in this way, the user can quickly locate the target game match (i.e., the target scene) to generate a video of the target event in the target game match, thereby improving the flexibility of independent selection.

[0073] Step 102: In response to a trigger operation on a video generation control, when there is live broadcast data corresponding to a target event in the historical live broadcast data, determine a video clip corresponding to the target event and live broadcast interaction information associated with the video clip, and combine the video clip with the live broadcast interaction information to generate a target video corresponding to the target event.

[0074] Among them, the target event can be a wonderful event corresponding to the highlight moment (also known as the peak moment or wonderful moment) in the target scene (the target event can be considered as a general term for all wonderful events), or it can be a bad event corresponding to the dark moment (also known as the darkest moment) in the target scene. For example, when the target scene is a game, the target event can be a wonderful event such as the player using high-end operations (such as continuous killing operations) or killing enemies, or it can be a bad event where the player makes an obvious mistake using high-end skills; for example, when the target scene is a ball game, the target event can be a wonderful event such as a player scoring a goal, winning a game, breaking a personal record or breaking a world record in a game, or it can be a bad event where the player makes an obvious mistake such as losing the ball in a game. Generating videos corresponding to wonderful events can allow users to appreciate or learn superb skills, and generating videos corresponding to bad events can allow users to reflect on themselves to avoid similar mistakes.

[0075] In some embodiments, before determining the video segment corresponding to the target event, the terminal may determine whether there is live data corresponding to the target event in the historical live data by: matching the component data of the target event with the historical live data, and when the degree of match between the historical live data and the component data exceeds a matching degree threshold, determining that there is live data corresponding to the target event in the historical live data; or, when the historical live data contains a target sentence for describing the target event and the number of occurrences of the target sentence reaches a number threshold, determining that there is live data corresponding to the target event in the historical live data; or, when the historical live data includes live interaction data for the target scene, performing event recognition on the live interaction data to obtain a corresponding recognition event, and when the recognition event is successfully compared with the target event, determining that there is live data corresponding to the target event in the historical live data.

[0076] In actual applications, the component data corresponding to the target events in different scenes are different, and the component data corresponding to different target events in the same scene are also different. The component data corresponding to the target events in the scenes can be pre-set. For example, when the target scene is a game and the target event is a wonderful event corresponding to a triple kill operation, the component data of the target event is the relevant data constituting the triple kill operation; for another example, when the target scene is a ball game and the target event is a goal event, the component data of the target event is the relevant data of the player kicking the ball and the kicked ball moving on the court until it enters the goal. When judging whether there is live broadcast data of the target event in the historical live broadcast data, the historical live broadcast data can be matched with the component data corresponding to the target event (such as calculating the similarity value between the two, such as the cosine similarity value) to obtain a matching result, so as to determine whether there is live broadcast data of the target event in the historical live broadcast data according to the matching result. For example, when the matching result indicates that the matching degree between the historical live broadcast data and the component data corresponding to the target event exceeds the matching degree threshold (such as the similarity value or the cosine similarity value exceeds the similarity threshold), it is determined that the historical live broadcast data contains the live broadcast data corresponding to the target event; otherwise, when the matching result indicates that the matching degree between the historical live broadcast data and the component data does not exceed the matching degree threshold (such as the similarity value or the cosine similarity value does not exceed the similarity threshold), it is determined that the historical live broadcast data does not contain the live broadcast data corresponding to the target event.

[0077] In addition, the target event may also have a corresponding description sentence (i.e., a target sentence). For example, when the target event is a wonderful event corresponding to a three-kill operation in a game, the description sentence corresponding to the target event may be "xx three-kill"; for another example, when the target event is a goal-scoring event in a ball game, the description sentence corresponding to the target event may be "a goal was scored", etc. When the historical live broadcast data includes the anchor's explanation data for the target scene, there is a target sentence describing the target event in the explanation data, and the number of occurrences of the target sentence exceeds the number threshold (which can be set according to the actual application, such as 3), it can be determined that the historical live broadcast data contains the live broadcast data corresponding to the target event. For example, when the target scene is a game, the target event is a wonderful event corresponding to a three-kill operation, and the corresponding target sentence is "three-kill", if the historical live broadcast data contains "three-kill" or "successful three-kill", and the number of occurrences reaches 3 times, it is determined that the historical live broadcast data contains the live broadcast data corresponding to the target event.

[0078] In addition, it is also possible to judge whether the historical live broadcast data contains the live broadcast data of the corresponding target event according to the live broadcast interactive data of the anchor or the audience for the target scene in the live broadcast, such as the number of likes, comment data (the number of comments and the content of comments), and the virtual gift data, etc., because the live broadcast interactive data can reflect the actual situation of the target scene in the live broadcast to a certain extent. For example, when there is a wonderful moment in the target scene, the number of likes at the wonderful moment is much greater than the number of likes at the non-wonderful moment. Under normal circumstances, the live broadcast interactive data corresponding to the target event in different scenes can be different, and the live broadcast interactive data (such as the content of comments) corresponding to different target events in the same scene can also be different. For example, when the target scene is a game, if the target event is a triple kill, the interactive data is the comment content about the triple kill, and if the target event is the release of the flying skill, the interactive data is the comment content about the release of the flying skill; for example, when the target scene is a ball game, if the target event is a high-quality goal, the interactive data is the comment content about the goal, and if the target event is a high-quality block, the interactive data is the comment content about the block.

[0079] When the historical live broadcast data includes live broadcast interaction data for the target scene, event recognition can be performed on the live broadcast interaction data. When the types of live broadcast interaction data are multiple, event recognition can be performed in combination with multiple live broadcast interaction data. For example, if the number of likes corresponding to the historical live broadcast data at a certain moment is significantly higher than the number of likes at other moments, it can be determined that the historical live broadcast data at a certain moment may contain live broadcast data corresponding to a wonderful event. Then, the comment content corresponding to the historical live broadcast data is further extracted by keywords, and the corresponding recognition event is determined according to the extracted keywords. For example, when the target scene is a game, the comment content is mostly related to keywords such as "continuous kill" and "three consecutive kills", then the recognition event can be determined to be a continuous kill event; for example, when the target scene is a ball game, the comment content is mostly related to keywords such as "three-pointer" and "goal", then the recognition event can be determined to be a goal event. The target event can be regarded as a wonderful event pre-set for the target scene. When the recognition event is successfully compared with the pre-set target event (such as the similarity between the recognition event and the target event reaches more than 95%, it is considered that the comparison between the two is successful), it is determined that the historical live broadcast data contains live broadcast data corresponding to the target event.

[0080] In some embodiments, the terminal may respond to a trigger operation on a video generation control by determining a video segment corresponding to the target event when there is live broadcast data corresponding to the target event in the historical live broadcast data in the following manner: in response to a trigger operation on a video generation control, at least one video template for selection is displayed; in response to a selection operation on a target video template, when there is live broadcast data corresponding to the target event indicated by the target video template in the historical live broadcast data, the live broadcast data is nested into the target video template to generate a video segment corresponding to the target event.

