Video generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a video generation method and device, electronic equipment and a storage medium. The method comprises the following steps: in response to a video generation instruction, displaying a plurality of video templates; under the condition that a target video template in the plurality of video templates is selected, displaying an object information collection page; in response to an acquisition confirmation instruction triggered based on an object information acquisition page, displaying a target video corresponding to the target video template; the target video is obtained by replacing a template object face image with a collection object face image and replacing a template audio with a collection object audio; wherein the acquisition object face image and the acquisition object audio are acquired based on the object information acquisition page under the acquisition confirmation instruction, the template object face image is a face image of a template object in the target video template, and the template audio is an audio in the target video template. According to the technical scheme provided by the invention, video generation is more efficient and flexible.

Description

Technical Field

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

[0002] With the development of the Internet and multimedia technology, video-based interactive methods have become more diverse. In related technologies, users are generally required to make videos for interaction themselves. Video production requires operations such as shooting and editing, which leads to low video production efficiency and poor video-based interactive effects. Summary of the invention

[0003] The present disclosure provides a video generation method, device, electronic device and storage medium to at least solve the problem of how to improve the efficiency of video generation in the related art. The technical solution of the present disclosure is as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a video generation method is provided, including:

[0005] In response to the video generation instruction, display a plurality of video templates;

[0006] When a target video template among the multiple video templates is selected, displaying an object information collection page;

[0007] In response to a collection confirmation instruction triggered based on the object information collection page, a target video corresponding to the target video template is displayed; the target video is obtained by replacing the template object's facial image with the collection object's facial image and replacing the template's audio with the collection object's audio;

[0008] Among them, the facial image of the acquisition object and the audio of the acquisition object are acquired based on the object information acquisition page under the acquisition confirmation instruction, the facial image of the template object is the facial image of the template object in the target video template, and the template audio is the audio in the target video template.

[0009] In a possible implementation, the object information acquisition page includes an image acquisition page and an audio acquisition page; and in response to the acquisition confirmation instruction triggered based on the object information acquisition page, displaying the target video corresponding to the target video template includes:

[0010] In response to an image acquisition completion instruction triggered based on the image acquisition page, displaying the facial image of the acquisition object;

[0011] In case of performing a confirmation operation on the facial image of the acquisition object, displaying the audio acquisition page;

[0012] In response to an audio collection completion instruction triggered based on the audio collection page, displaying the collection object audio;

[0013] When the audio of the acquisition object is confirmed, the target video is displayed.

[0014] In a possible implementation, the image acquisition page displays a facial description input area, and the acquiring of the object's facial image includes generating a facial image; the method further includes:

[0015] In response to the completion of the input operation of inputting the facial description information in the facial description input area, generating the image acquisition completion instruction;

[0016] The step of displaying the facial image of the acquisition object in response to the image acquisition completion instruction triggered based on the image acquisition page includes:

[0017] In response to the image acquisition completion instruction, the generated facial image is displayed.

[0018] In a possible implementation, the image acquisition page displays a shooting control, and the acquiring the facial image of the object includes capturing the facial image; and the displaying the facial image of the acquired object in response to the image acquisition completion instruction triggered based on the image acquisition page includes:

[0019] In response to the image acquisition completion instruction triggered based on the shooting control, the captured facial image is displayed.

[0020] In a possible implementation, the audio collection page displays a plurality of preset keywords; the collection object audio is a first collection audio; and the method further includes:

[0021] When at least one preset keyword is selected from the plurality of preset keywords and a selection confirmation operation is triggered, a first audio text and a first audio collection trigger control corresponding to the first audio text are displayed; the first audio text is generated based on the at least one preset keyword;

[0022] When the first audio collection trigger control is triggered, start collecting the audio corresponding to the first audio text, and when the audio collection corresponding to the first audio text is completed, generate the audio collection completion instruction;

[0023] The step of displaying the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page includes:

[0024] In response to the audio collection completion instruction, the first collected audio is displayed, and the first collected audio is the audio corresponding to the first audio text collected within a first time period; the start time of the first time period is the time when the first audio collection trigger control is triggered, and the end time of the first time period is the time corresponding to the audio collection completion instruction.

[0025] In a possible implementation, the audio collection page displays an input area for custom text; the collection object audio is a second collection audio; and the method further includes:

[0026] When it is detected that a custom text is input in the input area and the trigger text input is completed, displaying a second audio text corresponding to the custom text and a second audio collection trigger control corresponding to the second audio text;

[0027] When the second audio collection trigger control is triggered, start collecting the audio corresponding to the second audio text, and when the audio collection corresponding to the second audio text is completed, generate the audio collection completion instruction;

[0028] The step of displaying the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page includes:

[0029] In response to the audio collection completion instruction, the second collected audio is displayed, and the second collected audio is the audio corresponding to the second audio text collected within a second time period; the start time of the second time period is the time when the second audio collection trigger control is triggered, and the end time of the second time period is the time corresponding to the audio collection completion instruction.

[0030] In a possible implementation, the audio collection page displays a preset audio text and an audio collection trigger control; the collection object audio is a third collected audio; and the method further includes:

[0031] When the audio collection trigger control is triggered, start collecting the audio corresponding to the preset audio text, and when the audio collection corresponding to the preset audio text is completed, generate the audio collection completion instruction;

[0032] The step of displaying the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page includes:

[0033] In response to the audio collection completion instruction, the third collected audio is displayed. The third collected audio is obtained by replacing the timbre in the template audio by collecting the timbre in the audio corresponding to the preset audio text when the audio collection trigger control is triggered.

