Video generation method and apparatus, and computer device and storage medium

Abstract

Provided in the present disclosure are a video generation method and apparatus, and a computer device and a storage medium. The method comprises: presenting a game scene picture during an ongoing game matchup of a target game, wherein the game scene picture includes a target virtual character (S101); in response to the occurrence of a target game event during the game matchup, acquiring candidate video clips associated with the target game event, wherein the candidate video clips comprise a plurality of game scene picture frames (S102); in response to a video generation condition being met, determining and selecting from among a plurality of candidate video clips a plurality of target video clips corresponding to a target event trigger sequence, wherein the target event trigger sequence is determined by means of an artificial intelligence model on the basis of video release data and / or game interaction data related to the target game (S103); and according to an event occurrence sequence indicated by the target event trigger sequence, integrating the plurality of target video clips, so as to generate a target video (S104). By means of the embodiments of the present disclosure, a target event trigger sequence can be determined more quickly and more accurately, and the time consumed by game video clip screening is shortened, thereby improving the generation efficiency of a highlight video.

Description

Video generation method, device, computer equipment and storage medium

[0001] This application claims priority to Chinese Patent Application No. 202311236384.2 filed on September 22, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] Embodiments of the present disclosure relate to a video generation method, apparatus, computer equipment, and storage medium. Background Art

[0003] In the field of online games, users can edit original game videos, turn exciting clips in the game that are easy to attract other users into highlight videos, and publish them to relevant platforms for other users to watch.

[0004] However, when editing original game videos, it is necessary to analyze and summarize them to identify the highlights that may attract other users and how to edit them. This process is usually time-consuming and cumbersome, and the efficiency of generating highlight videos is low.

[0005] Summary of the Invention

[0006] The embodiments of the present disclosure at least provide a video generation method, apparatus, computer equipment, and storage medium.

[0007] In a first aspect, an embodiment of the present disclosure provides a video generation method, comprising:

[0008] Displaying a game scene screen during a game match of the target game; the game scene screen includes a target virtual character;

[0009] In response to a target game event occurring in the game match, obtaining a candidate video segment associated with the target game event; the candidate video segment includes multiple frames of game scene images;

[0010] In response to satisfying the video generation condition, determining a plurality of target video segments corresponding to a target event trigger sequence from the plurality of candidate video segments; the target event trigger sequence is determined by the artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0011] The multiple target video clips are integrated according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

[0012] In an optional implementation, the method further includes:

[0013] During the game, hot event prompt information for the target virtual character is displayed; the hot event prompt information is used to indicate a variety of candidate hot events that can be used to generate a target video.

[0014] In an optional implementation, determining a plurality of target video segments corresponding to a target event triggering sequence from a plurality of candidate video segments includes:

[0015] Based on the plurality of candidate video clips, determining at least one preliminary event trigger sequence that matches the plurality of candidate video clips from a plurality of candidate event trigger sequences; the event trigger sequence includes a plurality of candidate hot events arranged in sequence; the plurality of candidate event trigger sequences are determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0016] displaying the at least one primary event triggering sequence;

[0017] In response to a user selecting a target event trigger sequence from the at least one initially selected event trigger sequence, a plurality of candidate video segments corresponding to the target event trigger sequence are used as the plurality of target video segments.

[0018] In an optional embodiment, presenting the at least one primary event triggering sequence includes:

[0019] Display at least one of the primary event trigger sequences and the interaction data corresponding to each of the primary event trigger sequences; the interaction data includes video publishing data and / or game interaction data; the interaction data is used as reference data for the user to select the target event trigger sequence.

[0020] In an optional implementation, determining a plurality of target video segments corresponding to a target event triggering sequence from a plurality of candidate video segments includes:

[0021] Based on the plurality of candidate video clips, determining at least one preliminary event trigger sequence that matches the plurality of candidate video clips from a plurality of candidate event trigger sequences; the event trigger sequence includes a plurality of candidate hot events arranged in sequence; the plurality of candidate event trigger sequences are determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0022] Determining interaction scores corresponding to the at least one preliminary event triggering sequence based on interaction data corresponding to the at least one preliminary event triggering sequence, wherein the interaction data includes video publishing data and / or game interaction data;

[0023] According to the interaction score, a target event trigger sequence is determined from the at least one preliminarily selected event trigger sequence, and a plurality of candidate video segments corresponding to the target event trigger sequence are used as the plurality of target video segments.

