Video generation method, video generation device and video generation system

Abstract

The invention relates to a video generation method, a video generation device and a video generation system, and relates to the technical field of computers, and the method comprises the steps: obtaining a target bullet screen corresponding to a first video; determining a target video element matched with the semantics corresponding to the target bullet screen according to the target bullet screen; the target video element comprises at least one of a visual element or an auditory element; synthesizing a second video comprising the target video element and a first video clip according to the target video element and the first video clip; the first video clip is a video clip corresponding to the target bullet screen in the first video. The method is used for generating a video.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a video generation method, a video generation device, and a video generation system. Background Art

[0002] At present, with the popularity of short videos, the prior art often generates shorter video content including the video clip by extracting the video clip that the user is interested in from longer video content.

[0003] However, how to extract video clips that users are interested in from longer video content and then generate video content that meets user needs is a problem that needs to be solved at present. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a video generating method, a video generating device and a video generating system.

[0005] In a first aspect, a video generation method is provided, which is applied to a server, and the method includes: obtaining a target barrage corresponding to a first video; determining a target video element that matches the semantics corresponding to the target barrage based on the target barrage; the target video element includes at least one of a visual element or an auditory element; based on the target video element and a first video clip, synthesizing a second video including the target video element and the first video clip; the first video clip is a video clip in the first video corresponding to the target barrage.

[0006] In the above method of the present application, it is taken into consideration that: when a user posts a barrage during video playback, it usually indicates that the user has a high interest in the video clip corresponding to the barrage. Based on this consideration, in the above method, on the one hand, after obtaining the target barrage corresponding to the first video, the first video clip corresponding to the target barrage can be synthesized into the second video, so that the second video can include the video clip that the user is interested in; on the other hand, after obtaining the target barrage corresponding to the first video, the method can also determine the target video elements that match the semantics corresponding to the target barrage according to the target barrage, and synthesize these target video elements into the second video, thereby enriching the personalized content in the secondary creation video. Therefore, through the above method, a secondary creation video work (i.e., the second video) including the video clip of interest to the user and personalized video elements can be quickly generated without the user having to perform too much operation.

[0007] In some implementations, the target video element includes: a target picture, and the target picture is used to fill a background area of ​​the second video screen except for an area where the first video clip is located.

[0008] In some implementations, determining, based on the target barrage, a target video element that matches the semantics corresponding to the target barrage includes: determining, based on the target barrage, the target image that corresponds to the emotional color corresponding to the target barrage.

[0009] In some implementations, in the first video, the horizontal resolution of the picture is greater than the vertical resolution, and in the second video, the horizontal resolution of the picture is less than the vertical resolution.

[0010] In some implementations, the background area also includes at least one of the following: content information of the target barrage, publisher information of the target barrage, and a video title of the first video.

[0011] In some implementations, the target video element includes: target music, and the target music is used as background music for the second video.

[0012] In some implementations, determining, based on the target barrage, a target video element that matches the semantics corresponding to the target barrage includes: determining, based on the target barrage, the target music that corresponds to the emotional color corresponding to the target barrage.

[0013] In some implementations, the target video element includes: target text, and the target text is used as a title of the second video.

[0014] In some implementations, determining a target video element that matches the semantics corresponding to the target barrage based on the target barrage includes: determining the target text that corresponds to the emotional color corresponding to the target barrage and the content of the first video clip based on the target barrage and the first video clip.

[0015] In some implementations, the first video clip satisfies at least one of the following: the first video clip is a video clip including a scene played at a first moment in the first video, or the first video clip is a video clip including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

[0016] In some implementations, the method further includes: determining the first video segment from the first video based on the audio data and / or subtitle data of the first video; the first video segment is a video segment including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

[0017] In some implementations, the method also includes: determining the first video segment from the first video based on the difference between two adjacent frames of images in the first video; the first video segment is a video segment including the picture scene played at the first moment in the first video; the first moment is the time point corresponding to the target barrage in the first video.

[0018] In some implementations, the method further includes: determining the first video segment from the first video based on one or more of the scene, object, and image tags in the first video; the first video segment is a video segment corresponding to one or more of the scene, object, and image tags in the first video that are played at the first moment; the first moment is the time point corresponding to the target barrage in the first video.

[0019] In some implementations, the method further includes: generating a jump link from the second video to the first video, so that the jump link is displayed on the client interface during the process of playing the second video on the client.

[0020] In some implementations, obtaining the target barrage corresponding to the first video includes: receiving a video generation request from a client; the video generation request carries the target barrage and association information between the target barrage and the first video.

[0021] In some implementations, obtaining the target barrage corresponding to the first video includes: obtaining multiple barrages corresponding to the first video; determining the target barrage that meets preset conditions from the multiple barrages; the preset conditions include: the semantics corresponding to the barrage matches the preset semantic type, or the heat of the barrage is higher than at least one of the heat thresholds.

[0022] In a second aspect, a video generation method is provided, the method comprising: a client sends a video generation request to a server in response to a first instruction; the video generation request carries a target bullet screen and association information between the target bullet screen and a first video. The server determines a target video element that matches the semantics corresponding to the target bullet screen based on the target bullet screen; the target video element includes at least one of a visual element or an auditory element. The server synthesizes a second video including the target video element and the first video segment based on the target video element and the first video segment; the first video segment is a video segment in the first video corresponding to the target bullet screen.

[0023] In some implementations, the method further includes: after the client receives a first user operation performed on an area of ​​the target barrage in the playback interface of the first video, generating the first instruction.

[0024] In some implementations, the method further includes: after the client receives a second user operation on a first button corresponding to the target barrage in the playback interface of the first video, generating the first instruction.

[0025] In some implementations, the first button and the target barrage are displayed in the same text area in the playback interface of the first video.

[0026] According to a third aspect, a video generating device is provided, which is applied to a server, and the video generating device comprises: an acquisition unit for acquiring a target barrage corresponding to a first video; a processing unit for determining, based on the target barrage, a target video element that matches the semantics corresponding to the target barrage; the target video element comprises at least one of a visual element or an auditory element; the processing unit is further used to synthesize, based on the target video element and a first video segment, a second video comprising the target video element and the first video segment; the first video segment is a video segment in the first video corresponding to the target barrage.