[0034] In a possible implementation, the method further includes:

[0035] Display the session page;

[0036] In the conversation page, in response to a message interaction request based on a preset event, generating the video generation instruction;

[0037] The displaying of the target video corresponding to the target video template includes:

[0038] The target video in the target display state and the object identifier of the first session object that sent the target video are displayed in the session page; the target display state is used to indicate whether the video content of the target video is displayed.

[0039] In a possible implementation, the conversation page displays a conversation video sent by the second conversation object and in a non-message content display state and a reply control matched with the conversation video, the conversation video is a conversation message based on the preset event; the message interaction request is a message reply interaction request; the target display state is a message content display state; the method further includes:

[0040] When the reply control is triggered, generating the message reply interaction request;

[0041] The method of displaying the target video in the target display state and the object identifier of the first session object that sent the target video in the session page includes:

[0042] The target video in the message content display state and the object identifier of the first session object that sent the target video are displayed in the session page, and the session video is switched to the message content display state.

[0043] In a possible implementation, the conversation page displays a message interaction control that triggers the preset event; the message interaction request is a message initiation interaction request; the target display state is a non-display message content state; and the method further includes:

[0044] When the message interaction control is triggered, generating the message initiation interaction request;

[0045] The method of displaying the target video in the target display state and the object identifier of the first session object that sent the target video in the session page includes:

[0046] The target video in the non-display message content state, the object identifier of the first conversation object, and a reply control matching the target video are displayed in the conversation page.

[0047] According to a second aspect of an embodiment of the present disclosure, a video generating device is provided, the device comprising:

[0048] A video template display module, configured to display a plurality of video templates in response to a video generation instruction;

[0049] An information collection module is configured to display an object information collection page when a target video template among the multiple video templates is selected;

[0050] A target video display module is configured to execute a target video corresponding to the target video template in response to a collection confirmation instruction triggered based on the object information collection page; the target video is obtained by replacing the template object's facial image with the collection object's facial image and replacing the template's audio with the collection object's audio;

[0051] Among them, the facial image of the acquisition object and the audio of the acquisition object are acquired based on the object information acquisition page under the acquisition confirmation instruction, the facial image of the template object is the facial image of the template object in the target video template, and the template audio is the audio in the target video template.

[0052] In a possible implementation, the object information acquisition page includes an image acquisition page and an audio acquisition page; and the target video display module includes:

[0053] A captured image display unit, configured to execute an image capture completion instruction in response to being triggered based on the image capture page, and display the facial image of the captured object;

[0054] an audio collection page display unit, configured to display the audio collection page when a confirmation operation is performed on the facial image of the collection object;

[0055] A collection object audio display unit, configured to execute an audio collection completion instruction in response to being triggered based on the audio collection page, and display the collection object audio;

[0056] The target video display unit is configured to display the target video when a confirmation operation is performed on the audio of the acquisition object.

[0057] In a possible implementation, the image acquisition page displays a facial description input area, and the acquiring of the object's facial image includes generating a facial image; the device further includes:

[0058] A first acquisition completion instruction module is configured to execute an input completion operation in response to inputting facial description information in the facial description input area, and generate the image acquisition completion instruction;

[0059] Accordingly, the collected image display unit includes:

[0060] The generated facial image display subunit is configured to display the generated facial image in response to the image acquisition completion instruction.

[0061] In a possible implementation, the image acquisition page displays a shooting control, and the acquiring of the object's facial image includes shooting the facial image; and the acquired image display unit includes:

[0062] The captured facial image display subunit is configured to execute and display the captured facial image in response to the image acquisition completion instruction triggered based on the shooting control.

[0063] In a possible implementation, the audio collection page displays a plurality of preset keywords; the collection object audio is a first collection audio; and the device may further include:

[0064] The first audio text display module is configured to display a first audio text and a first audio collection trigger control corresponding to the first audio text when at least one preset keyword is selected from the plurality of preset keywords and a selection confirmation operation is triggered; the first audio text is generated based on the at least one preset keyword;

[0065] A second acquisition completion instruction module is configured to start acquiring the audio corresponding to the first audio text when the first audio acquisition trigger control is triggered, and generate the audio acquisition completion instruction when the audio acquisition corresponding to the first audio text is completed;

[0066] Accordingly, the acquisition object audio display unit includes:

[0067] The first collected audio display sub-unit is configured to execute in response to the audio collection completion instruction and display the first collected audio, where the first collected audio is the audio corresponding to the first audio text collected within a first time period; the start time of the first time period is the time when the first audio collection trigger control is triggered, and the end time of the first time period is the time corresponding to the audio collection completion instruction.

[0068] In a possible implementation, the audio collection page displays an input area for a custom text; the collection object audio is a second collection audio; and the device may further include:

[0069] A second audio text display module is configured to display a second audio text corresponding to the custom text and a second audio collection trigger control corresponding to the second audio text when a custom text is input in the input area and the trigger text input is completed;

[0070] A third acquisition completion instruction module is configured to start acquiring the audio corresponding to the second audio text when the second audio acquisition trigger control is triggered, and generate the audio acquisition completion instruction when the audio acquisition corresponding to the second audio text is completed;

[0071] Accordingly, the acquisition object audio display unit includes:

[0072] The second collected audio display sub-unit is configured to execute in response to the audio collection completion instruction and display the second collected audio, where the second collected audio is the audio corresponding to the second audio text collected within a second time period; the start time of the second time period is the time when the second audio collection trigger control is triggered, and the end time of the second time period is the time corresponding to the audio collection completion instruction.