[0024] In an optional embodiment, the multiple candidate hot events are determined using an artificial intelligence model using the following steps:

[0025] Obtaining video publishing data related to the target game; the video publishing data includes each published video;

[0026] For each candidate virtual character associated with the target game, determining interaction data of a published video corresponding to each candidate virtual character, and determining at least one target virtual character from the candidate virtual characters based on the interaction data;

[0027] For each target virtual character, determining the number of times each game event is triggered by the target virtual character according to each published video corresponding to the target virtual character;

[0028] The game events whose corresponding triggering times exceed the first threshold are used as the candidate hotspot events.

[0029] In an optional embodiment, the candidate hot events are determined using an artificial intelligence model by using the following steps:

[0030] Obtaining video publishing data related to the target game; the video publishing data includes each published video;

[0031] Determine the triggering times of each game event based on each published video;

[0032] The game events whose corresponding triggering times exceed the second threshold are used as the candidate hotspot events.

[0033] In an optional embodiment, the candidate event trigger sequence is determined using an artificial intelligence model using the following steps:

[0034] The candidate event triggering sequence is determined according to the event triggering order of each candidate hot event in multiple published videos.

[0035] In a second aspect, an embodiment of the present disclosure further provides a video generation device, including:

[0036] A first display module is used to display a game scene screen during a game of the target game; the game scene screen includes a target virtual character;

[0037] an acquisition module, configured to acquire, in response to a target game event occurring in the game match, a candidate video segment associated with the target game event; the candidate video segment includes multiple frames of game scene images;

[0038] A first determination module is configured to determine, in response to satisfying a video generation condition, a plurality of target video segments corresponding to a target event trigger sequence from at least one of the candidate video segments; the target event trigger sequence is determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0039] The integration module is used to integrate the multiple target video clips according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

[0040] In a third aspect, an embodiment of the present disclosure further provides a computer device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect or any optional implementation of the first aspect are performed.

[0041] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any optional implementation of the first aspect are executed.

[0042] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0044] FIG1 shows a flow chart of a video generation method provided by an embodiment of the present disclosure;

[0045] FIG2 shows a flowchart of generating candidate video segments provided by an embodiment of the present disclosure;

[0046] FIG3 shows a schematic diagram of the distribution of virtual characters provided by an embodiment of the present disclosure;

[0047] FIG4 is a schematic diagram showing the triggering times of various game events at different times provided by an embodiment of the present disclosure;

[0048] FIG5 shows a flowchart of another video generation method provided by an embodiment of the present disclosure;

[0049] FIG6 shows a schematic structural diagram of a video generating device provided by an embodiment of the present disclosure; and

[0050] FIG7 shows a schematic diagram of a computer device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0052] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0053] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0054] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0055] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0056] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0057] Research has shown that editing raw game videos requires analyzing and summarizing them to identify the most appealing clips and arrange them in the right order. This process is typically manual, time-consuming, and tedious, resulting in low efficiency in generating highlight videos.

[0058] Based on this, the present disclosure provides a video generation method, including: displaying a game scene screen during a game match of a target game; the game scene screen includes a target virtual character; in response to a target game event occurring in the game match, obtaining a candidate video clip associated with the target game event; the candidate video clip includes multiple frames of game scene screen; in response to meeting a video generation condition, determining multiple target video clips corresponding to a target event trigger sequence from multiple candidate video clips; the target event trigger sequence is determined by an artificial intelligence model based on video release data and / or game interaction data related to the target game; and the multiple target video clips are integrated in the order of event occurrence indicated by the target event trigger sequence to generate a target video.

[0059] The above-mentioned video generation method provided by the embodiment of the present disclosure, after obtaining the candidate video clips associated with the target game event, is used to select the target video clips and the target event trigger sequence for integrating the target video clips in the editing stage of the video clips. It is determined based on the video release data and / or game interaction data related to the target game using an artificial intelligence model. Compared with the manual summary and analysis of the target game, the target event trigger sequence can be determined more quickly and accurately, the time consumed for screening game video clips is reduced, and the efficiency of generating highlight videos is improved.