[0027] In some implementations, the target video element includes: a target picture, and the target picture is used to fill a background area of ​​the second video screen except for an area where the first video clip is located.

[0028] In some implementations, a processing unit is used to determine, based on the target barrage, a target video element that matches the semantics corresponding to the target barrage, including: a processing unit is used to determine, based on the target barrage, the target picture that corresponds to the emotional color corresponding to the target barrage.

[0029] In some implementations, in the first video, the horizontal resolution of the picture is greater than the vertical resolution, and in the second video, the horizontal resolution of the picture is less than the vertical resolution.

[0030] In some implementations, the background area also includes at least one of the following: content information of the target barrage, publisher information of the target barrage, and a video title of the first video.

[0031] In some implementations, the target video element includes: target music, and the target music is used as background music for the second video.

[0032] In some implementations, a processing unit is used to determine, based on the target barrage, a target video element that matches the semantics corresponding to the target barrage, including: a processing unit is used to determine, based on the target barrage, the target music that corresponds to the emotional color corresponding to the target barrage.

[0033] In some implementations, the target video element includes: target text, and the target text is used as a title of the second video.

[0034] In some implementations, a processing unit is used to determine, based on the target barrage, a target video element that matches the semantics corresponding to the target barrage, including: a processing unit is used to determine, based on the target barrage and the first video clip, the target text corresponding to the emotional color corresponding to the target barrage and the content of the first video clip.

[0035] In some implementations, the first video clip satisfies at least one of the following: the first video clip is a video clip including a scene played at a first moment in the first video, or the first video clip is a video clip including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

[0036] In some implementations, the processing unit is also used to determine the first video segment from the first video based on the audio data and / or subtitle data of the first video; the first video segment is a video segment including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

[0037] In some implementations, the processing unit is also used to determine the first video segment from the first video based on the difference between two adjacent frames of images in the first video; the first video segment is a video segment including the picture scene played at the first moment in the first video; the first moment is the time point corresponding to the target barrage in the first video.

[0038] In some implementations, the processing unit is also used to determine the first video segment from the first video based on one or more of the scene, object, and image tags in the first video; the first video segment is a video segment corresponding to one or more of the scene, object, and image tags in the first video that are played at the first moment; the first moment is the time point corresponding to the target barrage in the first video.

[0039] In some implementations, the processing unit is further used to generate a jump link from the second video to the first video, so that the jump link is displayed on the client interface during the process of playing the second video on the client.

[0040] In some implementations, an acquisition unit, used to acquire a target barrage corresponding to a first video, includes: an acquisition unit, used to receive a video generation request from a client; the video generation request carries the target barrage and association information between the target barrage and the first video.

[0041] In some implementations, an acquisition unit, used to acquire a target barrage corresponding to a first video, includes: an acquisition unit, used to acquire multiple barrages corresponding to the first video; the acquisition unit is also used to determine a target barrage that meets preset conditions from the multiple barrages; the preset conditions include: the semantics corresponding to the barrage matches a preset semantic type, or the heat of the barrage is higher than at least one of the heat thresholds.

[0042] In a fourth aspect, a video generating device is provided, comprising a processor and an interface, wherein the processor receives or sends data through the interface, and the processor is used to implement the method of the first aspect or any implementation manner of the first aspect.

[0043] In a fifth aspect, a video generation system is provided, comprising a client and a server. The client is used to send a video generation request to the server in response to a first instruction; the video generation request carries a target bullet screen and association information between the target bullet screen and a first video. The server is used to determine, based on the target bullet screen, a target video element that matches the semantics corresponding to the target bullet screen; the target video element includes at least one of a visual element or an auditory element. The server is also used to synthesize, based on the target video element and the first video clip, a second video including the target video element and the first video clip; the first video clip is a video clip in the first video corresponding to the target bullet screen.

[0044] In a sixth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium. When the instructions are executed on a processor, a method as in the first aspect or any implementation method in the first aspect is implemented.

[0045] In a seventh aspect, a computer program product is provided, the computer program product comprising instructions, which, when executed on a processor, implement the method as in the first aspect or any one of the implementations in the first aspect.

[0046] In the technical solution provided by the present application, it is taken into consideration that: when a user posts a barrage during video playback, it usually indicates that the user has a high interest in the video clip corresponding to the barrage. Based on this consideration, in the above method, on the one hand, after obtaining the target barrage corresponding to the first video, the first video clip corresponding to the target barrage can be synthesized into the second video, so that the second video can include the video clip that the user is interested in; on the other hand, after obtaining the target barrage corresponding to the first video, the method can also determine the target video elements that match the semantics corresponding to the target barrage according to the target barrage, and synthesize these target video elements into the second video, thereby enriching the personalized content in the secondary creation video. Therefore, through the above method, a secondary creation video work (i.e., the second video) including the video clip of interest to the user and personalized video elements can be quickly generated without the user having to perform too much operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 A schematic diagram of the structure of a communication system provided by an embodiment of the present disclosure;

[0050] Figure 2 One of the flowcharts of a video generation method provided by an embodiment of the present disclosure;

[0051] Figure 3 A second flowchart of a video generation method provided by an embodiment of the present disclosure;

[0052] Figure 4 A third flowchart of a video generation method provided in an embodiment of the present disclosure;

[0053] Figure 5 A fourth flowchart of a video generation method provided in an embodiment of the present disclosure;

[0054] Figure 6 A fifth flowchart of a video generation method provided in an embodiment of the present disclosure;

[0055] Figure 7 One of the schematic diagrams of a client interface provided by an embodiment of the present disclosure;

[0056] Figure 8 A sixth flowchart of a video generation method provided in an embodiment of the present disclosure;

[0057] Fig. 9 A seventh flowchart of a video generation method provided in an embodiment of the present disclosure;

[0058] Fig.10 A second schematic diagram of a client interface provided in an embodiment of the present disclosure;

[0059] Fig.11 A second schematic diagram of a client interface provided in an embodiment of the present disclosure;

[0060] Fig.12 A third schematic diagram of a client interface provided in an embodiment of the present disclosure;

[0061] Fig.13 A fourth schematic diagram of a client interface provided in an embodiment of the present disclosure;