[0073] In a possible implementation, the audio collection page displays a preset audio text and an audio collection trigger control; the collection object audio is a third collection audio; and the device may further include:

[0074] A fourth acquisition completion instruction module is configured to start acquiring the audio corresponding to the preset audio text when the audio acquisition trigger control is triggered, and generate the audio acquisition completion instruction when the audio acquisition corresponding to the preset audio text is completed;

[0075] Accordingly, the acquisition object audio display unit includes:

[0076] The third collected audio display sub-unit is configured to execute in response to the audio collection completion instruction and display the third collected audio, wherein the third collected audio is obtained by replacing the timbre in the template audio by the timbre in the audio corresponding to the preset audio text when the audio collection trigger control is triggered.

[0077] In a possible implementation, the device may further include:

[0078] A session page display module, configured to execute display of a session page;

[0079] A video instruction generation module is configured to be executed in the conversation page and generate the video generation instruction in response to a message interaction request based on a preset event;

[0080] The target video display module may include:

[0081] The display unit is configured to display the target video in the target display state and the object identifier of the first session object that sends the target video in the session page; the target display state is used to indicate whether the video content of the target video is displayed.

[0082] In a possible implementation, the conversation page displays a conversation video sent by the second conversation object and in a non-message content display state and a reply control matched with the conversation video, the conversation video is a conversation message based on the preset event; the message interaction request is a message reply interaction request; the target display state is a message content display state; the device further includes:

[0083] A message reply interaction module, configured to generate the message reply interaction request when the reply control is triggered;

[0084] Accordingly, the display unit comprises:

[0085] The first display subunit is configured to display the target video in the display message content state and the object identifier of the first session object that sent the target video in the session page, and switch the session video to the display message content state.

[0086] In a possible implementation, the conversation page displays a message interaction control that triggers the preset event; the message interaction request is a message initiation interaction request; the target display state is a non-display message content state; and the device may further include:

[0087] A message initiation interaction module, configured to generate the message initiation interaction request when the message interaction control is triggered;

[0088] Accordingly, the display unit comprises:

[0089] The second display subunit is configured to execute displaying the target video in the non-display message content state, the object identifier of the first conversation object, and the reply control matching the target video in the conversation page.

[0090] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the above-mentioned first aspects.

[0091] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any method described in the first aspect of the embodiment of the present disclosure.

[0092] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising computer instructions, which, when executed by a processor, enable a computer to execute any one of the methods described in the first aspect of an embodiment of the present disclosure.

[0093] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0094] In response to the video generation instruction, multiple video templates are displayed. When the target video template among the multiple video templates is selected, the object information collection page is displayed; and in response to the collection confirmation instruction triggered based on the object information collection page, the target video corresponding to the target video template is displayed; the target video is obtained by replacing the template object face image with the collection object face image and replacing the template audio with the collection object audio. In this way, by replacing the face image and audio in the video template, video generation is made more efficient and flexible, thereby improving the effect of video-based interaction.

[0095] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0097] Figure 1 It is a schematic diagram of an application environment according to an exemplary embodiment.

[0098] Figure 2 The figure is a flowchart of a video generating method according to an exemplary embodiment.

[0099] Figure 3 The figure is a schematic diagram showing a plurality of video templates according to an exemplary embodiment.

[0100] Figure 4 It is a schematic diagram of an image acquisition page according to an exemplary embodiment.

[0101] Figure 5 The figure is a schematic diagram showing a process of image acquisition and audio acquisition according to an exemplary embodiment.

[0102] Figure 6 The figure is a schematic diagram showing a session page according to an exemplary embodiment.

[0103] Figure 7 It is a schematic diagram of displaying a target video in a conversation page when a message reply interaction request is triggered based on a reply control according to an exemplary embodiment.

[0104] Figure 8 It is a schematic diagram of displaying a target video in a conversation page when a message interaction request is initiated based on a message interaction control triggering message according to an exemplary embodiment.

[0105] Fig. 9 The figure is a block diagram of a video generating device according to an exemplary embodiment.

[0106] Fig.10 It is a block diagram of an electronic device for video generation according to an exemplary embodiment.

[0107] Fig.11 The invention is a block diagram of an electronic device for video generation based on an exemplary embodiment. DETAILED DESCRIPTION

[0108] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0109] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0110] See also Figure 1 , Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment. Figure 1 As shown, the application environment may include a server 01 and a terminal 02 .

[0111] In an optional embodiment, the terminal 02 can be used for display processing of video generation. Specifically, the terminal 02 can include but is not limited to smart phones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices and other types of electronic devices. Optionally, the operating system running on the electronic device can include but is not limited to Android system, IOS system, Linux, Windows, etc.

[0112] In an optional embodiment, server 01 can be used for background support of video generation. Specifically, server 01 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0113] In addition, it should be noted that Figure 1 What is shown is only one application environment of the video generation method provided by the present disclosure.

[0114] In the embodiments of this specification, the server 01 and the terminal 02 may be directly or indirectly connected via wired or wireless communication, and this application does not impose any limitation thereto.

[0115] It should be noted that the following figure shows a possible order of steps, which is not actually limited to this order. Some steps can be executed in parallel without relying on each other. The user information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data for display, training data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0116] Figure 2 FIG. 1 is a flow chart of a video generation method according to an exemplary embodiment. Figure 2 As shown, the following steps may be included.

[0117] In step S201, in response to a video generation instruction, multiple video templates are displayed.

[0118] In the embodiments of this specification, the video template may refer to a template for generating a video. As an example, it may be a template for generating a blessing video, so that a blessing video can be efficiently generated based on the video template for blessing interaction, and the present disclosure does not limit the video template.

[0119] In a possible implementation, a video generation instruction may be triggered in a multimedia application. Accordingly, in response to the video generation instruction, multiple video templates may be displayed, for example Figure 3 The multiple templates for generating blessing videos, namely video blessing templates, are shown, wherein the template contents corresponding to video templates 1 to 3 are respectively in Figure 3 Not shown.