[0060] The defects of the above solutions and the proposed solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0061] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0062] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0063] To facilitate understanding of this embodiment, a video generation method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the video generation method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities.

[0064] 1 , which is a flow chart of a video generation method provided by an embodiment of the present disclosure, the method includes S101 to S104 .

[0065] S101: Displaying a game scene screen during a game match of a target game; the game scene screen includes a target virtual character.

[0066] S102: In response to a target game event occurring in the game match, a candidate video segment associated with the target game event is obtained; the candidate video segment includes multiple frames of game scene images.

[0067] S103: In response to satisfying the video generation conditions, multiple target video segments corresponding to the target event trigger sequence are determined from at least one of the candidate video segments; the target event trigger sequence is determined by the artificial intelligence model based on the video publishing data and / or game interaction data related to the target game.

[0068] S104: Integrate the multiple target video clips according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

[0069] In the embodiment of the present disclosure, the target game may include a battle-type game, a competition-type game, etc.

[0070] At least one game match may occur in the target game. In each game match, at least one game event may occur, such as a kill event, a double kill event, an assist event, etc.

[0071] The target virtual character displayed in the game scene screen may include a virtual human character or other types of virtual characters.

[0072] In one embodiment, in response to the start of a game match for the target game, a game scene screen during the game match can be displayed.

[0073] In the disclosed embodiments, the target game event can be a game event in a hot event. In the disclosed embodiments, a target video can be generated for the target game event. Here, when the target game event occurs during a game match, a candidate video clip associated with the target game event can be obtained.

[0074] In a specific implementation, the candidate video clips can be obtained by intercepting video frames. The candidate video clips can include multiple frames of game scene images. The multiple frames of game scene images included in the candidate video clips can be associated with the target game event.

[0075] In one embodiment, all video frames associated with the target game event may be obtained. In another embodiment, a portion of the video frames associated with the target game event may also be obtained. These portions of the video frames may be selected at a preset time interval.

[0076] Figure 2 shows a flowchart for generating candidate video segments. After obtaining video frames (all video frames or part of the video frames) associated with target game events in the target game by intercepting video frames, the video frames and the target game can be input into the artificial intelligence model. The artificial intelligence model can obtain the moment information of the video frames in the target game based on the video frames and the target game, and then arrange the obtained video frames according to the moment information to obtain the corresponding candidate video segments.

[0077] In the embodiment of the present disclosure, illustratively, the video generation condition may include a user triggering a video generation operation, or may include the end of a game match.

[0078] For the case where the above-mentioned video generation conditions include a user-triggered video generation operation, in one embodiment, in response to satisfying the video generation conditions, determining and selecting multiple target video segments corresponding to the target event trigger sequence from at least one candidate video segment may include: in response to the user-triggered video generation operation, determining and selecting multiple target video segments corresponding to the target event trigger sequence from multiple candidate video segments.

[0079] In the above embodiment, the video generation operation can be triggered after the game game ends; it can also be triggered during the game game. For example, after the target game event occurs in the current game game and the candidate video clips are obtained, the user can trigger the video generation operation.

[0080] In a further embodiment, after obtaining candidate video clips associated with a target game event, video generation prompt information may be displayed. The video generation prompt information may be used to prompt the generation of a target video. In response to a confirmation operation on the video generation prompt information, multiple target video clips corresponding to the target event trigger sequence may be determined and selected from the multiple candidate video clips.

[0081] Alternatively, in a further embodiment, hot event prompt information for the target virtual character may be displayed during the game; the hot event prompt information is used to indicate a variety of candidate hot events that can be used to generate the target video.

[0082] In the above embodiment, after the target virtual character triggers a candidate hot event, hot event prompt information for the target virtual character can be displayed. By displaying this hot event prompt information, the user can promptly generate a target video containing the candidate hot event, meeting the user's video publishing needs for a specific hot event of a specific virtual character.

[0083] With respect to the case where the above-mentioned video generation conditions include the end of a game match, in one embodiment, in response to satisfying the video generation conditions, multiple target video segments corresponding to the target event trigger sequence are determined and selected from multiple candidate video segments. This may also include: in response to the end of a game match, multiple target video segments corresponding to the target event trigger sequence are determined and selected from multiple candidate video segments.