[0081] Here, multiple video templates can be pre-set for users to use when editing videos. Usually, the target events corresponding to different video templates can be different. For example, when the target scene is a game, the target event corresponding to video template 1 is a flash kill event, and the target event corresponding to video template 2 is an N-kill event. Users can edit videos based on the selected video template to obtain video clips corresponding to the target events.

[0082] See also Figure 5 , Figure 5It is a schematic diagram of video editing provided in an embodiment of the present application. When a user triggers a video generation control 501, the terminal responds to the trigger operation and displays a video template interface. The video template interface includes multiple selectable video templates, such as video templates 1 to video templates 4. In response to a selection operation on a target video template (such as video template 1), when there is live broadcast data of a target event corresponding to the target video template (i.e., video template 1) in the historical live broadcast data, according to the target event corresponding to the target video template (such as video template 1), the live broadcast data of the time period corresponding to the target event is intercepted from the historical live broadcast data, and the intercepted live broadcast data corresponding to the target event is imported into the target video template (i.e., video template 1, corresponding to the flash kill event), so as to generate a video clip corresponding to the target event.

[0083] In some embodiments, the terminal can embed the live broadcast data into the target video template to generate a video clip corresponding to the target event in the following manner: embed the live broadcast data into the target video template to generate a preprocessed clip; in response to the video parameter editing operation, display the video editing parameters in the target video template, wherein the video editing parameters include at least one of the following: subtitles, special effects, sound effects, and textures; in response to the video editing operation, edit the preprocessed clip according to the video editing parameters to obtain a video clip corresponding to the target event.

[0084] See also Figure 6 , Figure 6 This is a schematic diagram of video editing provided in an embodiment of the present application. The live data corresponding to the target event intercepted from the historical live data is embedded in the target video template to generate a preprocessed segment (that is, the initial video segment is generated first). The target video template includes editing controls that can be used to edit the preprocessed segment, such as subtitle controls, special effects controls, sound effects controls, and texture controls. Video editing parameters such as subtitles, special effects, sound effects, and textures can be edited in the target video template through the editing controls. In response to the video editing operation, the preprocessed segment can be edited according to the video editing parameters to obtain a video segment corresponding to the target event, such as adding the video editing parameters of at least one of the subtitle special effects, sound effects, and textures to the preprocessed segment, and the segment after the preprocessed segment is edited is used as the video segment corresponding to the target event. In this way, users can conveniently edit the preprocessed segment according to actual needs to obtain the desired video segment, thereby improving the flexibility and richness of video editing.

[0085] In some embodiments, the terminal may determine the live interactive information associated with the video clip in the following manner: display an interactive control for obtaining the live interactive information in a target video template; in response to a trigger operation on the interactive control, obtain the live interactive information associated with the video clip, and display the live interactive information in the information editing area in the target video template; wherein the display position of the live interactive information in the information editing area corresponds to the time period of the video clip corresponding to the live interactive information; accordingly, the terminal may combine the video clip with the live interactive information in the following manner to generate a target video corresponding to the target event: in response to a determination operation on the live interactive information, combine the video clip with the live interactive information in the target video template to generate a target video corresponding to the target event.

[0086] See also Figure 7 , Figure 7 It is a schematic diagram of video editing provided in an embodiment of the present application, wherein an interactive control 701 (such as synchronized live broadcast information) is displayed in a target video template, and in response to a trigger operation on the interactive control 701, live broadcast interaction data of a time period corresponding to a target event during the live broadcast process is obtained, such as the number of likes, comment data (the number of comments and the content of comments), virtual gift data, etc., and the live broadcast interaction information is displayed in an information editing area 702, wherein the display position of the live broadcast interaction information in the information editing area 702 corresponds to the time period of the live broadcast interaction information in the video clip, and when the user triggers the "Done" confirmation button, the terminal responds to the trigger operation, combines the video clip and the live broadcast interaction information in the target video template, and uses the combined video as the target video corresponding to the target event.

[0087] In addition, the terminal can further edit the acquired live interactive information in the information editing area of ​​the target video template. In response to the information editing operation, the live interactive information displayed in the information editing area is edited, such as editing, modifying or deleting the live interactive information, to obtain the edited live interactive information, so as to combine the edited live interactive information with the video clip.

[0088] In some embodiments, the terminal may respond to a trigger operation on an interactive control to obtain live interactive information associated with a video clip in the following manner: in response to a trigger operation on an interactive control, display an information filtering condition setting interface; in response to a filtering condition setting operation triggered based on the information filtering condition setting interface, display the set information filtering conditions; in response to a live interactive information obtaining operation, obtain live interactive information that meets the information filtering conditions and has an associated relationship with the video clip.

[0089] Here, when there are multiple live interactive information associated with a video clip, certain information screening conditions can be set manually, wherein the information screening conditions include but are not limited to at least one of the following: the number and category of the live interactive information (categories include but are not limited to text, emoticons, virtual gifts), and select the live interactive information that meets the information screening conditions to combine the selected live interactive information with the video clip.

[0090] See also Figure 8 , Figure 8 It is a schematic diagram of filtering live interactive information provided in an embodiment of the present application, wherein an interactive control 801 (such as synchronized live broadcast information) is displayed in a target video template, and in response to a trigger operation on the interactive control 801, an information filtering condition setting interface 802 is displayed, and the information filtering condition is set through the information filtering condition setting interface 802. After the setting is completed, the live interactive information that meets the information filtering condition can be filtered out from the live interactive information associated with multiple video clips; in this way, the user can select the required live interactive information according to actual needs, so as to combine the filtered live interactive information with the video clips, thereby improving the flexibility of video editing.

[0091] In some embodiments, the terminal may respond to a trigger operation on a video generation control in the following manner to determine a video segment corresponding to the target event when there is live data corresponding to the target event in the historical live data: in response to a trigger operation on a video generation control, a playback interface of the historical live video corresponding to the target scene is displayed, and event indication information and a clipping control are displayed in the playback interface; wherein the event indication information is used to indicate that there is live data corresponding to the target event in the historical live data corresponding to the historical live video, and the clipping control is used to clip at least one video segment from the historical live video; in response to a video clipping operation triggered based on the clipping control, a video segment corresponding to the target event is clipped from the historical live video.

[0092] Here, in the process of live broadcasting the target scene, the entire live broadcast process can be recorded to obtain a historical live broadcast video, and the historical live broadcast video can be further edited to obtain a video clip corresponding to the target event. In actual applications, the historical live broadcast video can also be directly displayed in the live broadcast recording interface, and in response to the playback operation of the historical live broadcast video, the event indication information and the editing control are displayed in the playback interface, and the video is edited based on the event indication information and the editing control.