[0120] In step S203, when a target video template among multiple video templates is selected, an object information collection page is displayed.

[0121] In actual application, any video template can be selected for video generation process, and the selected video template can be called target video template. Accordingly, when the target video template among multiple video templates is selected, the object information collection page, such as the shooting page, is displayed.

[0122] Exemplarily, the object information collection page can be used to collect facial images for subsequent replacement of the facial images of the template object in the target video template, and can be used to collect the audio of the generated video for subsequent replacement of the template audio in the target video template. The present disclosure does not limit the presentation method of the object information collection page, as long as the above-mentioned collection function can be achieved.

[0123] In step S205, in response to the acquisition confirmation instruction triggered based on the object information acquisition page, the target video corresponding to the target video template is displayed; the target video is obtained by replacing the template object facial image with the acquisition object facial image and replacing the template audio with the acquisition object audio.

[0124] Among them, the above-mentioned facial image of the acquisition object and the audio of the acquisition object are acquired based on the object information acquisition page under the acquisition confirmation instruction, the above-mentioned template object facial image is the facial image of the template object in the target video template, and the template audio is the audio in the target video template.

[0125] In actual applications, after the facial image and audio are collected, a collection confirmation instruction can be triggered. Accordingly, in response to the collection confirmation instruction triggered based on the object information collection page, the target video corresponding to the target video template can be displayed.

[0126] In response to the video generation instruction, multiple video templates are displayed. When the target video template among the multiple video templates is selected, the object information collection page is displayed; and in response to the collection confirmation instruction triggered based on the object information collection page, the target video corresponding to the target video template is displayed; the target video is obtained by replacing the template object face image with the collection object face image and replacing the template audio with the collection object audio. In this way, by replacing the face image and audio in the video template, video generation is made more efficient and flexible, thereby improving the effect of video-based interaction.

[0127] In a possible implementation, the object information acquisition page may include an image acquisition page and an audio acquisition page. Accordingly, in response to the acquisition confirmation instruction triggered based on the object information acquisition page, displaying the target video corresponding to the target video template may include:

[0128] In response to an image acquisition completion instruction triggered based on the image acquisition page, displaying a facial image of the acquisition object;

[0129] When the facial image of the acquisition object is confirmed, an audio acquisition page is displayed;

[0130] In response to an audio collection completion instruction triggered based on the audio collection page, display the audio of the collection object;

[0131] After confirming the audio of the captured object, the target video is displayed.

[0132] In the embodiments of this specification, the image acquisition page may refer to a page for acquiring an image sequence, such as a shooting page, which is not limited in this disclosure. The audio acquisition page may refer to a page for acquiring audio, such as a recording page, a shooting page, etc., which is not limited in this disclosure. By setting the image acquisition page and the audio acquisition page, facial image acquisition and audio acquisition can be performed separately, making the acquisition of object information more flexible and the operation more convenient.

[0133] In a possible implementation, the image acquisition page may display a face description input area, such as Figure 5 As shown. Accordingly, the above-mentioned acquisition of the object's facial image may include generating a facial image, that is, the facial image may be generated by AI technology based on the facial description information input in the facial description input area, and the facial image acquisition is more intelligent and flexible, and can be applied to the scene of virtual human interaction. Based on this, the above-mentioned method may also include: in response to the input completion operation of the facial description information input in the facial description input area, generating an image acquisition completion instruction. For example, click Figure 4 The "Complete" control in can be thought of as an input completion operation.

[0134] Accordingly, the above-mentioned displaying the facial image of the acquisition object in response to the image acquisition completion instruction triggered based on the image acquisition page may include: displaying the generated facial image in response to the image acquisition completion instruction. The generated facial image may use AI's Wenshengtu technology to generate a generated facial image that matches the facial description information.

[0135] In another possible implementation, the image acquisition page may refer to a page capable of taking images, so that an image of the face used to replace the video template can be taken, and image acquisition is more convenient and efficient. Based on this, the above image acquisition page may display a shooting control, such as Figure 5 51 shown in the second figure above. Capturing the facial image of the object may include shooting the facial image. Accordingly, the above-mentioned displaying the facial image of the object in response to the image acquisition completion instruction triggered based on the image acquisition page may include: displaying the shot facial image in response to the image acquisition completion instruction triggered based on the shooting control. For example, a preset operation may be performed on the shooting control to trigger the image acquisition completion instruction. The preset operation may include but is not limited to operations such as clicking and long pressing.

[0136] The above is an exemplary introduction to the image acquisition page. The following is an exemplary introduction to the audio acquisition page, wherein the audio acquisition page can be used to acquire at least one of audio content and audio timbre.

[0137] In a possible implementation, the audio collection page may display multiple preset keywords, such as Figure 5 As shown in the third figure above. Correspondingly, the above-mentioned collected object audio is the first collected audio. Based on this, the above-mentioned method may also include:

[0138] When at least one preset keyword is selected from a plurality of preset keywords and a selection confirmation operation is triggered, a first audio text and a first audio collection trigger control corresponding to the first audio text are displayed; the first audio text is generated based on at least one preset keyword. Figure 5 As shown in the upper right figure of , selecting the confirmation operation may include clicking "generate greetings", which is not limited in the present disclosure. Figure 5 As shown in the upper right figure of , selecting at least one preset keyword may include "family", "health", "happiness" and "festival". Figure 5 As shown in the lower right figure, the first audio text can be the text generated under the blessing, and the first audio acquisition trigger control can be a "confirm" control.