[0084] In the above embodiment, after the game is finished, multiple target video segments corresponding to the target event triggering sequence may be automatically determined and selected from multiple candidate video segments.

[0085] The above-mentioned target event trigger sequence can be determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game.

[0086] The video publishing data related to the target game may include published videos, popularity information of published videos, etc.; the game interaction data may include interaction data during the game, such as the number of team formations, etc.

[0087] The target event trigger sequence may include various hotspot events and the order in which events occur between the various hotspot events.

[0088] According to the event occurrence order indicated by the target event trigger sequence, the target video clips can be integrated to generate the target video.

[0089] The target event trigger sequence can be determined by the user. For example, the user can determine the occurrence order of multiple target game events according to his own wishes, so that in the subsequent process, the video clips associated with multiple target game events can be integrated according to the determined occurrence order to obtain the target video.

[0090] In one embodiment, determining multiple target video segments corresponding to the target event trigger sequence from multiple candidate video segments may include the following steps:

[0091] A1: Based on multiple candidate video clips, determine at least one preliminary event trigger sequence that matches the multiple candidate video clips from multiple candidate event trigger sequences; the event trigger sequence includes multiple candidate hot events arranged in sequence; the multiple candidate event trigger sequences are determined by the artificial intelligence model based on video release data and / or game interaction data related to the target game;

[0092] A2: Display at least one primary event trigger sequence;

[0093] A3: In response to a user selecting a target event trigger sequence from at least one initially selected event trigger sequence, a plurality of candidate video segments corresponding to the target event trigger sequence are used as a plurality of target video segments.

[0094] In the above embodiment, multiple candidate event triggering sequences can be determined based on the video publishing data and / or game interaction data related to the target game. Different candidate event triggering sequences may contain different candidate hot events and different event occurrence orders.

[0095] The preliminary event trigger sequence matching the multiple candidate video segments may include candidate hot events corresponding to the candidate video segments.

[0096] After displaying at least one preliminary event trigger sequence, the user can select a target event trigger sequence from the at least one preliminary event trigger sequence. In response to the target event trigger sequence selected by the user, multiple candidate video segments corresponding to the target event trigger sequence can be used as multiple target video segments.

[0097] In the above implementation, users can randomly select a target event trigger sequence based on their own preferences, or they can use relevant interaction data as a reference to select a target event trigger sequence that is more likely to generate a target video that is more likely to attract the attention of other users. Based on this, in a further implementation, displaying at least one preliminary event trigger sequence may include:

[0098] Display at least one preliminary event trigger sequence and the interaction data corresponding to each preliminary event trigger sequence; the interaction data includes video publishing data and / or game interaction data; the interaction data is used as reference data for users to select the target event trigger sequence.

[0099] For example, the video publishing data may include published videos and popularity information of the published videos, such as likes, comments, etc.; the game interaction data may include interaction data during the game, such as the number of team formations, etc.

[0100] Based on the above interaction data, users can refer to and select a target event trigger sequence that can generate a target video that is more likely to attract the attention of other users, thereby making the target event trigger sequence more popular with other users.

[0101] The target event trigger sequence may also be automatically determined, for example, based on the interaction data corresponding to each of the primary event trigger sequences.

[0102] In one embodiment, determining multiple target video segments corresponding to the target event triggering sequence from at least one candidate video segment may include:

[0103] B1: Based on at least one candidate video clip, determine at least one preliminary event trigger sequence that matches the at least one candidate video clip from multiple candidate event trigger sequences; the event trigger sequence includes multiple candidate hot events arranged in sequence; the candidate event trigger sequence is determined by the artificial intelligence model based on video release data and / or game interaction data related to the target game;

[0104] B2: Determine the interaction score corresponding to at least one preliminary event triggering sequence based on the interaction data corresponding to at least one preliminary event triggering sequence; the interaction data includes video publishing data and / or game interaction data.

[0105] B3: Determine a target event trigger sequence from at least one pre-selected event trigger sequence according to the interaction score, and use multiple candidate video segments corresponding to the target event trigger sequence as multiple target video segments.