[0062] Fig.14 One of the structural schematic diagrams of a video generating device provided in an embodiment of the present disclosure;

[0063] Fig.15 A second structural diagram of a video generating device provided in an embodiment of the present disclosure;

[0064] Fig.16 The third structural diagram of a video generating device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0065] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0067] The following is an introduction to the technical solution provided by this disclosure:

[0068] In order to capture video clips of interest to users from longer videos and then generate video content that meets user needs, the embodiments of the present disclosure take into account: when a user posts a barrage (hereinafter referred to as a target barrage for ease of description) in a certain video (hereinafter referred to as the first video for ease of description), on the one hand, the video element (hereinafter referred to as the target video element) that matches the semantics corresponding to the target barrage can be determined based on the target barrage corresponding to the first video. The target video element may include at least one of a visual element (for example, a picture or text, etc.) or an auditory element (for example, background music of a video, etc.). On the other hand, a second video including the target video element and the first video clip can be synthesized based on the above-mentioned target video element and the first video clip. The first video clip is a video clip in the first video corresponding to the target barrage.

[0069] In this way, on the one hand, by synthesizing the first video clip corresponding to the target barrage into the second video, the second video can include the video clip that the user is interested in; on the other hand, by synthesizing the target video element that matches the semantics corresponding to the target barrage into the second video, the personalized content in the secondary creation video can be enriched. Therefore, through the above method, a secondary creation video work (i.e., the second video) including the video clip that the user is interested in and the personalized video element can be quickly generated without the user having to perform too much operation.

[0070] The following is an introduction to the specific implementation of the video generation method provided by the embodiment of the present disclosure with reference to a specific example:

[0071] First, the application scenarios of the embodiments of the present disclosure are introduced. Figure 1 The figure shows a schematic diagram of a communication system provided by an embodiment of the present disclosure. The communication system 10 may include a server 101 and multiple clients (the figure takes client 102, client 103, client 104 and client 105 as examples for illustration), and the multiple clients may be connected to the server 101 through a communication network.

[0072] The server 101 may be used to store video data and distribute the video data to a client for playing the video, so that the client plays the video data after receiving the video data.

[0073] In the actual application process, the client can be various electronic devices. For example, the client can be a mobile phone, a tablet computer, a desktop, a laptop, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) and a virtual reality (VR) device. In addition, the client can also be a software / hardware module running in the above-mentioned various electronic devices. The specific form of the client may not be particularly limited in the embodiments of the present disclosure.

[0074] The following introduces the video generation method provided by the embodiment of the present disclosure by taking the operation process of the server 101 as an example with reference to an example.

[0075] S201. The server 101 obtains a target barrage corresponding to a first video.

[0076] like Figure 3 As shown, in one implementation, the above S201 may specifically include the following S201a:

[0077] S201a, the server 101 receives a video generation request from the client.

[0078] The video generation request carries the target barrage and the association information between the target barrage and the first video.

[0079] The client in S201a may be any client connected to the server 101 .

[0080] Through the above implementation method, it is possible to send a video generation request from the client to the server, so that the client decides which barrage the server uses as the target barrage, so as to synthesize the second video according to the video generation method provided in the embodiment of the present application.

[0081] The following will combine Figure 8 The content of S301 in the figure gives a detailed introduction to the operation process of the client when the client sends a video generation request to the server 101, which will not be described in detail here.

[0082] In another implementation, Figure 3 As shown, the above S201 may specifically include the following S201b1-S201b2:

[0083] S201b1, the server 101 obtains multiple bullet comments corresponding to the first video.

[0084] Among them, the multiple barrages corresponding to the first video may specifically include: all or part of the barrages corresponding to the first video.

[0085] S201b2. The server 101 determines a target barrage meeting preset conditions from multiple barrages.

[0086] Among them, the preset conditions may include: the semantics corresponding to the barrage matches the preset semantic type.

[0087] For example, the preset semantic types may include: happy, excited, sad, sad, etc. In this way, the server 101 may determine a bullet screen that matches the semantic types of happy, excited, sad, sad, etc. from multiple bullet screens as a target bullet screen.

[0088] In addition, the preset conditions may also include: the heat of the barrage is higher than the heat threshold.

[0089] For example, the popularity of a barrage higher than a popularity threshold may include: the number of likes of the barrage higher than a number threshold, the number of times the content information of the barrage is repeatedly published higher than a number threshold, etc. In this way, the server 101 may determine, from among multiple barrages, a barrage with a number of likes higher than a number threshold, or a barrage with a number of times the content information of the barrage is repeatedly published higher than a number threshold, as a target barrage.

[0090] In addition, the preset conditions may also include: the semantics corresponding to the barrage matches the preset semantic type and the heat of the barrage is higher than the heat threshold.

[0091] For example, the server 101 may determine a target bullet screen from multiple bullet screens that satisfies the following two conditions at the same time: the semantics corresponding to the bullet screen matches a preset semantic type, and the heat of the bullet screen is higher than a heat threshold.

[0092] S202. The server 101 determines, according to the target bullet comment, a target video element that matches the semantics corresponding to the target bullet comment.

[0093] The target video element may include at least one of a visual element or an auditory element.

[0094] For example, visual elements may include: pictures, texts, and visual effects, etc. Exemplarily, if the target barrage corresponds to the semantics of sadness, the target video elements may include: pictures, texts, and visual effects that express sadness.

[0095] For another example, the auditory elements may include music and special sound effects, etc. For example, if the target barrage corresponds to the semantics of joy, the target video elements may include music and special sound effects that express joy.

[0096] S203: The server 101 synthesizes a second video including the target video element and the first video segment according to the target video element and the first video segment.

[0097] Among them, the first video clip is a video clip in the first video corresponding to the target barrage.

[0098] Through the above method provided in the embodiment of the present application, a second video including both a target video element matching the semantics corresponding to the target barrage and a first video segment corresponding to the target barrage can be generated. In this way, without having to play the first video to the user, the effect of spreading the viewpoint of the target barrage in the first video to more people can be achieved by simply playing the second video to the user.

[0099] Three implementation methods are listed below to introduce the contents included in the above target video elements.

[0100] In a first implementation manner, the target video element may include: a target picture.