[0093] See also Fig. 9 , Fig. 9It is a schematic diagram of video editing provided in an embodiment of the present application. When a user triggers a video generation control 901, the terminal responds to the trigger operation, obtains the historical live video, and displays the playback interface of the historical live video. Event indication information 902 (corresponding to three target events, namely target event A to target event C) and editing control 903 are displayed in the playback interface, wherein the event indication information 902 is used to indicate the existence of a corresponding target event in the historical live video, and the editing control 903 is used to edit a video clip corresponding to the target event from the historical live video. In response to the video editing operation triggered by the editing control 903, a video clip corresponding to the target event is edited from the historical live video.

[0094] In some embodiments, the terminal may display event indication information in the playback interface in the following manner: when the number of target events is at least two, obtaining an influencing parameter for influencing the editing priority of the target event, wherein the influencing parameter includes at least one of the following: virtual character data associated with the target event, the event type to which the target event belongs, and historical editing data corresponding to the target event; determining the editing priority of each target event based on the influencing parameter, and displaying the event indication information corresponding to each target event in the playback interface using a display style corresponding to the editing priority.

[0095] Here, when there are multiple target events, the editing priorities corresponding to different target events may be different. According to the editing priority corresponding to the target event, the event indication information corresponding to each target event may be displayed in a corresponding display style, that is, for target events with different editing priorities, different display styles (such as different display colors, different display brightness, different display fonts, etc.) are used to display the event indication information corresponding to each target event, or the event indication information corresponding to the target event with a higher editing priority is highlighted. For example, there are three target events in the historical live video, namely, target event 1, target event 2 and target event 3. The editing priorities corresponding to these three target events decrease in sequence. The event indication information corresponding to target event 1 may be displayed in red font, the event indication information corresponding to target event 2 may be displayed in yellow font, and the event indication information corresponding to target event 3 may be displayed in gray font. This facilitates users to edit the historical live video based on the event indication information corresponding to the required target event to obtain the video clip corresponding to the required target event, which is conducive to improving the pertinence and efficiency of the generation of video clips.

[0096] In actual implementation, the editing priority of the target event can be determined through the following processing: obtaining the influencing parameters for influencing the editing priority of the target event, and based on the influencing parameters, calling the neural network model to perform editing priority prediction processing to obtain the editing priority of the target event; wherein the neural network model is trained through event samples, the influencing parameters corresponding to the event samples, and the editing priorities annotated by the event samples.

[0097] Taking the target scene as a game, for example, the virtual character data associated with the target event can be the relevant data of the specific character in the target scene corresponding to the current account, such as the virtual character data can be the game character type of the current account in the game (such as an offensive game character or a defensive game character), the game character level, the game character's proficiency in skills and other data; the event type to which the target event belongs refers to the attribute classification corresponding to the target event, such as N-kill events, high-performance skill use events, etc.; the historical editing data corresponding to the target event refers to the generation volume, forwarding interaction volume, etc. of the video clips corresponding to the target event obtained by the current account or other accounts different from the current account. After obtaining the influencing parameters for influencing the editing priority of the target event, the first neural network model trained with the influencing parameters is used for prediction processing to obtain the editing priority of the target event, which can make the prediction more accurate.

[0098] Before applying the first neural network model, it is necessary to train the initial first neural network model, and then put the trained first neural network model into use to realize the prediction of the editing priority of the target event by combining the influencing parameters through artificial intelligence technology. Among them, the first neural network model is trained by event samples, influencing parameters corresponding to the event samples, and editing priorities annotated by the event samples. For example, based on the event samples, the virtual character data associated with the event samples, and the editing priorities annotated by the event samples, the initial first neural network model is called for prediction processing to obtain the predicted editing priority. After determining the value of the loss function of the first neural network model through the predicted editing priority and the annotated editing priority, it can be determined whether the value of the loss function exceeds the preset threshold. When the value of the loss function exceeds the preset threshold, the error signal of the first neural network model is determined based on the loss function, the error information is back-propagated in the first neural network model, and the model parameters of each layer are updated during the propagation process.

[0099] In some embodiments, the terminal may display a clip control in the playback interface in the following manner: display a corresponding clip control at the associated position of each event indication information in the playback interface, wherein there is a one-to-one correspondence between the clip control and the target event; correspondingly, the terminal may respond to a video clip operation triggered by the clip control in the following manner to obtain a video clip corresponding to the target event from a historical live video: respond to a video clip operation triggered by a selected clip control to obtain a video clip corresponding to the target event corresponding to the selected clip control from the historical live video.

[0100] See also Fig.10 , Fig.10 This is a schematic diagram of video editing provided in an embodiment of the present application. When there are multiple target events, a corresponding editing control is displayed at the associated position of the event indication information of each target event, that is, one target event corresponds to one editing control, such as target event 1 corresponds to editing control 1, and editing control 1 is displayed at the associated position of event indication information 1001 corresponding to target event 1, editing control 2 is displayed at the associated position of event indication information 1002 corresponding to target event 2, and editing control 3 is displayed at the associated position of event indication information 1003 corresponding to target event 3. Users can choose to edit the video clip corresponding to a specific target event. For example, when the user selects editing control 1, the terminal receives a video editing operation for target event 1, and edits the video clip corresponding to target event 1 from the historical live video. In this way, users can conveniently edit the video clip of the selected specific target event according to actual needs, thereby improving the flexibility of video editing.

[0101] In some embodiments, the terminal can respond to the video editing operation triggered by the editing control in the following manner to obtain a video clip corresponding to the target event from the historical live video: when the number of target events is multiple, the editing control corresponds to multiple target events; in response to the triggering operation on the editing control, the event indication information corresponding to each target event is controlled to be in an operational state; in response to the event indication information selection operation, the video clip corresponding to the target event corresponding to the selected event indication information is clipped from the historical live video.

[0102] See also Fig.11 , Fig.111 is a schematic diagram of video editing provided by an embodiment of the present application. When there are multiple target events, event indication information corresponding to each target event and editing controls corresponding to all target events (i.e., one editing control corresponds to multiple target events) are displayed, such as event indication information 1101 corresponding to target event 1, event indication information 1102 corresponding to target event 2, and event indication information 1103 corresponding to target event 3. Target events 1 to 3 correspond to the same editing control 1104. When a user triggers editing control 1104, the terminal responds to the triggering operation and controls event indication information 1101 to event indication information 1103 to be in an operable state. The user can edit the video clip corresponding to a specific target event by selecting the event indication information. For example, when the user selects event indication information 1102, the terminal responds to the event indication information selection operation, receives a video editing operation for target event 2, and responds to the video editing operation to edit the video clip corresponding to target event 2 from the historical live video. In this way, the user can conveniently edit the video clip of the selected specific target event according to actual needs, thereby improving the flexibility of video editing.

[0103] In some embodiments, the terminal may determine the live broadcast interaction information associated with the video clip in the following manner: when the number of live broadcast interaction information associated with the video clip is multiple, obtain an influencing parameter for influencing the selection priority of the live broadcast interaction information; wherein the influencing parameter includes at least one of the following: the correlation between the live broadcast interaction information and the video clip, the account data of the interactive account corresponding to the live broadcast interaction information, and the category of the live broadcast interaction information; based on the influencing parameter, determine the selection priority of each live broadcast interaction information, and obtain the live broadcast interaction information with a selection priority higher than the priority threshold from multiple live broadcast interaction information.