[0106] In the above embodiment, step B1 is the same as step A1. For detailed description, please refer to the above text and will not be repeated here.

[0107] Different scores can be set for different interaction data. For example, different scores can be set for the popularity of released games included in video release data and for interaction data during the game.

[0108] Exemplarily, at least one preliminary event triggering sequence may be sorted according to the interaction score, and a preliminary event triggering sequence with the highest interaction score may be determined from the at least one preliminary event triggering sequence as the target event triggering sequence.

[0109] Through the above implementation, target event trigger sequences with high interaction popularity can be objectively screened out. The target video obtained according to the target event trigger sequences screened out in this way can more easily attract the attention of other users.

[0110] The following describes the process of determining candidate hotspot events and the process of determining candidate event trigger sequences.

[0111] In one embodiment, the candidate hot events may be determined using an artificial intelligence model. The artificial intelligence model may determine, based on video release data related to the target game, game events related to a target virtual character in the target game as candidate hot events. Alternatively, the artificial intelligence model may determine, without considering the target virtual character, game events that meet preset characteristics as candidate hot events.

[0112] Specifically, multiple candidate hot events can be determined using the artificial intelligence model by using the following steps:

[0113] C1: Obtain video publishing data related to the target game; the video publishing data includes each published video.

[0114] C2: For each candidate virtual character associated with the target game, determine the interaction data of the published video corresponding to each candidate virtual character, and determine at least one target virtual character from each candidate virtual character based on the interaction data.

[0115] C3: For each target virtual character, determine the number of times the target virtual character triggers each game event based on the published videos corresponding to the target virtual character.

[0116] C4: The game events whose corresponding triggering times exceed the first threshold are regarded as candidate hot events.

[0117] In the above embodiment, at least one candidate virtual character may be associated with the target game, and the published video corresponding to each candidate virtual character may include a game event triggered by the candidate virtual character.

[0118] Multiple candidate virtual characters associated with the target game may exist in the same published video or in different published videos.

[0119] The interaction data of the published video corresponding to each candidate virtual character may include interaction data such as the likes, views, and the number of times the candidate virtual character is used in the published video by other users. Based on the interaction data such as the likes and views of the published video by other users, the popularity information of the published video can be determined. The difficulty of controlling the candidate virtual character can be determined based on the number of times the candidate virtual character is used in the published video, and then the degree of attraction of the candidate virtual character to the user can be determined. Exemplarily, based on the interaction data, a target virtual character whose popularity information meets the first preset condition (such as the popularity exceeds a threshold) and the difficulty of controlling meets the second preset condition (such as the difficulty exceeds a threshold) can be selected from each candidate virtual character. As shown in Figure 3, the horizontal axis can represent the popularity information of the published video where each virtual character is located, and the vertical axis can represent the difficulty of controlling each virtual character. Based on the information represented by the horizontal and vertical axes, a target virtual character whose popularity information meets the first preset condition and the difficulty of controlling meets the second preset condition can be selected.

[0120] For each target virtual character, the number of times each target virtual character triggers each game event in the corresponding published video can be determined respectively.

[0121] A game event with a trigger count exceeding a first threshold may indicate that the game event has been triggered a large number of times. By using the corresponding game event with a trigger count exceeding the first threshold as a candidate hot event, a target event trigger sequence is subsequently selected from the event trigger sequence containing the candidate hot event, and a target video generated based on the target event trigger sequence is more likely to meet the user's attention.

[0122] In another embodiment, candidate hot events are determined using an artificial intelligence model using the following steps:

[0123] D1: Obtain video publishing data related to the target game; the video publishing data includes each published video;

[0124] D2: Determine the triggering times of each game event based on each published video;

[0125] D3: The game events whose corresponding triggering times exceed the second threshold are regarded as candidate hot events.

[0126] In the above embodiment, the triggering times of each game event determined based on each published video may be the sum of the triggering times obtained after each virtual character is triggered separately.