[0101] The target image is used to fill the background area of ​​the second video except the area where the first video clip is located.

[0102] Specifically, in some usage scenarios, the target image that fills the background area may be referred to as a board background image. In the embodiments of the present application, no limitation is imposed on the naming of the image that fills the background area.

[0103] In this implementation, it is considered that the resolution of the second video may be different from that of the first video. For example, when the screen size of the first video is 6:4 and the screen size of the second video is 16:9, there may be a background area in the screen of the second video other than the area where the first video clip is located. Therefore, through the above implementation, the target image that matches the semantics corresponding to the target bullet comment can be used to fill the above background area, so that the generated second video and the target bullet comment can be more matched.

[0104] Among them, in some designs, the horizontal resolution of the picture in the first video is greater than the vertical resolution, and the horizontal resolution of the picture in the second video is less than the vertical resolution.

[0105] In the above design, it is taken into consideration that: with the development of mobile Internet, more and more people use mobile terminals to watch videos, and mobile terminals (such as mobile phones) are usually vertical display screens (that is, the horizontal resolution of the display screen is smaller than the vertical resolution). Therefore, when the above first video is a horizontal video (that is, the horizontal resolution of the screen in the first video is larger than the vertical resolution), the above design can make the generated second video a vertical video (that is, the horizontal resolution of the screen in the second video is smaller than the vertical resolution), which makes it easier to watch the second video on the mobile terminal.

[0106] In addition, when the first video is a horizontal video and the second video is a vertical video, the background area of ​​the second video except for the area where the first video clip is located is also relatively large. At this time, the target image that matches the semantics corresponding to the target barrage is used to fill the above background area, which can further enhance the user experience.

[0107] Furthermore, in some designs, such as Figure 4 As shown, the above S202 may specifically include the following S202a:

[0108] S202a, the server 101 determines a target image corresponding to the emotional color corresponding to the target barrage according to the target barrage.

[0109] Among them, the emotional color corresponding to the target barrage can specifically be the recognition result obtained by identifying the emotional information included in the content information of the target barrage using technologies such as Artificial Intelligence Generated Content (AIGC) and Natural Language Processing (NLP).

[0110] Exemplarily, the emotional color corresponding to the target barrage may specifically include one or more of the emotional colors such as happiness, anger, resentment or sadness.

[0111] In addition, the target picture corresponding to the emotional color corresponding to the target barrage may specifically include: the color of the picture corresponds to the emotional color corresponding to the target barrage.

[0112] For example, when the emotional color corresponding to the target barrage is happy, a red picture is used as the target picture. In addition, when the emotional color corresponding to the target barrage is sad, a gray picture is used as the target picture.

[0113] Furthermore, in some possible designs, the target image may be an image selected from a preset image library that corresponds to the emotional color corresponding to the target barrage.

[0114] In some other possible designs, the target image may be an image generated by AIGC technology that corresponds to the emotional color of the target barrage.

[0115] In addition, in some designs, the background area of ​​the second video screen, except for the area where the first video clip is located, may also include at least one of the following: content information of the target barrage, user publisher information of the target barrage, and the video title of the first video.

[0116] Specifically, in this design, one or more of the content information of the target barrage, the publisher information of the user who posted the target barrage, and the video title of the first video can be displayed on the background area of ​​the second video, so that the content of the background area in the second video is more relevant to the user's interests.

[0117] In a second implementation manner, the target video element may include: target music.

[0118] The target music is used as background music for the second video.

[0119] Through this implementation method, the target music that matches the semantics corresponding to the target barrage can be used as the background music of the second video, so that the generated second video and the target barrage can be more matched.

[0120] Furthermore, in some designs, such as Figure 4 As shown, the above S202 may specifically include the following S202b:

[0121] S202b, the server 101 determines the target music corresponding to the emotional color corresponding to the target barrage according to the target barrage.

[0122] Among them, the emotional color corresponding to the target barrage can specifically be the recognition result obtained by identifying the emotional information included in the content information of the target barrage by using artificial intelligence content generation technologies such as AIGC and NLP.

[0123] Exemplarily, the emotional color corresponding to the target barrage may specifically include one or more of the emotional colors such as happiness, anger, resentment or sadness.

[0124] For example, when the emotional color corresponding to the target barrage is happy, cheerful music is used as the target music; when the emotional color corresponding to the target barrage is sad, dull music is used as the target music.

[0125] In a third implementation manner, the target video element may include: target text.

[0126] The target text is used as the title of the second video.

[0127] Through this implementation method, the target text that matches the semantics corresponding to the target barrage can be used as the title of the second video, so that the title of the second video and the target barrage can be more matched.

[0128] Furthermore, in some designs, such as Figure 4 As shown, the above S202 may specifically include the following S202c:

[0129] S202c. The server 101 determines the target text corresponding to the emotional color corresponding to the target barrage according to the target barrage.

[0130] Among them, the emotional color corresponding to the target barrage can specifically be the recognition result obtained by identifying the emotional information included in the content information of the target barrage by using artificial intelligence content generation technologies such as AIGC and NLP.

[0131] Exemplarily, the emotional color corresponding to the target barrage may specifically include one or more of the emotional colors such as happiness, anger, resentment or sadness.

[0132] For example, when the emotional color corresponding to the target barrage is happy, the target text may be content reflecting happiness. For example, "It's great" and other content are used as the target text. When the emotional color corresponding to the target barrage is sad, the target text may be content reflecting sadness. For example, "I'm sad" and other content are used as the target text.

[0133] The content and generation process of the above-mentioned first video segment (ie, the video segment in the first video corresponding to the target barrage) are introduced below.

[0134] In some implementations, the first video clip is a video clip including a scene played at a first moment in the first video, wherein the first moment is a time point corresponding to the target bullet comment in the first video.

[0135] For example, if the scene played at the first moment in the first video is a landscape, a video clip within the time period of playing the landscape can be captured from the first video as the first video clip.

[0136] In some other implementations, the first video clip is a video clip including a dialogue between characters played at a first moment in the first video, wherein the first moment is a time point corresponding to the target bullet comment in the first video.

[0137] For example, if the scene played at the first moment in the first video is a conversation between people, then a video clip within the time period of the conversation between the people can be captured from the first video as the first video clip.