[0139] When the first audio collection trigger control is triggered, the audio corresponding to the first audio text is collected, and when the audio collection corresponding to the first audio text is completed, an audio collection completion instruction is generated. Exemplarily, when the first audio collection trigger control is triggered, a recording page can be displayed, such as Figure 5 As shown in the middle figure below. Thus, the audio corresponding to the first audio text can be collected on the recording page, and when the audio collection corresponding to the first audio text is completed, an audio collection completion instruction can be generated. Exemplarily, when "Finish" is clicked, the audio collection can be confirmed to be completed, and the present disclosure does not limit this.

[0140] Accordingly, the above-mentioned display of the audio of the collection object in response to the audio collection completion instruction triggered based on the audio collection page may include: in response to the audio collection completion instruction, displaying the first collected audio, the first collected audio may be the audio corresponding to the first audio text collected within the first time period; the start time of the first time period may be the time when the first audio collection trigger control is triggered, and the end time of the first time period may be the time corresponding to the audio collection completion instruction. Among them, the first collected audio may be as follows: Figure 5 As shown in 52 in the lower left figure.

[0141] By generating audio content based on keywords and combining it with the collected timbre, the audio of the target video is generated. The audio content does not need to be manually input by the user, the generation of audio content is more efficient, and the timbre can be flexibly set, making the audio of the target video more flexible and efficient.

[0142] In another possible implementation, the audio collection page may display an input area with a custom text; accordingly, the collection object audio may be the second collection audio. Based on this, the method may further include:

[0143] When it is detected that a custom text is input in the input area and the trigger text input is completed, a second audio text corresponding to the custom text and a second audio acquisition trigger control corresponding to the second audio text are displayed;

[0144] When the second audio collection trigger control is triggered, the audio corresponding to the second audio text starts to be collected, and when the audio collection corresponding to the second audio text is completed, an audio collection completion instruction is generated. Figure 5 The recording page shown in the middle picture below only displays the second audio text. The specific collection process can refer to the above corresponding content and will not be repeated here.

[0145] Accordingly, the above-mentioned display of the collected object audio in response to the audio collection completion instruction triggered based on the audio collection page may include: in response to the audio collection completion instruction, displaying the second collected audio, and the second collected audio may be the audio corresponding to the second audio text collected within the second time period; the start time of the second time period may be the time when the second audio collection trigger control is triggered, and the end time of the second time period may be the time corresponding to the audio collection completion instruction.

[0146] Among them, the present disclosure does not limit the display method of the second audio text and the second audio collection trigger control.

[0147] The audio of the target video is generated by combining customized audio content with the collected timbre. The audio content can be customized by the user without restriction, and the timbre can be flexibly set, so that the audio content of the target video can be differentiated based on different users, making the target video more personalized.

[0148] In another possible implementation, the audio acquisition page may display a preset audio text and an audio acquisition trigger control. The preset audio text may refer to a preset text for acquiring timbre, such as a paragraph of text. Accordingly, the acquisition object audio may be a third acquired audio. Based on this, the method may further include: when the audio acquisition trigger control is triggered, starting to acquire the audio corresponding to the preset audio text, and when the audio acquisition corresponding to the preset audio text is completed, generating an audio acquisition completion instruction. The audio corresponding to the preset audio text may also be acquired in Figure 5 The recording page shown in the middle picture below only displays the preset audio text. The specific collection process can refer to the above corresponding content, which will not be repeated here.

[0149] Accordingly, the above-mentioned display of the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page may include: in response to the audio acquisition completion instruction, displaying a third acquired audio, which can be obtained by replacing the timbre in the template audio with the timbre in the audio corresponding to the preset audio text when the audio acquisition trigger control is triggered. In other words, the audio content of the target video is the same as the audio content in the target video template, but the timbre is different.

[0150] By replacing the timbre in the template audio with the collected timbre, the generation of the target video is made more efficient, and the timbre in the target video can be flexibly set based on the user.

[0151] As an example, the video generation method in the embodiment of this specification can be performed in a conversation scenario. Based on this, the above method can also include: displaying a conversation page, such as Figure 6And in the conversation page, in response to a message interaction request based on a preset event, a video generation instruction can be generated.

[0152] In the embodiments of this specification, the preset event may refer to a preset event for triggering message interaction, such as a time-sensitive event, for example, a holiday greeting event, a sports event, etc., which is not limited in this disclosure. It should be noted that the embodiment of this specification uses the holiday greeting event to introduce the conversation display method, which is not limited in this disclosure.

[0153] In actual applications, the two parties of the conversation corresponding to the conversation page can interact with each other based on preset events, such as interacting with blessing messages based on holiday blessing events. Among them, the two parties of the conversation on the conversation page may include a first conversation object and a second conversation object, the first conversation object may refer to oneself, and the second conversation object may refer to the other party. In the conversation interaction based on preset events, the target application provides multiple video templates corresponding to the preset events, so that the conversation interaction based on the preset events can be more convenient and flexible. Based on this, in the conversation page, a message interaction request based on the preset event can be triggered, and accordingly, in response to the message interaction request based on the preset event, multiple video templates corresponding to the preset event can be displayed for the convenience of the conversation participants. Among them, the target application may refer to the application to which the conversation page belongs, such as a short video application, etc., which is not limited in this disclosure.

[0154] In one example, the message interaction request may be actively triggered by the first conversation object. Figure 6 As shown, it can be triggered Figure 6 61 "AI face-changing to send blessings" to generate a message interaction request.

[0155] In another example, a reply can be made based on the conversation video sent by the second conversation object based on a preset event trigger to trigger the generation of a message interaction request. Figure 6 As shown, for example, you can trigger Figure 6 62 "re-shoot" on the right side of the conversation video sent by the second conversation object to generate a message interaction request.

[0156] Correspondingly, the target video corresponding to the target video template may include: displaying the target video in a target display state in the conversation page and the object identifier of the first conversation object that sent the target video.