[0104] Here, when there are multiple live interactive information associated with the video clip corresponding to the target event, the terminal can first intelligently determine the selection priority of each live interactive information, and filter out the target number of live interactive information with a higher selection priority (such as a selection priority higher than the priority threshold) as the live interactive information required for video editing.

[0105] When determining the selection priority of live interactive information, the correlation between the live interactive information and the video clip in the influencing parameters refers to the relevance or relevance between the live interactive information and the video clip (or target event). Generally, when other influencing parameters are fixed, the higher the correlation, the higher the selection priority of the corresponding live interactive information; the account data of the interactive account corresponding to the live interactive information (i.e., the account sending the live interactive information) refers to the account level of the interactive account, historical interactive data (such as the frequency of the interactive account sending live interactive data in history, the number of edited videos, and the number of forwardings for the edited videos, etc.); the categories of live interactive information include but are not limited to: text, emoticons, virtual gifts, etc.; after obtaining the influencing parameters for influencing the selection priority of the live interactive information, the second neural network model trained with the influencing parameters can be used for prediction processing to obtain the selection priority of the live interactive information, which can make the prediction more accurate.

[0106] Before applying the second neural network model, it is necessary to train the initial second neural network model, and then put the trained second neural network model into use to realize the combination of influencing parameters and predict the selection priority of live interactive information through artificial intelligence technology. Among them, the neural network model is trained through live interactive information samples, influencing parameters corresponding to live interactive information samples, and selection priorities annotated by live interactive information samples. For example, based on live interactive information samples, categories of event live interactive information samples, and selection priorities annotated by live interactive information samples, the initial second neural network model is called for prediction processing to obtain the predicted selection priority. After determining the value of the loss function of the second neural network model through the predicted selection priority and the annotated selection priority, it can be determined whether the value of the loss function exceeds the preset threshold. When the value of the loss function exceeds the preset threshold, the error signal of the second neural network model is determined based on the loss function, the error information is back-propagated in the second neural network model, and the model parameters of each layer are updated during the propagation process.

[0107] Among them, the embodiments of the present application do not limit the model structure of the neural network model (including the first neural network model and the second neural network model mentioned above). For example, the neural network model can be a convolutional neural network, a deep neural network, etc.; it is not limited to the form of the loss function, for example, it can be a cross entropy loss function, an L2 loss function, etc.

[0108] Here, back propagation is explained. The training sample data is input into the input layer of the neural network model, passes through the hidden layer, and finally reaches the output layer and outputs the result. This is the forward propagation process of the neural network model. Since there is an error between the output result of the neural network model and the actual result, the error between the output result and the actual value is calculated, and the error is backpropagated from the output layer to the hidden layer until it propagates to the input layer. In the process of back propagation, the value of the model parameter is adjusted according to the error, that is, the loss function is constructed according to the error between the output result and the actual value, and the partial derivatives of the loss function with respect to the model parameters are calculated layer by layer to generate the gradient of the loss function with respect to the model parameters of each layer. Since the direction of the gradient indicates the direction of error expansion, the gradient of the model parameters is inverted and summed with the original parameters of each layer model. The summed result is used as the updated model parameters of each layer, thereby reducing the error caused by the model parameters, and the above process is continuously iterated until convergence.

[0109] In some embodiments, the terminal may combine the video clips with the live interactive information to generate a target video corresponding to the target event in the following manner: when the number of video clips corresponding to the target event is multiple and the multiple video clips are discontinuous, respectively combine each video clip with the associated live interactive information to generate multiple corresponding combined videos; and splice the multiple combined videos to generate a target video corresponding to the target event.

[0110] Here, when there are multiple discontinuous video clips corresponding to the same target event, each video clip can be combined with the corresponding live interactive information to obtain multiple corresponding combined videos, and the multiple combined videos can be spliced ​​together to use the spliced ​​video as the target video corresponding to the target event. For example, when the target event corresponds to three discontinuous video clips (such as video clip 1, video clip 2, and video clip 3) in the same live broadcast, video clip 1 is combined with the corresponding live interactive information 1 to obtain combined video 1, video clip 2 is combined with the corresponding live interactive information 2 to obtain combined video 2, video clip 3 is combined with the corresponding live interactive information 3 to obtain combined video 3, combined video 1, combined video 2, and combined video 3 are spliced ​​together to obtain a spliced ​​video, and the spliced ​​video is used as the target video corresponding to the target event.

[0111] In some embodiments, the terminal may combine the video clips with the live interactive information to generate a target video corresponding to the target event in the following manner: when there are multiple types of target events, the video clips corresponding to each type of target event are combined with the associated live interactive information to generate a target video corresponding to each type of target event; accordingly, the terminal may splice the target videos corresponding to each type of target event in the order in which the target event appears in the live broadcast of the target scene to generate a video corresponding to the target scene.

[0112] Here, when there are multiple types of target events, that is, there are multiple different types of target events (such as target event 1 and target event 2), the video clip 1 corresponding to the target event 1 is combined with the live interactive information 1 associated with the video clip 1 to generate the target video 1 corresponding to the target event 1, and the video clip 2 corresponding to the target event 2 is combined with the live interactive information 2 associated with the video clip 2 to generate the target video 2 corresponding to the target event 2, and finally the target video 1 corresponding to the target event 1 and the target video 2 corresponding to the target event 2 are spliced ​​to obtain the video corresponding to the target scene. It should be noted that after obtaining the target videos corresponding to each type of target event, the target videos corresponding to each type of target event can also be combined to obtain a video set including multiple target videos as the video corresponding to the target scene, such as combining the above-mentioned target video 1 and target video 2 to obtain the video set {target video 1, target video 2}.

[0113] In some embodiments, the terminal may combine the video clips corresponding to each type of target event with the associated live interactive information to generate target videos corresponding to each type of target event in the following manner: when there are multiple video clips corresponding to each type of target event, combine each video clip corresponding to each type of target event with the associated live interactive information to generate multiple combined videos corresponding to each type of target event; splice the multiple combined videos corresponding to each type of target event to generate the target video corresponding to each type of target event.

[0114] Here, when there are multiple types of target events and each target event has multiple corresponding video clips, such as target event 1 corresponds to video clips 1 to 3, and target event 2 corresponds to video clips 4 to 5, for target event 1, video clip 1 is combined with the corresponding live interactive information 1 to obtain combined video 1, video clip 2 is combined with the corresponding live interactive information 2 to obtain combined video 2, video clip 3 is combined with the corresponding live interactive information 3 to obtain combined video 3, and combined video 1, combined video 2 and combined video 3 are spliced ​​to obtain the target video corresponding to target event 1; similarly, for target event 2, video clip 4 is combined with the corresponding live interactive information 4 to obtain combined video 4, video clip 5 is combined with the corresponding live interactive information 5 to obtain combined video 5, and combined video 4 and combined video 5 are spliced ​​to obtain the target video corresponding to target event 2.