[0138] It should be noted that, in actual application, the first moment may be the moment when the target barrage is sent in the first video. For example, if the target barrage is sent by the user clicking the send button at moment a in the first video, then moment a may be used as the first moment.

[0139] In addition, the first moment can also be any moment in the time period when the target bullet screen is displayed in the first video. For example, in the first video, the target bullet screen is displayed in the screen from moment b and disappears from the screen at moment c. Then the first moment can be any time point between moment b and moment c.

[0140] It is understandable that, in actual application, the determination rule of the first moment can be set according to actual needs, and there is no limitation on this in the embodiments of the present application.

[0141] The following introduces the specific process of determining the first video segment from the first video in three implementation modes in combination with examples:

[0142] In the first implementation, Figure 5 As shown, the method may also include:

[0143] S204a: The server 101 determines a first video segment from the first video according to the audio data and / or subtitle data of the first video.

[0144] The first video clip is a video clip of a character dialogue played at a first moment in the first video. The first moment is a time point corresponding to the target barrage in the first video.

[0145] In this implementation, it is considered that the audio data and / or subtitle data of the first video can be used to identify the video clip of the character dialogue of the first video. Therefore, through the above implementation, the first video clip including the character dialogue played at the first moment can be determined from the first video.

[0146] In one possible design, S204a may include:

[0147] S204a1. The server 101 determines a first video segment from the first video according to the audio data of the first video.

[0148] In one aspect, the server 101 may determine the first video segment from the first video based on all audio data corresponding to the first video.

[0149] On the other hand, the server 101 may also first capture the audio data in a preset time period before and after the first moment from all the audio data corresponding to the first video, and then determine the first video segment from the first video based on the audio data in the preset time period.

[0150] For example, the server 101 may first read the sending time of the target bullet comment as the first moment, and then obtain the video medium of a preset time period near the first moment (for example, obtain the video medium of 2 minutes near the first moment), and then obtain the audio data of the preset time period from the obtained video medium. Then, according to the audio data of the preset time period, the first video segment including the character dialogue played at the first moment is determined from the first video.

[0151] In another possible design, S204a may further include:

[0152] S204a2: The server 101 determines a first video segment from the first video according to the subtitle data of the first video.

[0153] The server 101 may determine the first video segment from the first video according to all subtitle data corresponding to the first video.

[0154] In addition, the server 101 may firstly capture the subtitle data in a preset time period before and after the first moment from all the subtitle data corresponding to the first video, and then determine the first video segment including the character dialogue played at the first moment from the first video according to the subtitle data in the preset time period.

[0155] In yet another possible design, S204a may include:

[0156] S204a3: The server 101 may determine a first video segment from the first video according to the audio data and subtitle data of the first video.

[0157] For example, the server 101 may obtain the audio data and subtitle data by referring to the specific processes of S204a1 and S204a2, and then determine a more accurate video segment portion of the character dialogue as the first video segment based on the audio data and subtitle data.

[0158] In the second implementation, Figure 5 As shown, the method may also include:

[0159] S204b: The server 101 determines a first video segment from the first video according to a difference between two adjacent frames of images in the first video.

[0160] The first video clip is a video clip including a scene played at a first moment in the first video. The first moment is a time point corresponding to the target bullet screen in the first video.

[0161] Specifically, when the difference between two adjacent frames of images is large (for example, when the difference is greater than a preset threshold), it indicates that the scene in the video may have been switched. Therefore, a first video segment including the scene played at the first moment is determined from the first video according to the difference between two adjacent frames of images in the first video.

[0162] For example, after the server 101 obtains two adjacent frames of images, the pixels at corresponding positions in the two frames of images may be compared (specifically, the red, green, blue (RGB) values ​​of the pixels may be compared or the grayscale values ​​of the pixels may be compared). Then, based on the comparison results of the pixels at each position, a comparison algorithm such as mean square error (MSE) or structural similarity index may be used to determine the size of the difference between the two frames of images.

[0163] As another example, after the server 101 obtains two adjacent frames of images, the feature extraction model can be used to extract feature information of the two frames of images, and then the size of the difference between the two frames of images can be determined based on the feature information of the two frames of images.

[0164] It is understandable that, similar to the specific content in S204a, in S204b, the server 101 can first obtain the video medium of the preset time period around the first moment (for example, obtain the video medium of 2 minutes around the first moment), and then extract the image data of each frame from the obtained video medium, and then obtain a list including the correspondence between the image data and the time point. Then, the two adjacent frames of images in the list are compared to determine the difference between the two adjacent frames of images in the video medium. Then, according to the difference between the two adjacent frames of images, the first video segment is determined from the first video.

[0165] In the third implementation, Figure 5 As shown, the method may also include:

[0166] S204c: The server 101 determines a first video segment from the first video according to one or more of the scene, object, and image tags in the first video.

[0167] The first video clip is a video clip corresponding to one or more of the scene, object and image label in the picture played at the first moment in the first video. The first moment is the time point corresponding to the target bullet screen in the first video.

[0168] For example, technical means such as AI big models can be used to understand one or more of the scenes, objects, and image labels in the first video, and then determine the first video segment from the first video based on the understanding results.

[0169] It is understandable that the above S204a, S204b and S204c respectively introduce the implementation methods of determining the first video segment from the first video in the method provided by the embodiment of the present disclosure through three implementation methods. In actual application, the first video segment can also be determined from the first video in other ways. For example, multiple items in S204a, S204b and S204c can be combined to determine the first video segment from the first video based on multiple items in the audio data, subtitle data, difference between two adjacent frames of images, scenes, objects and image labels of the first video.

[0170] In addition, it should be noted that Figure 5 In the example, S204a, S204b and S204c are placed after S202 for execution. In the actual application process, the execution order of S204a, S204b and S204c can be determined according to actual needs. For example, S204a, S204b and S204c can be executed at any time before S203. It is understandable that the execution order of each step in the embodiment of the present application is determined by the logical relationship between the steps. The numbering of each step in the embodiment of the present application (such as S201, S202, etc.) and the order of each step in the accompanying drawings are only used to distinguish different steps, and do not mean the limitation of the execution order of each step.