[0157] The target display state can be used to indicate whether to display the video content of the target video. For example, the target display state can be a message content display state, which can be seen in Figure 3 As shown in 34 and 35 in the lower left figure; the target display state is the non-display message content state, which can be seen in Figure 663 is a non-display message content state; or, the target display state can be a display message content state.

[0158] By responding to a message interaction request based on a preset event in the conversation page and triggering the generation of a video generation instruction, a convenient conversation interaction in a template manner based on preset events is achieved. In the conversation interaction, the facial image of the captured object can be used to replace the facial image of the template object in the target video template, and the audio of the captured object can be used to replace the target audio, thereby increasing the fun and richness of the conversation interaction, enriching the functions of the conversation interaction, and improving the utilization rate of conversation resources.

[0159] In a possible implementation, the conversation page may display a conversation video sent by the second conversation object and in a non-display message content state and a reply control matching the conversation video, wherein the conversation video is a conversation message based on the preset event; the message interaction request is a message reply interaction request; and the target display state is a display message content state. Exemplarily, the conversation video sent by the second conversation object and in a non-display message content state may be as follows: Figure 6 63. The reply control can be as follows Figure 6 62. Accordingly, the method may further include: generating the message reply interaction request when the reply control is triggered, that is, the message reply interaction request may be triggered based on the reply control.

[0160] Based on the above triggering message interaction request, the above displaying the target video in the target display state and the object identifier of the first session object that sent the target video in the conversation page may include: displaying the target video in the message content display state and the object identifier of the first session object that sent the target video in the conversation page, and switching the conversation video to the message content display state, for example Figure 7 As shown in the lower left figure.

[0161] In an example, the object identifier of the first conversation object may include, but is not limited to, an object avatar, an object account, an object name, etc. of the first conversation object, which is not limited in the present disclosure.

[0162] Through the above message interaction method, after replying on your side, the conversation information of both parties can be displayed in the message content status. Figure 7 As shown, at the beginning, the other party's blessing message is in the waiting state for exchange. After you reply, the blessing messages of both parties are in the display message content state. This linkage display method of session messages makes the session process richer and more flexible, and improves the utilization rate of session resources.

[0163] In a possible implementation, a conversation page may display a message interaction control that triggers a preset event; the message interaction request is a message initiation interaction request; the target display state is a non-display message content state; the method may further include: when the message interaction control is triggered, generating a message initiation interaction request.

[0164] Correspondingly, the above-mentioned display of the target video in the target display state and the object identifier of the first conversation object that sends the target video in the conversation page may include: displaying the target video in the non-display message content state, the object identifier of the first conversation object, and a reply control matching the target video in the conversation page.

[0165] For example, the message interaction control can be as follows Figure 6 As shown in 61, by triggering the message interaction control, the first conversation object can actively trigger a message interaction request instead of replying to the conversation video of the second conversation object. In this case, after the first conversation object sends the target video, it can also be similar to the conversation video sent by the second conversation object, without displaying the content, and is in a non-displaying message content state. The reply control matching the target video can be as shown in Figure 8 81 shown.

[0166] Fig. 9 is a block diagram of a video generation device according to an exemplary embodiment. Fig. 9 , the device may include:

[0167] The video template display module 901 is configured to display a plurality of video templates in response to the video generation instruction;

[0168] The information collection module 903 is configured to display an object information collection page when a target video template is selected from the multiple video templates;

[0169] The target video display module 905 is configured to execute a target video corresponding to the target video template in response to a collection confirmation instruction triggered based on the object information collection page; the target video is obtained by replacing the template object's face image with the collection object's face image and replacing the template's audio with the collection object's audio;

[0170] Among them, the facial image of the acquisition object and the audio of the acquisition object are acquired based on the object information acquisition page under the acquisition confirmation instruction, the facial image of the template object is the facial image of the template object in the target video template, and the template audio is the audio in the target video template.

[0171] In response to the video generation instruction, multiple video templates are displayed. When the target video template among the multiple video templates is selected, the object information collection page is displayed; and in response to the collection confirmation instruction triggered based on the object information collection page, the target video corresponding to the target video template is displayed; the target video is obtained by replacing the template object face image with the collection object face image and replacing the template audio with the collection object audio. In this way, by replacing the face image and audio in the video template, video generation is made more efficient and flexible, thereby improving the effect of video-based interaction.

[0172] In a possible implementation, the object information collection page includes an image collection page and an audio collection page; the target video display module 905 may include:

[0173] A captured image display unit, configured to execute an image capture completion instruction in response to being triggered based on the image capture page, and display the facial image of the captured object;

[0174] an audio collection page display unit, configured to display the audio collection page when a confirmation operation is performed on the facial image of the collection object;

[0175] A collection object audio display unit, configured to execute an audio collection completion instruction in response to being triggered based on the audio collection page, and display the collection object audio;

[0176] The target video display unit is configured to display the target video when a confirmation operation is performed on the audio of the acquisition object.

[0177] In a possible implementation, the image acquisition page displays a facial description input area, and the acquiring of the object's facial image includes generating a facial image; the device may further include:

[0178] A first acquisition completion instruction module is configured to execute an input completion operation in response to inputting facial description information in the facial description input area, and generate the image acquisition completion instruction;

[0179] Accordingly, the above-mentioned collected image display unit may include:

[0180] The generated facial image display subunit is configured to display the generated facial image in response to the image acquisition completion instruction.

[0181] In a possible implementation, the image acquisition page displays a shooting control, and the acquiring of the object's facial image includes shooting the facial image; the acquired image display unit may include:

[0182] The captured facial image display subunit is configured to execute and display the captured facial image in response to the image acquisition completion instruction triggered based on the shooting control.