[0115] In some embodiments, after the terminal generates a target video corresponding to a target event, in response to a preview operation on the target video, the terminal plays the video content of the video clip in the preview interface of the target video, and during the playback of the video content, displays live interactive information that is associated with the video content.

[0116] Here, after generating the target video corresponding to the target event, the generated target video can be displayed in the live broadcast recording interface or the preview control corresponding to the target video can be displayed in the live broadcast recording interface. In response to the playback operation for the target video, the target video is played. During the playback process, the video content of the video clip associated with the target event and the live broadcast interactive information are displayed.

[0117] See also Fig.12 , Fig.12 This is a schematic diagram of video playback provided in an embodiment of the present application, in which a preview control 1201 is displayed in a live broadcast recording interface, and in response to a preview operation for a target video triggered based on the preview control 1201, the target video is played, that is, while displaying the video content of the video clip in the preview interface or the playback interface of the target video, live broadcast interactive information (such as barrage 1 and barrage 2) that is associated with the video content is displayed.

[0118] In addition, after generating the target video corresponding to the target event, you can also share the target video, such as sharing the target video to the terminal corresponding to other accounts, or publishing and sharing the target video on social platforms. Fig.13 , Fig.13 This is a video sharing schematic diagram provided in an embodiment of the present application. After the target video is generated, the target video can be exported from the live broadcast platform and saved to the system album. After the export is completed, it can automatically jump to the social platform A for publishing and sharing.

[0119] The following will describe an exemplary application of the embodiment of the present application in an actual application scenario. Take the target scenario as a game and the target event as a highlight moment event as an example. Fig.14 , Fig.14 : is a flow chart of a video processing method based on live broadcast provided in an embodiment of the present application, the method comprising:

[0120] Step 201: The live broadcast platform sends a binding request to the live broadcast center.

[0121] The binding request is used to request to establish a binding relationship between the live broadcast account and the game account corresponding to the target game.

[0122] In actual applications, before users broadcast games through a client with a live broadcast function in the terminal (such as a live broadcast platform), they must first establish a binding relationship between the live broadcast account on the live broadcast platform and the game account on the game side. The live broadcast platform has developed a game account binding intermediate page, which is called up by the anchor on the live broadcast platform. If the live broadcast platform sends the binding request triggered by the anchor to the live broadcast platform, the live broadcast platform will authorize the binding of the live broadcast account and the game account.

[0123] Step 202: The live broadcast platform responds to the binding request, establishes a binding relationship between the live broadcast account and the game account corresponding to the target game, and returns the established binding relationship to the live broadcast platform.

[0124] Since the binding request carries the live broadcast account corresponding to the anchor to be bound and the game account of the target game, that is, the live broadcast platform transmits the anchor's live broadcast account on the live broadcast platform side to the account binding intermediate page of the live broadcast middle station. At this point, the account binding intermediate page of the live broadcast middle station has the relevant information of the live broadcast platform. When the live broadcast middle station receives the binding request sent by the live broadcast platform, it responds to the binding request, establishes a binding relationship between the live broadcast account and the game account corresponding to the target game, and implements the mapping relationship between the anchor's live broadcast account on the live broadcast platform and the game account in the target game to the live broadcast middle station.

[0125] After the live broadcast center binds the anchor and the target game (that is, establishes a binding relationship between the live broadcast account and the game account corresponding to the target game), the established binding relationship is returned to the live broadcast platform. After the live broadcast platform receives the binding relationship, it can obtain the live broadcast information related to the target game based on the binding relationship.

[0126] Step 203: The live broadcast platform sends an information acquisition request to the live broadcast center.

[0127] The information acquisition request is used to request to obtain the match list information (ie, the live broadcast record information) of the target game within a preset time period (eg, the last 7 days).

[0128] Step 204: The live broadcast center sends an information acquisition request to the game side.

[0129] Among them, the information acquisition request carries the live broadcast account. The live broadcast middle platform determines the game account of the target game that has a binding relationship with the live broadcast account based on the binding relationship, and forwards the information acquisition request to the game side, and obtains the game list information related to the game account of the target game that has a binding relationship with the live broadcast account through the game side.

[0130] Step 205: The game side obtains the match list information of the target game based on the information acquisition request, and returns the match list information of the target game to the live broadcast center.

[0131] Step 206: The live broadcast center sends the match list information of the target game to the live broadcast platform.

[0132] Step 207: The live broadcast platform displays the match list information of the target game on the live broadcast record interface.

[0133] Through the above method, the live broadcast platform obtains the match list information of the target game on the game side through the live broadcast center, and displays the match list information in the live broadcast record interface of the live broadcast platform, wherein the match list information includes the live broadcast record information of at least one game match:.

[0134] In addition, a video generation control can be displayed next to the live broadcast record information of each game match. The anchor can understand the corresponding performance of each game match (or each live broadcast session) of the target game according to the match list information (such as success or failure?), and can generate a video of the highlight moment event of a game match through the video generation control corresponding to a game match according to needs, such as Figure 4 shown.

[0135] Step 208: The live broadcast platform sends a video editing request to the live broadcast platform in response to the triggering operation of the video generation control corresponding to the target game match.

[0136] Here, when the anchor wants to generate a video corresponding to a highlight moment event in the target game match, the video generation control corresponding to the target game match can be triggered. The live broadcast platform responds to the trigger operation of the video generation control corresponding to the target game match, generates and sends a video editing request to the live broadcast center, requesting to edit the video corresponding to the highlight moment event in the target game match.

[0137] Step 209: The live broadcast center forwards the video editing request to the game side.

[0138] Step 210: Based on the video editing request, the game side generates a video clip corresponding to the highlight moment event, and returns the video clip to the live broadcast center.

[0139] Here, when there is live broadcast data corresponding to a highlight moment event in the historical live broadcast data of the target game game, the game side extracts the live broadcast data corresponding to the highlight moment event from the historical live broadcast data of the target game game, and generates a clipped video corresponding to the highlight moment event (i.e., the above-mentioned target video) based on the live broadcast data corresponding to the highlight moment event; or, when the game side recognizes that there is live broadcast data corresponding to a highlight moment event in the historical live broadcast data of the target game game, it captures a video clip corresponding to the live broadcast data of the highlight moment event from the recorded historical live video to obtain the clipped video corresponding to the highlight moment event.

[0140] It is understandable that the live broadcast data corresponding to the highlight moment event may include the game content data and live broadcast interaction data (such as barrage, virtual gifts, etc.) of the highlight moment event, so the video content of the above-mentioned edited video may also include the game content data and live broadcast interaction data of the highlight moment event.

[0141] Step 211: The live broadcast center sends the edited video to the live broadcast platform.

[0142] Through the above method, the game side automatically generates edited videos corresponding to highlight moment events, realizing intelligent and efficient video editing.