[0171] In addition, in some implementations, such as Figure 6 As shown, the method may also include:

[0172] S205. The server 101 generates a jump link from the second video to the first video, so that the jump link is displayed on the client interface during the process of playing the second video on the client.

[0173] Exemplarily, the client interface for playing the second video on the client can be as follows: Figure 7 As shown, it can be seen that the screen of the second video includes the area 503 where the first video clip is located, and the screen of the second video also includes a background area 501 other than the area where the first video clip is located. In addition, in the client interface, in addition to the screen of the second video, a jump link 502 is also included. In this way, when the user clicks the jump link 502, the client can jump to the first video.

[0174] In some implementations, the method may further include:

[0175] S206: The server 101 pushes the second video to one or more clients according to a preset push algorithm.

[0176] For example, the server 101 may use a preset push algorithm to predict one or more users who are interested in the second video, and push the second video to the clients corresponding to the one or more users, so that the clients can play the second video after receiving the user operation of playing the second video.

[0177] Exemplarily, the server 101 pushes the second video to the client corresponding to the one or more users, which may specifically include: the server 101 sends an instruction message to the one or more clients to instruct the one or more clients to display the title, picture and other graphic information of the second video at the corresponding position of the client interface. In addition, the user operation of playing the second video may include: the user clicks, long presses, and other operations on the title, picture and other graphic information of the second video in the client interface.

[0178] In addition, it is understandable that the server 101 sends the video data of the second video to each client so that when each client plays the second video, the server 101 can also send the jump link generated in S205 to each client so that each client can display the jump link on the client interface during the process of playing the second video. In this way, when each client receives the user operation on the jump link, it jumps to the first video.

[0179] In the above S201a, it is introduced that the server 101 can obtain the target bullet comment corresponding to the first video by receiving the video generation request of the client. Next, taking the interaction scenario between the server 101 and the client 102 as an example, the operation process of the client 102 when the client 102 sends a video generation request to the server 101 is described in detail. Figure 8 As shown, the method may include the following contents of S301-S302:

[0180] S301 , the client 102 sends a video generation request to the server 101 in response to a first instruction.

[0181] The video generation request carries the target bullet screen and the association information between the target bullet screen and the first video. For example, the association information may include: the identifier of the first video, so that after receiving the video generation request, the server 101 can read the target bullet screen from the video generation request, and can also determine the first video corresponding to the target bullet screen according to the identifier of the first video.

[0182] The first instruction may be an instruction generated in the client 102 after the user performs a corresponding operation in the operation interface of the client 102. The generation process of the first instruction is introduced below through two implementation modes.

[0183] In a first implementation, the first instruction may be an instruction generated in the client 102 after the user performs an operation in the target bullet screen area in the playback interface of the first video. Fig. 9 As shown, the method may also include:

[0184] S1. After receiving a first user operation on an area of ​​a target bullet screen in a playback interface of a first video, the client 102 generates a first instruction.

[0185] The first user operation may be any one of click, long press, and drag.

[0186] For example, the playback interface of the first video in the client 102 is as follows: Fig.10 As shown, in the playback interface 400 of the first video, a target bullet screen 401 is displayed. When the user performs a first user operation on the target bullet screen 401, the client 102 generates a first instruction.

[0187] In a second implementation, the first instruction may be an instruction generated in the client 102 after the user operates the first button corresponding to the target bullet screen in the playback interface of the first video. Fig.11 As shown, the method may also include:

[0188] S21. After receiving a second user operation on a first button corresponding to the target bullet screen in the playback interface of the first video, the client 102 generates a first instruction.

[0189] For example, the playback interface of the first video in the client 102 is as follows: Fig.12 As shown, in the playback interface 400 of the first video, a target bullet screen 401 is displayed, and a first button 402 corresponding to the target bullet screen is also included. When the user performs a second user operation on the first button 402, the client 102 generates a first instruction.

[0190] The second user operation may be any one of click, long press, and drag.

[0191] in, Fig.12 Take a square button marked with “One-click to create a film” as an example as the first button 402. It is understandable that in actual application, the shape and pattern of the first button 402 can be set according to actual needs, and there is no limitation on this in the embodiment of the present disclosure.

[0192] In addition, in some designs, the first button and the target bullet screen are displayed in the same text area in the playback interface of the first video. Fig.12 The first button 402 and the target barrage 401 are displayed in the same text area in the playback interface of the first video.

[0193] In addition, in some designs, before executing S21, the method may further include:

[0194] S22. After receiving the third user operation of posting the target barrage, the client 102 displays the target barrage and the first button in the playback interface of the first video.

[0195] For example, in Fig.12 In the playback interface 400 shown, when the user inputs the content of the bullet comment (i.e., "This person is so handsome!") into the bullet comment input box 403 in the playback interface 400 and clicks "Send", the client 102 displays the target bullet comment 401 and the first button 402 in the playback interface of the first video. The third user operation of publishing the target bullet comment can be understood as: the user inputs the content of the bullet comment into the bullet comment input box 403 in the playback interface 400 and clicks "Send".

[0196] In the above design, it is considered that compared with other users watching the video, the user who posts the target bullet screen usually has a higher demand for generating the above second video. Therefore, after receiving the third user operation of posting the target bullet screen, the client can display the target bullet screen and the first button in the playback interface of the first video. In this way, the user who posts the target bullet screen can trigger the generation of the second video by performing the second user operation on the first button, thereby improving the user experience.

[0197] In addition, if Fig.13 As shown, after the client 102 receives the above-mentioned first user operation or the second user operation, the client 102 can also display a prompt message 404 on the interface (taking "Video is being released, please pay attention to my message notification~" as an example in the figure) to prompt the user that the second video is being released.

[0198] S302: After receiving the video generation request, the server 101 may execute the above Figure 2-6 Part or all of steps S201-S206.

[0199] Based on the above method embodiment, the device provided by the embodiment of the present disclosure is described below. Fig.14 FIG. 6 is a schematic diagram of a video generation device provided by an embodiment of the present disclosure. Specifically, the video generation device 60 may be a chip or a system on a chip. The video generation device 60 may be used to implement Figure 2-Figure 3Specifically, the video generating device 60 may include:

[0200] The acquisition unit 601 is used to acquire the target barrage corresponding to the first video.