[0183] In a possible implementation, the audio collection page displays a plurality of preset keywords; the collection object audio is a first collection audio; and the device may further include:

[0184] The first audio text display module is configured to display a first audio text and a first audio collection trigger control corresponding to the first audio text when at least one preset keyword is selected from the plurality of preset keywords and a selection confirmation operation is triggered; the first audio text is generated based on the at least one preset keyword;

[0185] A second acquisition completion instruction module is configured to start acquiring the audio corresponding to the first audio text when the first audio acquisition trigger control is triggered, and generate the audio acquisition completion instruction when the audio acquisition corresponding to the first audio text is completed;

[0186] Accordingly, the above-mentioned collection object audio presentation unit may include:

[0187] The first collected audio display sub-unit is configured to execute in response to the audio collection completion instruction and display the first collected audio, where the first collected audio is the audio corresponding to the first audio text collected within a first time period; the start time of the first time period is the time when the first audio collection trigger control is triggered, and the end time of the first time period is the time corresponding to the audio collection completion instruction.

[0188] In a possible implementation, the audio collection page displays an input area for a custom text; the collection object audio is a second collection audio; and the device may further include:

[0189] A second audio text display module is configured to display a second audio text corresponding to the custom text and a second audio collection trigger control corresponding to the second audio text when a custom text is input in the input area and the trigger text input is completed;

[0190] A third acquisition completion instruction module is configured to start acquiring the audio corresponding to the second audio text when the second audio acquisition trigger control is triggered, and generate the audio acquisition completion instruction when the audio acquisition corresponding to the second audio text is completed;

[0191] Accordingly, the above-mentioned collection object audio presentation unit may include:

[0192] The second collected audio display sub-unit is configured to execute in response to the audio collection completion instruction and display the second collected audio, where the second collected audio is the audio corresponding to the second audio text collected within a second time period; the start time of the second time period is the time when the second audio collection trigger control is triggered, and the end time of the second time period is the time corresponding to the audio collection completion instruction.

[0193] In a possible implementation, the audio collection page displays a preset audio text and an audio collection trigger control; the collection object audio is a third collection audio; and the device may further include:

[0194] A fourth acquisition completion instruction module is configured to start acquiring the audio corresponding to the preset audio text when the audio acquisition trigger control is triggered, and generate the audio acquisition completion instruction when the audio acquisition corresponding to the preset audio text is completed;

[0195] Accordingly, the above-mentioned collection object audio presentation unit may include:

[0196] The third collected audio display sub-unit is configured to execute in response to the audio collection completion instruction and display the third collected audio, wherein the third collected audio is obtained by replacing the timbre in the template audio by the timbre in the audio corresponding to the preset audio text when the audio collection trigger control is triggered.

[0197] In a possible implementation, the device may further include:

[0198] A session page display module, configured to execute display of a session page;

[0199] A video instruction generation module is configured to be executed in the conversation page and generate the video generation instruction in response to a message interaction request based on a preset event;

[0200] The target video display module 905 may include:

[0201] The display unit is configured to display the target video in the target display state and the object identifier of the first session object that sends the target video in the session page; the target display state is used to indicate whether the video content of the target video is displayed.

[0202] In a possible implementation, the conversation page displays a conversation video sent by the second conversation object and in a non-message content display state and a reply control matched with the conversation video, the conversation video is a conversation message based on the preset event; the message interaction request is a message reply interaction request; the target display state is a message content display state; the device may further include:

[0203] A message reply interaction module, configured to generate the message reply interaction request when the reply control is triggered;

[0204] Accordingly, the above-mentioned display unit may include:

[0205] The first display subunit is configured to display the target video in the display message content state and the object identifier of the first session object that sent the target video in the session page, and switch the session video to the display message content state.

[0206] In a possible implementation, the conversation page displays a message interaction control that triggers the preset event; the message interaction request is a message initiation interaction request; the target display state is a non-display message content state; and the device may further include:

[0207] A message initiation interaction module, configured to generate the message initiation interaction request when the message interaction control is triggered;

[0208] Accordingly, the above-mentioned display unit may include:

[0209] The second display subunit is configured to execute displaying the target video in the non-display message content state, the object identifier of the first conversation object, and the reply control matching the target video in the conversation page.

[0210] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0211] Fig.10 is a block diagram of an electronic device for video generation according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for video generation is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0212] Those skilled in the art will understand that Fig.10 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0213] Fig.11 The block diagram of an electronic device for video generation is shown based on an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for video generation is implemented.

[0214] Those skilled in the art will understand that Fig.11 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0215] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the video generation method in the embodiment of the present disclosure.

[0216] In an exemplary embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the video generation method in the embodiment of the present disclosure. The computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0217] In an exemplary embodiment, a computer program product containing instructions is also provided. When the computer program product is run on a computer, the computer is enabled to perform the video generating method in the embodiment of the present disclosure.

[0218] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0219] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0220] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A video generation method, characterized in that: include: In response to the video generation instruction, display a plurality of video templates; When a target video template among the multiple video templates is selected, displaying an object information collection page; In response to a collection confirmation instruction triggered based on the object information collection page, displaying a target video corresponding to the target video template; The target video is obtained by replacing the template object's facial image with the captured object's facial image and replacing the template's audio with the captured object's audio; Among them, the facial image of the acquisition object and the audio of the acquisition object are acquired based on the object information acquisition page under the acquisition confirmation instruction, the facial image of the template object is the facial image of the template object in the target video template, and the template audio is the audio in the target video template.