[0127] Here, virtual characters can be ignored, and game events corresponding to each game event with a triggering number exceeding the second threshold can be directly used as candidate hot events, so that a target event triggering sequence with a large number of triggering times corresponding to the corresponding game time can be selected from the event triggering sequence containing the above-mentioned candidate hot events. As shown in Figure 4, the horizontal axis can represent time, and the vertical axis can represent the number of triggers. Figure 4 contains the number of triggers corresponding to each game event at each moment. According to the number of triggers corresponding to each game event at each moment, the total number of triggers that occurred in the game match can be determined, and the game events with a corresponding total number of triggers exceeding the second threshold can be screened as candidate hot events. It should be understood here that the number of triggers corresponding to each game event at each moment in Figure 4 is only schematic.

[0128] The aforementioned candidate hot event trigger sequence can also be determined using an artificial intelligence model. In one embodiment, the candidate event trigger sequence can be determined based on the event triggering order of each candidate hot event in multiple published videos.

[0129] Here, the AI ​​model can output the game events that occurred at each moment. Based on the time information corresponding to each game event in the published video, the event triggering sequence between each game event can be determined, and then a candidate event triggering sequence can be obtained.

[0130] The embodiment of the present disclosure also provides a flowchart of another video generation method, as shown in FIG5 .

[0131] After entering a game, users can trigger the hotspot notification control to enable the hotspot notification feature. When a hot event occurs during a game, a hotspot notification message is displayed. This notification message indicates to the user that the current event is a hotspot event and can be used to generate a highlight video. After the user triggers a hotspot event, candidate video clips associated with the hotspot event are obtained. The process for obtaining candidate video clips can be found in the previous section and will not be repeated here.

[0132] After the game is over, the highlight video editing phase begins. This involves selecting multiple target video clips from a pool of candidate video clips that correspond to the target event trigger sequence. These target video clips are then combined in the order indicated by the target event trigger sequence to create a highlight video.

[0133] The user may trigger a highlight video publishing operation. In response to the highlight video publishing operation triggered by the user, the generated highlight video may be published.

[0134] The steps of determining and selecting multiple target video segments corresponding to the target event trigger sequence from multiple candidate video segments, and integrating the multiple target video segments according to the order of events indicated by the target event trigger sequence to generate a highlight video can be found in the previous text and will not be repeated here. In addition, in the disclosed embodiments, the target event trigger sequence is determined by the artificial intelligence model based on video release data and / or game interaction data related to the target game.

[0135] Through the above-mentioned implementation, during the editing stage of the video clips, the target event trigger sequence can be determined based on the video release data and / or game interaction data related to the target game using an artificial intelligence model. Compared with the manual summary and analysis of the target game, the target event trigger sequence can be determined more quickly, the time consumed is reduced, and the efficiency of generating highlight videos is improved.

[0136] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0137] Based on the same inventive concept, the embodiment of the present disclosure also provides a video generation device corresponding to the video generation method. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned video generation method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0138] 6 is a schematic diagram of a video generation device according to an embodiment of the present disclosure, wherein the device includes:

[0139] The first display module 601 is used to display a game scene screen during the game of the target game; the game scene screen includes a target virtual character;

[0140] An acquisition module 602 is configured to acquire, in response to a target game event occurring in the game match, a candidate video segment associated with the target game event; the candidate video segment includes multiple frames of game scene images;

[0141] A first determination module 603 is configured to determine, in response to satisfying a video generation condition, a plurality of target video segments corresponding to a target event trigger sequence from at least one of the candidate video segments; the target event trigger sequence is determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0142] The integration module 604 is configured to integrate the multiple target video clips according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

[0143] In an optional embodiment, the device further includes:

[0144] The second display module is used to display hot event prompt information for the target virtual character during the game match; the hot event prompt information is used to indicate a variety of candidate hot events that can be used to generate the target video.

[0145] In an optional implementation, the first determining module 603 is specifically configured to:

[0146] Based on the plurality of candidate video clips, determining at least one preliminary event trigger sequence that matches the plurality of candidate video clips from a plurality of candidate event trigger sequences; the event trigger sequence includes a plurality of candidate hot events arranged in sequence; the plurality of candidate event trigger sequences are determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0147] displaying the at least one primary event triggering sequence;

[0148] In response to a user selecting a target event trigger sequence from the at least one initially selected event trigger sequence, a plurality of candidate video segments corresponding to the target event trigger sequence are used as the plurality of target video segments.