[0201] The processing unit 602 is used to determine, according to the target barrage, a target video element that matches the semantics corresponding to the target barrage; the target video element includes at least one of a visual element or an auditory element.

[0202] The processing unit 602 is further used to synthesize a second video including the target video element and the first video segment according to the target video element and the first video segment; the first video segment is a video segment in the first video corresponding to the target barrage.

[0203] In some implementations, the target video element includes: a target picture, and the target picture is used to fill a background area of ​​the second video screen except for an area where the first video clip is located.

[0204] In some implementations, the processing unit 602 is configured to determine, according to the target bullet comment, a target video element that matches the semantics corresponding to the target bullet comment, including:

[0205] The processing unit 602 is used to determine the target image corresponding to the emotional color corresponding to the target barrage according to the target barrage.

[0206] In some implementations, in the first video, the horizontal resolution of the picture is greater than the vertical resolution, and in the second video, the horizontal resolution of the picture is less than the vertical resolution.

[0207] In some implementations, the background area also includes at least one of the following: content information of the target barrage, publisher information of the target barrage, and a video title of the first video.

[0208] In some implementations, the target video element includes: target music, and the target music is used as background music for the second video.

[0209] In some implementations, the processing unit 602 is configured to determine, according to the target bullet comment, a target video element that matches the semantics corresponding to the target bullet comment, including:

[0210] The processing unit 602 is used to determine the target music corresponding to the emotional color corresponding to the target barrage according to the target barrage.

[0211] In some implementations, the target video element includes: target text, and the target text is used as a title of the second video.

[0212] In some implementations, the processing unit 602 is configured to determine, according to the target bullet comment, a target video element that matches the semantics corresponding to the target bullet comment, including:

[0213] The processing unit 602 is used to determine the target text corresponding to the emotional color corresponding to the target barrage and the content of the first video segment according to the target barrage and the first video segment.

[0214] In some implementations, the first video clip satisfies at least one of the following: the first video clip is a video clip including a scene played at a first moment in the first video, or the first video clip is a video clip including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

[0215] In some implementations, the processing unit 602 is further used to determine the first video segment from the first video based on the audio data and / or subtitle data of the first video; the first video segment is a video segment including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

[0216] In some implementations, the processing unit 602 is also used to determine the first video segment from the first video based on the difference between two adjacent frames of images in the first video; the first video segment is a video segment including the picture scene played at the first moment in the first video; the first moment is the time point corresponding to the target barrage in the first video.

[0217] In some implementations, the processing unit 602 is further used to determine the first video segment from the first video based on one or more of the scene, object, and image tags in the first video; the first video segment is a video segment corresponding to one or more of the scene, object, and image tags in the first video that are played at the first moment; the first moment is the time point corresponding to the target barrage in the first video.

[0218] In some implementations, the processing unit 602 is further configured to generate a jump link from the second video to the first video, so that the jump link is displayed on the client interface during the process of playing the second video on the client.

[0219] In some implementations, the acquisition unit 601 is configured to acquire a target bullet comment corresponding to the first video, including:

[0220] The acquisition unit 601 is used to receive a video generation request from a client; the video generation request carries a target bullet comment and association information between the target bullet comment and a first video.

[0221] In some implementations, the acquisition unit 601 is configured to acquire a target bullet comment corresponding to the first video, including:

[0222] An acquisition unit 601 is used to acquire multiple bullet comments corresponding to the first video;

[0223] The acquisition unit 601 is also used to determine a target barrage that meets preset conditions from the multiple barrages; the preset conditions include: the semantics corresponding to the barrage matches the preset semantic type, or the heat of the barrage is higher than at least one of the heat thresholds.

[0224] The video generating device 60 provided in the embodiment of the present application can execute the steps performed by the server 101 in the method provided in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0225] The embodiments of the present disclosure may divide the functional modules of the device according to the above method examples. For example, each functional module may be divided according to each function, or two or more functions may be integrated into one processing module. The above integrated modules may be implemented in the form of hardware or software functional modules. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation. In the case of dividing each functional module according to each function, such as Fig.14 FIG. 7 is another possible structural diagram of a video generating device involved in an embodiment of the present disclosure. The video generating device 70 may include:

[0226] The barrage module 701 is responsible for receiving the barrage posted by the user, recording the first video associated with the barrage, and the time point information of the posting, and performing sensitive word filtering and content review, etc. After filtering, the above information is notified to the process control module 702.

[0227] The process control module 702 is responsible for the overall business process control of the bullet screen video, which segments the wonderful clips of the first video, matches the appropriate background pictures and background music, and finally synthesizes and publishes the second video.

[0228] Video information module 703: responsible for obtaining information of the first video and obtaining medium information of the first video for subsequent processing.

[0229] Video understanding module 704: responsible for analyzing and understanding the content of the first video through AI large model video processing technology to facilitate intelligent segmentation of the video.

[0230] Video transcoding module 705: responsible for transcoding the captured first video clip, generating background pictures, background music, barrage content, original video title and other information, and synthesizing them into a new vertical video (ie, the second video).

[0231] The video publishing module 706 is responsible for publishing the second video and associating it with the first video.

[0232] The video generating device 70 provided in the embodiment of the present application can execute the steps performed by the server 101 in the method provided in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0233] In addition, if Fig.16 FIG. 8 is a schematic diagram of another video generation device provided in an embodiment of the present application. The video generation device 80 can be used to execute the steps performed by the server 101 in the video generation method provided in an embodiment of the present disclosure.

[0234] In practical applications, the functions of the video generating device 80 can be implemented by various electronic devices.

[0235] Exemplarily, the video generating device 80 may include: a processor 801 , a communication line 802 , a memory 803 , and some or all of at least one communication interface 804 .

[0236] Among them, the processor 801 can be used to execute all or part of the steps in the method provided by the embodiment of the present disclosure. In addition, the memory 803 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the memory 803 stores computer instructions. The processor 801 can be used to execute all or part of the steps in the method provided by the present embodiment by executing the computer instructions stored in the memory 803. In addition, the communication interface 804 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. In addition, the communication line 802 is used to connect the various components in the video generation device 80. Specifically, the communication line 802 may include a data bus, a power bus, a control bus, and a status signal bus. However, for the sake of clarity, various buses are marked as communication lines 802 in the figure.