2. The method according to claim 1, characterized in that The object information acquisition page includes an image acquisition page and an audio acquisition page; the displaying of the target video corresponding to the target video template in response to the acquisition confirmation instruction triggered based on the object information acquisition page includes: In response to an image acquisition completion instruction triggered based on the image acquisition page, displaying the facial image of the acquisition object; In case of performing a confirmation operation on the facial image of the acquisition object, displaying the audio acquisition page; In response to an audio collection completion instruction triggered based on the audio collection page, displaying the collection object audio; When the audio of the acquisition object is confirmed, the target video is displayed.

3. The method according to claim 2, characterized in that The image acquisition page displays a facial description input area, and the acquiring of the facial image of the object includes generating a facial image; the method further includes: In response to the completion of the input operation of inputting the facial description information in the facial description input area, generating the image acquisition completion instruction; The step of displaying the facial image of the acquisition object in response to the image acquisition completion instruction triggered based on the image acquisition page includes: In response to the image acquisition completion instruction, the generated facial image is displayed.

4. The method according to claim 2, characterized in that: The image acquisition page displays a shooting control, and the acquiring of the facial image of the object includes shooting the facial image; and the display of the facial image of the acquired object in response to the image acquisition completion instruction triggered based on the image acquisition page includes: In response to the image acquisition completion instruction triggered based on the shooting control, the captured facial image is displayed.

5. The method according to claim 2, characterized in that: The audio collection page displays a plurality of preset keywords; the collection object audio is a first collection audio; and the method further includes: When at least one preset keyword is selected from the plurality of preset keywords and a selection confirmation operation is triggered, a first audio text and a first audio collection trigger control corresponding to the first audio text are displayed; the first audio text is generated based on the at least one preset keyword; When the first audio collection trigger control is triggered, start collecting the audio corresponding to the first audio text, and when the audio collection corresponding to the first audio text is completed, generate the audio collection completion instruction; The step of displaying the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page includes: In response to the audio collection completion instruction, the first collected audio is displayed, and the first collected audio is the audio corresponding to the first audio text collected within a first time period; the start time of the first time period is the time when the first audio collection trigger control is triggered, and the end time of the first time period is the time corresponding to the audio collection completion instruction.

6. The method according to claim 2 or 5, characterized in that: The audio collection page displays an input area for custom text; The collected audio is a second collected audio; and the method further includes: When it is detected that a custom text is input in the input area and the trigger text input is completed, displaying a second audio text corresponding to the custom text and a second audio collection trigger control corresponding to the second audio text; When the second audio collection trigger control is triggered, start collecting the audio corresponding to the second audio text, and when the audio collection corresponding to the second audio text is completed, generate the audio collection completion instruction; The step of displaying the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page includes: In response to the audio collection completion instruction, the second collected audio is displayed, and the second collected audio is the audio corresponding to the second audio text collected within a second time period; the start time of the second time period is the time when the second audio collection trigger control is triggered, and the end time of the second time period is the time corresponding to the audio collection completion instruction.

7. The method according to claim 2, characterized in that: The audio collection page displays a preset audio text and an audio collection trigger control; the collection object audio is a third collection audio; and the method further includes: When the audio collection trigger control is triggered, start collecting the audio corresponding to the preset audio text, and when the audio collection corresponding to the preset audio text is completed, generate the audio collection completion instruction; The step of displaying the audio of the acquisition object in response to the audio acquisition completion instruction triggered based on the audio acquisition page includes: In response to the audio collection completion instruction, the third collected audio is displayed. The third collected audio is obtained by replacing the timbre in the template audio by collecting the timbre in the audio corresponding to the preset audio text when the audio collection trigger control is triggered.

8. The method according to claim 1, characterized in that The method further comprises: Display the session page; In the conversation page, in response to a message interaction request based on a preset event, generating the video generation instruction; The displaying of the target video corresponding to the target video template includes: The target video in the target display state and the object identifier of the first session object that sent the target video are displayed in the session page; the target display state is used to indicate whether the video content of the target video is displayed.

9. The method according to claim 8, characterized in that The conversation page displays a conversation video sent by the second conversation object and in a non-displaying message content state, and a reply control matching the conversation video, wherein the conversation video is a conversation message based on the preset event; The message interaction request is a message reply interaction request; The target display state is the display message content state; The method further comprises: When the reply control is triggered, generating the message reply interaction request; The method of displaying the target video in the target display state and the object identifier of the first session object that sent the target video in the session page includes: The target video in the message content display state and the object identifier of the first session object that sent the target video are displayed in the session page, and the session video is switched to the message content display state.

10. The method according to claim 8, characterized in that The conversation page displays a message interaction control that triggers the preset event; the message interaction request is a message initiation interaction request; The target display state is a non-display message content state; The method further comprises: When the message interaction control is triggered, generating the message initiation interaction request; The method of displaying the target video in the target display state and the object identifier of the first session object that sent the target video in the session page includes: The target video in the non-display message content state, the object identifier of the first conversation object, and a reply control matching the target video are displayed in the conversation page.

11. A video generating device, characterized in that: include: A video template display module, configured to display a plurality of video templates in response to a video generation instruction; An information collection module is configured to display an object information collection page when a target video template among the multiple video templates is selected; A target video display module is configured to execute a collection confirmation instruction triggered based on the object information collection page in response to display a target video corresponding to the target video template; The target video is obtained by replacing the template object's facial image with the captured object's facial image and replacing the template's audio with the captured object's audio; Among them, the facial image of the acquisition object and the audio of the acquisition object are acquired based on the object information acquisition page under the acquisition confirmation instruction, the facial image of the template object is the facial image of the template object in the target video template, and the template audio is the audio in the target video template.

12. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the video generating method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the video generating method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, enable a computer to execute the video generating method according to any one of claims 1 to 10.

Images