[0143] In actual applications, multiple video templates can be pre-set for users to use when editing videos. The anchor can use the video templates to edit and generate edited videos corresponding to highlight moment events in the live broadcast platform. For example, the anchor triggers the video generation control corresponding to the target game match, and the live broadcast platform responds to the trigger operation and displays a video template interface, wherein the video template interface includes multiple selectable video templates, such as video template 1 (such as a template corresponding to the highlight moment event of N consecutive kills) and video template 2 (such as a template corresponding to the highlight moment event of 100% instant kill). In response to the selection operation for the target video template (such as video template 1), a video editing request is sent to the live broadcast center, wherein the video editing request is used to request the editing of the edited video corresponding to video template 1 (i.e., the edited video corresponding to the N consecutive kill event).

[0144] The live broadcast center sends a video editing request to the game side. The game side responds to the video editing request. When it is identified that there is live broadcast data corresponding to the target video template (i.e., N consecutive kill events) in the historical live broadcast data of the target game game, the game side extracts the live broadcast data corresponding to the target video template (i.e., N consecutive kill events) from the historical live broadcast data of the target game game, and returns the extracted live broadcast data corresponding to the target video template (i.e., N consecutive kill events) to the live broadcast platform through the live broadcast center. The live broadcast platform inserts the live broadcast data corresponding to the target video template (i.e., N consecutive kill events) into the target video template to generate a video clip corresponding to the target video template (i.e., N consecutive kill events).

[0145] In addition, the live broadcast platform inserts the live broadcast data corresponding to the target video template (i.e., the N-kill streak event) into the target video template, and may first generate an initial video clip (i.e., the pre-processed clip mentioned above). The target video template may include editing controls for editing the pre-processed clip, such as subtitle controls, special effects controls, sound effects controls, and texture controls. Video editing parameters such as subtitles, special effects, sound effects, and textures may be edited in the target video template through the editing controls. In response to the video editing operation, the pre-processed clip may be edited according to the video editing parameters to obtain a video clip corresponding to the target event. For example, the video editing parameters of at least one of the subtitle special effects, sound effects, and textures are added to the pre-processed clip, and the clip after the pre-processed clip is edited is used as the video clip corresponding to the target video template (i.e., the N-kill streak event). For details, see Figure 6 In this way, users can conveniently edit the pre-processed clips according to actual needs to obtain the desired video clips, which improves the flexibility and richness of video editing.

[0146] In addition, the target video template can also display interactive controls for obtaining live interactive information ( Figure 7 In the synchronized live broadcast information in the target video template, in response to the trigger operation on the interactive control, the live broadcast interaction data of the time period corresponding to the highlight moment event in the live broadcast process is obtained, such as the number of likes, comment data, virtual gift swiping data, etc., and the live broadcast interaction information is displayed in the information editing area. When the user triggers the "Done" confirmation button, the terminal responds to the trigger operation, combines the video clip and the live broadcast interaction information in the target video template, and uses the combined video as the edited video corresponding to the highlight moment event (that is, the target video mentioned above); in addition, the live broadcast platform can further edit the obtained live broadcast interaction information in the information editing area of ​​the target video template, and edit the live broadcast interaction information displayed in the information editing area in response to the information editing operation, such as editing, modifying or deleting the live broadcast interaction information, to obtain the edited live broadcast interaction information, so as to combine the edited live broadcast interaction information with the video clip.

[0147] Through the above method, users can select the game match of the video they want to edit according to their editing needs. After selecting the game match, they can select a video template for self-editing according to their editing needs, and perform secondary editing on the edited video based on the selected video template, thereby improving the flexibility of video editing.

[0148] It should be noted that after the game side obtains the above-mentioned target game's match list information, video clips, live broadcast data corresponding to the target video template (i.e., N-kill streak event) and other related information, it notifies the live broadcast center through a callback, and the live broadcast center transmits the corresponding information to the live broadcast platform. If the game side fails to notify, the live broadcast center can send an alarm prompt message to the live broadcast platform, so that users on the live broadcast platform can perceive the failure of information acquisition in advance.

[0149] In actual applications, after generating a target video corresponding to a highlight moment event, the target video can also be shared, such as sharing the target video to terminals corresponding to other accounts, or publishing and sharing the target video on a social platform.

[0150] Through the above method, the game match information and game match situation of each live broadcast session are displayed in the game match list, so that the game match record can be checked, which is convenient for users to quickly locate the relevant games of the highlight moment event, and then generate a clip of the highlight moment in the corresponding game game according to the located game, so that the video editing is more targeted and accurate; in addition, according to the highlight moment triggered by the relevant game, the effective historical live broadcast data can be quickly obtained, the data utilization rate is high, the video editing efficiency can be improved, and the game materials required for video editing are relatively complete, and it is not easy to miss any clips worth recording in the game, which meets the flexibility and diversity of video editing.

[0151] So far, the live broadcast-based video processing method provided by the embodiment of the present application has been described in combination with the exemplary application and implementation of the electronic device provided by the embodiment of the present application. The following will continue to describe how the various modules in the live broadcast-based video processing device 555 provided by the embodiment of the present application cooperate to implement the live broadcast-based video processing solution.

[0152] The control display module 5551 is used to display the video generation control corresponding to the target scene in the live broadcast recording interface, and the video generation control is used to generate the video of the corresponding target event according to the historical live broadcast data of the target scene; the video generation module 5552 is used to respond to the trigger operation of the video generation control, when there is live broadcast data corresponding to the target event in the historical live broadcast data, determine the video segment corresponding to the target event and the live broadcast interaction information associated with the video segment, and combine the video segment with the live broadcast interaction information to generate the target video corresponding to the target event.

[0153] In some embodiments, after generating the target video corresponding to the target event, the device also includes: a video preview module, which is used to respond to the preview operation on the target video, play the video content of the video clip in the preview interface of the target video, and display the live interactive information that is associated with the video content during the playback of the video content.

[0154] In some embodiments, the video generation module is also used to display at least one video template for selection in response to a trigger operation on the video generation control; in response to a selection operation on a target video template, when there is live broadcast data corresponding to a target event indicated by the target video template in the historical live broadcast data, the live broadcast data is nested into the target video template to generate a video clip corresponding to the target event.

[0155] In some embodiments, the video generation module is also used to embed the live broadcast data into the target video template to generate a pre-processed segment; in response to a video parameter editing operation, the video editing parameters are displayed in the target video template, and the video editing parameters include at least one of the following: subtitles, special effects, sound effects, and textures; in response to the video editing operation, the pre-processed segment is edited according to the video editing parameters to obtain a video segment corresponding to the target event.

[0156] In some embodiments, the video generation module is also used to display an interactive control for obtaining live interactive information in the target video template; in response to a trigger operation on the interactive control, obtain the live interactive information associated with the video clip, and display the live interactive information in the information editing area in the target video template; wherein the display position of the live interactive information in the information editing area corresponds to the time period of the live interactive information corresponding to the video clip; in response to a determination operation on the live interactive information, combine the video clip and the live interactive information in the target video template to generate a target video corresponding to the target event.