[0237] The method steps in this embodiment can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, PROM, EPROM, EEPROM, registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0238] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in this embodiment is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a communication device, a user device or other programmable device. The computer program or instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instruction can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as an SSD.

[0239] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0240] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A video generation method, characterized in that: The method is applied to a server, and the method comprises: Obtain a target comment corresponding to the first video; According to the target bullet comment, determining a target video element that matches the semantics corresponding to the target bullet comment; the target video element includes at least one of a visual element or an auditory element; According to the target video element and the first video segment, a second video including the target video element and the first video segment is synthesized; the first video segment is a video segment in the first video corresponding to the target barrage.

2. The method according to claim 1, characterized in that The target video element includes: a target picture, and the target picture is used to fill the background area of ​​the second video screen except the area where the first video clip is located.

3. The method according to claim 2, characterized in that The step of determining, according to the target bullet screen, a target video element that matches the semantics corresponding to the target bullet screen, includes: According to the target barrage, the target picture corresponding to the emotional color corresponding to the target barrage is determined.

4. The method according to claim 2, characterized in that: In the first video, the horizontal resolution of the picture is greater than the vertical resolution, and in the second video, the horizontal resolution of the picture is less than the vertical resolution.

5. The method according to claim 2, characterized in that: The background area also includes at least one of the following: content information of the target barrage, publisher information of the target barrage, and a video title of the first video.

6. The method according to claim 1, characterized in that The target video element includes: target music, and the target music is used as background music for the second video.

7. The method according to claim 6, characterized in that The step of determining, according to the target bullet screen, a target video element that matches the semantics corresponding to the target bullet screen, includes: According to the target barrage, the target music corresponding to the emotional color corresponding to the target barrage is determined.

8. The method according to claim 1, characterized in that The target video element includes: a target text, and the target text is used as a title of the second video.

9. The method according to claim 8, characterized in that The step of determining, according to the target bullet screen, a target video element that matches the semantics corresponding to the target bullet screen, includes: According to the target bullet comment and the first video clip, the target text corresponding to the emotional color corresponding to the target bullet comment and the content of the first video clip is determined.

10. The method according to claim 1, characterized in that The first video clip satisfies at least one of the following: the first video clip is a video clip including the scene played at the first moment in the first video, or the first video clip is a video clip including the dialogue between characters played at the first moment in the first video; the first moment is the time point corresponding to the target barrage in the first video.

11. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: The first video segment is determined from the first video based on the audio data and / or subtitle data of the first video; the first video segment is a video segment including a dialogue between characters played at a first moment in the first video; the first moment is a time point corresponding to the target barrage in the first video.

12. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: The first video segment is determined from the first video according to the difference between two adjacent frames of images in the first video; the first video segment is a video segment including the picture scene played at the first moment in the first video; the first moment is the time point corresponding to the target barrage in the first video.

13. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: The first video segment is determined from the first video according to one or more of the scenes, objects and image tags in the first video; the first video segment is a video segment corresponding to one or more of the scenes, objects and image tags in the first video and in the picture played at the first moment; the first moment is the time point corresponding to the target barrage in the first video.

14. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: Generate a jump link from the second video to the first video, so that the jump link is displayed on the client interface during the process of playing the second video on the client.

15. The method according to any one of claims 1 to 10, characterized in that: The obtaining of a target bullet comment corresponding to the first video includes: A video generation request is received from a client; the video generation request carries a target bullet screen and association information between the target bullet screen and a first video.

16. The method according to any one of claims 1 to 10, characterized in that: The obtaining of a target bullet comment corresponding to the first video includes: Obtain multiple bullet comments corresponding to the first video; From the multiple bullet comments, determine a target bullet comment that meets a preset condition; the preset condition includes: the semantics corresponding to the bullet comment matches a preset semantic type, or the heat of the bullet comment is higher than at least one of a heat threshold.

17. A video generation method, characterized in that: The method comprises: The client sends a video generation request to the server in response to the first instruction; the video generation request carries the target bullet comment and the association information between the target bullet comment and the first video; The server determines, according to the target bullet screen, a target video element that matches the semantics corresponding to the target bullet screen; the target video element includes at least one of a visual element or an auditory element; The server synthesizes a second video including the target video element and the first video segment according to the target video element and the first video segment; the first video segment is a video segment in the first video corresponding to the target barrage.

18. The method according to claim 17, characterized in that The method further comprises: The client generates the first instruction after receiving the first user operation performed on the area of ​​the target bullet screen in the playback interface of the first video.

19. The method according to claim 17, characterized in that The method further comprises: The client generates the first instruction after receiving a second user operation on a first button corresponding to the target bullet screen in the playback interface of the first video.

20. The method according to claim 19, characterized in that The first button and the target barrage are displayed in the same text area in the playback interface of the first video.

21. A video generating device, characterized in that: The video generation device is applied to a server, and the video generation device comprises: An acquisition unit, used to acquire a target bullet comment corresponding to the first video; A processing unit, configured to determine, according to the target bullet comment, a target video element that matches the semantics corresponding to the target bullet comment; the target video element includes at least one of a visual element or an auditory element; The processing unit is also used to synthesize a second video including the target video element and the first video segment based on the target video element and the first video segment; the first video segment is a video segment in the first video corresponding to the target barrage.

22. A video generating device, characterized in that: include: The method comprises a processor and an interface, wherein the processor receives or sends data through the interface, and the processor is used to implement the method according to any one of claims 1 to 16.

23. A video generation system, characterized in that: The video generation system includes a client and a server; wherein: The client is used to send a video generation request to the server in response to the first instruction; the video generation request carries the target bullet screen and the association information between the target bullet screen and the first video; The server is used to determine, according to the target bullet screen, a target video element that matches the semantics corresponding to the target bullet screen; the target video element includes at least one of a visual element or an auditory element; The server is also used to synthesize a second video including the target video element and the first video segment based on the target video element and the first video segment; the first video segment is a video segment in the first video corresponding to the target barrage.

24. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device implements the method according to any one of claims 1 to 16.

25. A computer program product, characterized in that When the computer program product is executed on a computer, the computer is enabled to implement the method according to any one of claims 1 to 16.

Images