[0149] In an optional implementation, the first determining module 603 is specifically configured to:

[0150] Display at least one of the primary event trigger sequences and the interaction data corresponding to each of the primary event trigger sequences; the interaction data includes video publishing data and / or game interaction data; the interaction data is used as reference data for the user to select the target event trigger sequence.

[0151] In an optional implementation, the first determining module 603 is specifically configured to:

[0152] Based on the plurality of candidate video clips, determining at least one preliminary event trigger sequence that matches the plurality of candidate video clips from a plurality of candidate event trigger sequences; the event trigger sequence includes a plurality of candidate hot events arranged in sequence; the plurality of candidate event trigger sequences are determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0153] Determining interaction scores corresponding to the at least one preliminary event triggering sequence based on interaction data corresponding to the at least one preliminary event triggering sequence, wherein the interaction data includes video publishing data and / or game interaction data;

[0154] According to the interaction score, a target event trigger sequence is determined from the at least one preliminarily selected event trigger sequence, and a plurality of candidate video segments corresponding to the target event trigger sequence are used as the plurality of target video segments.

[0155] In an optional embodiment, the device further includes:

[0156] The second determining module is configured to:

[0157] Obtaining video publishing data related to the target game; the video publishing data includes each published video;

[0158] For each candidate virtual character associated with the target game, determining interaction data of a published video corresponding to each candidate virtual character, and determining at least one target virtual character from the candidate virtual characters based on the interaction data;

[0159] For each target virtual character, determining the number of times each game event is triggered by the target virtual character according to each published video corresponding to the target virtual character;

[0160] The game events whose corresponding triggering times exceed the first threshold are used as the candidate hotspot events.

[0161] In an optional embodiment, the device further includes:

[0162] The third determining module is configured to:

[0163] Obtaining video publishing data related to the target game; the video publishing data includes each published video;

[0164] Determine the triggering times of each game event based on each published video;

[0165] The game events whose corresponding triggering times exceed the second threshold are used as the candidate hotspot events.

[0166] In an optional embodiment, the device further includes:

[0167] The fourth determining module is configured to:

[0168] The candidate event triggering sequence is determined according to the event triggering order of each candidate hot event in multiple published videos.

[0169] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0170] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Referring to Figure 7, it is a structural diagram of the computer device 700 provided in the embodiment of the present disclosure, including a processor 701, a memory 702, and a bus 703. Among them, the memory 702 is used to store execution instructions, including a memory 7021 and an external memory 7022; the memory 7021 here is also called an internal memory, which is used to temporarily store the calculation data in the processor 701, as well as the data exchanged with the external memory 7022 such as a hard disk. The processor 701 exchanges data with the external memory 7022 through the memory 7021. When the computer device 700 is running, the processor 701 communicates with the memory 702 through the bus 703, so that the processor 701 executes the following instructions:

[0171] Displaying a game scene screen during a game match of the target game; the game scene screen includes a target virtual character and hot event prompt information for the target virtual character; the hot event prompt information is used to indicate multiple candidate hot events that can be used to generate the target video;

[0172] In response to a target game event occurring in the game match, capturing and saving a candidate video clip associated with the target game event; the candidate video clip includes multiple frames of game scene images; the target game event belongs to the multiple candidate hot events;

[0173] In response to the video generation condition being met and in response to the game match ending, determining and selecting a plurality of target video segments corresponding to a target event trigger sequence from each of the at least one stored candidate video segments; the target event trigger sequence is determined by the artificial intelligence model based on video publishing data and / or game interaction data related to the target game;

[0174] The multiple target video clips are integrated according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

[0175] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program executes the steps of the video generation method described in the above method embodiment. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0176] The embodiments of the present disclosure also provide a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the video generation method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0177] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0179] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0180] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0181] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure is essentially or the contributing part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0182] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A video generation method, comprising: Displaying a game scene screen during a game match of the target game, wherein the game scene screen includes a target virtual character; In response to a target game event occurring in the game match, obtaining a candidate video segment associated with the target game event, wherein the candidate video segment includes multiple frames of game scene images; In response to satisfying the video generation condition, determining a plurality of target video segments corresponding to a target event trigger sequence from the plurality of candidate video segments, wherein the target event trigger sequence is determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game; The multiple target video clips are integrated according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

2. The method according to claim 1, further comprising: During the game, hot event prompt information for the target virtual character is displayed, wherein the hot event prompt information is used to indicate a variety of candidate hot events that can be used to generate the target video.