[0157] In some embodiments, the video generation module is also used to display an information filtering condition setting interface in response to a trigger operation on the interactive control; to display the set information filtering conditions in response to a filtering condition setting operation triggered based on the information filtering condition setting interface; and to obtain live interactive information that meets the information filtering conditions and has an associated relationship with the video clip in response to a live interactive information acquisition operation.

[0158] In some embodiments, after the live broadcast interaction information is displayed in the information editing area in the target video template, the device also includes: an information editing module, which is used to edit the live broadcast interaction information displayed in the information editing area in response to the information editing operation to obtain the edited live broadcast interaction information, so as to combine the edited live broadcast interaction information with the video clip.

[0159] In some embodiments, the video generation module is also used to display the playback interface of the historical live video corresponding to the target scene in response to a trigger operation on the video generation control, and to display event indication information and a clipping control in the playback interface; wherein the event indication information is used to indicate that there is live data corresponding to the target event in the historical live data corresponding to the historical live video, and the clipping control is used to clip at least one video clip from the historical live video; in response to a video clipping operation triggered based on the clipping control, a video clip corresponding to the target event is clipped from the historical live video.

[0160] In some embodiments, the video generation module is also used to obtain influencing parameters for influencing the editing priority of the target events when the number of the target events is at least two, wherein the influencing parameters include at least one of the following: virtual character data associated with the target event, the event type to which the target event belongs, and historical editing data corresponding to the target event; the editing priority of each of the target events is determined based on the influencing parameters, and in the playback interface, the event indication information corresponding to each of the target events is displayed in a display style corresponding to the editing priority.

[0161] In some embodiments, the video generation module is also used to display corresponding editing controls at the associated positions of each event indication information in the playback interface, and there is a one-to-one correspondence between the editing controls and the target events; in response to a video editing operation triggered based on the selected editing control, a video clip corresponding to the target event corresponding to the selected editing control is edited from the historical live video.

[0162] In some embodiments, the video generation module is also used for, when there are multiple target events, the clip control corresponds to the multiple target events; in response to a trigger operation on the clip control, controlling the event indication information corresponding to each of the target events to be in an operable state; in response to an event indication information selection operation, clipping from the historical live video a video clip corresponding to the target event corresponding to the selected event indication information.

[0163] In some embodiments, the video generation module is also used to obtain influencing parameters for influencing the selection priority of the live interaction information when there are multiple live interaction information associated with the video clip; wherein the influencing parameters include at least one of the following: the correlation between the live interaction information and the video clip, the account data of the interactive account corresponding to the live interaction information, and the category of the live interaction information; based on the influencing parameters, the selection priority of each of the live interaction information is determined, and the live interaction information with a selection priority higher than the priority threshold is obtained from the multiple live interaction information.

[0164] In some embodiments, the video generation module is also used to, when there are multiple video clips corresponding to the target event and the multiple video clips are discontinuous, respectively combine each of the video clips with the associated live interactive information to generate a corresponding multiple combined videos; and splice the multiple combined videos to generate a target video corresponding to the target event.

[0165] In some embodiments, the video generation module is also used to combine the video clips corresponding to each type of target event with the associated live interactive information to generate target videos corresponding to each type of target event when there are multiple types of target events; the device also includes: a video generation module, which is used to splice the target videos corresponding to each type of target event in the order of appearance of each type of target event in the live broadcast of the target scene, to generate a video corresponding to the target scene.

[0166] In some embodiments, the video generation module is also used to combine the video clips corresponding to each type of target event with the associated live interactive information to generate multiple combined videos corresponding to each type of target event when there are multiple video clips corresponding to each type of target event; and to splice the multiple combined videos corresponding to each type of target event to generate target videos corresponding to each type of target event.

[0167] In some embodiments, before determining the video segment corresponding to the target event, the device also includes: a live data screening module, which is used to match the constituent data of the target event with the historical live data, and when the matching degree between the historical live data and the constituent data exceeds a matching degree threshold, it is determined that there is live data corresponding to the target event in the historical live data; or, when the historical live data contains a target sentence for describing the target event, and the number of occurrences of the target sentence reaches a number threshold, it is determined that there is live data corresponding to the target event in the historical live data; or, when the historical live data includes live interaction data for the target scene, event recognition is performed on the live interaction data to obtain a corresponding recognition event, and when the recognition event is successfully compared with the target event, it is determined that there is live data corresponding to the target event in the historical live data.

[0168] The embodiment of the present application provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer-readable storage medium. The processor of the electronic device reads the computer executable instruction from the computer-readable storage medium, and the processor executes the computer executable instruction, so that the electronic device executes the video processing method based on live broadcast described in the embodiment of the present application.

[0169] The present application embodiment provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions or computer programs are stored. When the computer-executable instructions or computer programs are executed by a processor, the processor will be caused to execute the live video processing method provided by the present application embodiment, for example, Figure 3 A video processing method based on live broadcast is shown.

[0170] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0171] In some embodiments, computer executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0172] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file storing other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0173] As an example, computer executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0174] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A video processing method based on live broadcast, characterized in that: The method comprises: Displaying a video generation control corresponding to the target scene in the live broadcast recording interface, wherein the video generation control is used to generate a video corresponding to the target event based on the historical live broadcast data of the target scene; In response to a trigger operation on the video generation control, when there is live broadcast data corresponding to the target event in the historical live broadcast data, the video clip corresponding to the target event and the live broadcast interaction information associated with the video clip are determined, and the video clip is combined with the live broadcast interaction information to generate a target video corresponding to the target event.

2. The method according to claim 1, characterized in that After generating the target video corresponding to the target event, the method further includes: In response to a preview operation on the target video, the video content of the video clip is played in the preview interface of the target video, and During the playing of the video content, the live interactive information associated with the video content is displayed.

3. The method according to claim 1, characterized in that In response to the triggering operation on the video generation control, when there is live broadcast data corresponding to the target event in the historical live broadcast data, determining the video segment corresponding to the target event includes: In response to a trigger operation on the video generation control, displaying at least one video template for selection; In response to a selection operation on a target video template, when there is live data corresponding to a target event indicated by the target video template in the historical live data, the live data is nested into the target video template to generate a video clip corresponding to the target event.

4. The method according to claim 3, characterized in that The step of embedding the live broadcast data into the target video template to generate a video clip corresponding to the target event includes: Embedding the live broadcast data into the target video template to generate a pre-processed segment; In response to the video parameter editing operation, displaying the video editing parameters in the target video template, the video editing parameters including at least one of the following: subtitles, special effects, sound effects, and textures; In response to a video editing operation, the pre-processed segment is edited according to the video editing parameters to obtain a video segment corresponding to the target event.