3. The method according to claim 1 or 2, wherein: The step of determining a plurality of target video segments corresponding to a target event triggering sequence from a plurality of candidate video segments comprises: Based on the multiple candidate video clips, at least one preliminary event trigger sequence matching the multiple candidate video clips is determined from the multiple candidate event trigger sequences, wherein each candidate event trigger sequence includes a plurality of candidate hot events arranged in sequence, and the plurality of candidate event trigger sequences are determined by the artificial intelligence model based on video publishing data and / or game interaction data related to the target game; displaying the at least one primary event triggering sequence; In response to a user selecting the target event trigger sequence from the at least one initially selected event trigger sequence, a plurality of candidate video segments corresponding to the target event trigger sequence are used as the plurality of target video segments.

4. The method according to claim 3, wherein: The presenting of the at least one preliminary event triggering sequence comprises: Display the at least one preliminary event trigger sequence and each preliminary event trigger sequence Corresponding interaction data, wherein the interaction data includes video publishing data and / or game interaction data, and the interaction data is used as reference data for the user to select the target event trigger sequence.

5. The method according to claim 1 or 2, wherein: The step of determining a plurality of target video segments corresponding to a target event triggering sequence from a plurality of candidate video segments comprises: Based on the multiple candidate video clips, at least one preliminary event trigger sequence matching the multiple candidate video clips is determined from the multiple candidate event trigger sequences, wherein each candidate event trigger sequence includes a plurality of candidate hot events arranged in sequence, and the plurality of candidate event trigger sequences are determined by the artificial intelligence model based on video publishing data and / or game interaction data related to the target game; Determine the interaction score corresponding to the at least one preliminary event trigger sequence based on the interaction data corresponding to the at least one preliminary event trigger sequence, wherein the interaction data includes video publishing data and / or game interaction data; According to the interaction score, the target event trigger sequence is determined from the at least one preliminary event trigger sequence, and a plurality of candidate video segments corresponding to the target event trigger sequence are used as the plurality of target video segments.

6. The method according to any one of claims 2 to 5, wherein: The artificial intelligence model is used to determine the multiple candidate hot events, including: Acquire video publishing data related to the target game, wherein the video publishing data includes each published video; For each candidate virtual character associated with the target game, determining interaction data of a published video corresponding to each candidate virtual character, and determining at least one target virtual character from among the candidate virtual characters based on the interaction data; For each of the target virtual characters, according to each published video corresponding to the target virtual character, determine the number of times the target virtual character triggers each game event; The game events whose trigger times exceed the first threshold are used as the candidate hotspot events.

7. The method according to any one of claims 2 to 5, wherein: The candidate hot events are determined by using an artificial intelligence model, including: Acquire video publishing data related to the target game, wherein the video publishing data includes each published video; Determine the triggering times of each game event based on each published video; The game events whose trigger times exceed the second threshold are used as the candidate hotspot events.

8. The method according to claim 3 or 5, wherein: Determining the candidate event trigger sequence using an artificial intelligence module includes: The candidate event triggering sequence is determined according to the event triggering order of each of the candidate hot events in multiple published videos.

9. A video generating device, comprising: The first display module is used to display the game scene screen during the game match of the target game; The game scene screen includes a target virtual character; An acquisition module, configured to acquire, in response to a target game event occurring in the game match, a candidate video segment associated with the target game event, wherein the candidate video segment includes multiple frames of game scene images; A first determination module is used to determine, in response to satisfying a video generation condition, a plurality of target video segments corresponding to a target event trigger sequence from at least one of the candidate video segments, wherein the target event trigger sequence is determined by an artificial intelligence model based on video publishing data and / or game interaction data related to the target game; The integration module is used to integrate the multiple target video clips according to the event occurrence order indicated by the target event trigger sequence to generate a target video.

10. A computer device comprising: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the video generation method according to any one of claims 1 to 8 is performed.

11. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the video generation method according to any one of claims 1 to 8 is executed.

Images