5. The method according to claim 3, characterized in that The determining of the live interactive information associated with the video clip includes: Displaying an interactive control for obtaining live interactive information in the target video template; In response to a trigger operation on the interactive control, acquiring live interactive information associated with the video clip, and displaying the live interactive information in an information editing area in the target video template; Wherein, the display position of the live interactive information in the information editing area corresponds to the time period of the live interactive information corresponding to the video segment; The combining the video clip with the live interactive information to generate a target video corresponding to the target event includes: In response to a determination operation on the live interactive information, the video clip is combined with the live interactive information in the target video template to generate a target video corresponding to the target event.

6. The method according to claim 5, characterized in that The step of obtaining the live interactive information associated with the video clip in response to the triggering operation on the interactive control includes: In response to a trigger operation on the interactive control, displaying an information screening condition setting interface; In response to a screening condition setting operation triggered based on the information screening condition setting interface, displaying the set information screening condition; In response to the live interactive information acquisition operation, the live interactive information that meets the information screening condition and is associated with the video clip is acquired.

7. The method according to claim 5, characterized in that After the live interactive information is displayed in the information editing area in the target video template, the method further includes: In response to the information editing operation, the live interactive information displayed in the information editing area is edited to obtain the edited live interactive information, so as to combine the edited live interactive information with the video clip.

8. The method according to claim 1, characterized in that In response to the triggering operation on the video generation control, when there is live broadcast data corresponding to the target event in the historical live broadcast data, determining the video segment corresponding to the target event includes: In response to a trigger operation on the video generation control, a playback interface of the historical live video corresponding to the target scene is displayed, and event indication information and a clipping control are displayed in the playback interface; The event indication information is used to indicate that there is live data corresponding to the target event in the historical live data corresponding to the historical live video, and the clipping control is used to clip at least one video clip from the historical live video; In response to the video clipping operation triggered by the clipping control, a video clip corresponding to the target event is clipped from the historical live video.

9. The method according to claim 8, characterized in that The displaying of event indication information in the playback interface includes: When the number of the target events is at least two, obtaining an influencing parameter for influencing the editing priority of the target event, wherein the influencing parameter includes at least one of the following: virtual character data associated with the target event, an event type to which the target event belongs, and historical editing data corresponding to the target event; The editing priority of each of the target events is determined based on the influencing parameters, and event indication information corresponding to each of the target events is displayed in the playback interface using a display style corresponding to the editing priority.

10. The method according to claim 9, characterized in that Displaying clip controls in the playback interface includes: At the associated position of each event indication information in the playback interface, a corresponding clipping control is displayed, and there is a one-to-one correspondence between the clipping control and the target event; The step of responding to the video clipping operation triggered by the clipping control, clipping the video clip corresponding to the target event from the historical live video, includes: In response to the video editing operation triggered based on the selected editing control, a video clip corresponding to the target event corresponding to the selected editing control is edited from the historical live video.

11. The method according to claim 8, characterized in that The step of responding to the video clipping operation triggered by the clipping control, clipping the video clip corresponding to the target event from the historical live video, includes: When there are multiple target events, the clipping control corresponds to the multiple target events; In response to a trigger operation on the clip control, controlling the event indication information corresponding to each of the target events to be in an operable state; In response to the event indication information selection operation, a video clip corresponding to the target event corresponding to the selected event indication information is obtained by editing the historical live video.

12. The method according to claim 1, characterized in that The determining of the live interactive information associated with the video clip includes: When there are multiple live interactive information associated with the video clip, obtaining an influencing parameter for influencing the selection priority of the live interactive information; The influencing parameter includes at least one of the following: the correlation between the live interactive information and the video clip, the account data of the interactive account corresponding to the live interactive information, and the category of the live interactive information; Based on the influencing parameters, the selection priority of each of the live broadcast interaction information is determined, and the live broadcast interaction information having a selection priority higher than a priority threshold is obtained from the multiple live broadcast interaction information.

13. The method according to claim 1, characterized in that The combining the video clip with the live interactive information to generate a target video corresponding to the target event includes: When there are multiple video clips corresponding to the target event and the multiple video clips are discontinuous, each of the video clips is combined with the associated live interactive information to generate multiple corresponding combined videos; The multiple combined videos are spliced ​​together to generate a target video corresponding to the target event.

14. The method according to claim 1, wherein: The combining the video clip with the live interactive information to generate a target video corresponding to the target event includes: When there are multiple types of the target event, the video clips corresponding to each type of the target event are combined with the associated live interactive information to generate target videos corresponding to each type of the target event; The method further comprises: According to the order in which each type of the target event appears in the live broadcast of the target scene, the target videos corresponding to each type of the target event are spliced ​​to generate a video corresponding to the target scene.

15. The method according to claim 14, characterized in that The step of combining the video clips corresponding to each type of the target event with the associated live interactive information to generate a target video corresponding to each type of the target event includes: When there are multiple video clips corresponding to each type of target event, each video clip corresponding to each type of target event is combined with the associated live interactive information to generate multiple combined videos corresponding to each type of target event; Multiple combined videos corresponding to each type of the target event are spliced ​​together to generate target videos corresponding to each type of the target event.

16. The method according to claim 1, wherein: Before determining the video segment corresponding to the target event, the method further includes: Matching the component data of the target event with the historical live data, and when the matching degree between the historical live data and the component data exceeds a matching degree threshold, determining that there is live data corresponding to the target event in the historical live data; or, When the historical live broadcast data contains a target sentence for describing a target event, and the number of occurrences of the target sentence reaches a number threshold, it is determined that live broadcast data corresponding to the target event exists in the historical live broadcast data; or, When the historical live broadcast data includes live broadcast interaction data for the target scene, event recognition is performed on the live broadcast interaction data to obtain a corresponding recognition event, and when the recognition event is successfully compared with the target event, it is determined that there is live broadcast data corresponding to the target event in the historical live broadcast data.

17. A video processing device based on live broadcast, characterized in that: The device comprises: A control display module, used to display a video generation control corresponding to a target scene in a live broadcast recording interface, wherein the video generation control is used to generate a video corresponding to a target event based on historical live broadcast data of the target scene; A video generation module is used to respond to a trigger operation on the video generation control. When there is live broadcast data corresponding to the target event in the historical live broadcast data, determine the video segment corresponding to the target event and the live broadcast interaction information associated with the video segment, and combine the video segment with the live broadcast interaction information to generate a target video corresponding to the target event.

18. An electronic device, characterized in that: include: A memory for storing computer executable instructions or computer programs; The processor is used to implement the live broadcast-based video processing method described in any one of claims 1 to 16 when executing the computer executable instructions or computer programs stored in the memory.

19. A computer-readable storage medium, characterized in that: Computer executable instructions or computer programs are stored, and when the computer executable instructions or computer programs are executed by a processor, the live broadcast-based video processing method described in any one of claims 1 to 16 is implemented.

20. A computer program product comprising a computer program or computer executable instructions, characterized in that When the computer program or computer executable instructions are executed by a processor, the live broadcast-based video processing method described in any one of claims 1 to 16 is implemented.

Images