Method, device and equipment for generating dialogue digital person, medium and product

Abstract

The invention discloses a dialogue digital person generation method and device, equipment, a medium and a product, and relates to the technical field of computers, and the method comprises the steps: displaying a digital person generation interface; obtaining a target script material in response to a material adding operation generated in the script material area; analyzing the material content of the target script material to obtain at least one dialogue role corresponding to the target script material and dialogue content corresponding to the at least one dialogue role, and displaying each dialogue role and dialogue content corresponding to each dialogue role in a script material area; displaying a digital person corresponding to the dialogue role in a preview area; and in response to a digital person synthesis operation generated in the generation area, generating a target dialogue digital person matched with the target script material according to the dialogue role and the dialogue content. According to the technical scheme, intelligent generation of the dialogue digital person is achieved, accurate matching of the dialogue role and the dialogue content of the dialogue role is guaranteed, and the scene dialogue effect of multiple dialogue roles is achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to methods, devices, equipment, media, and products for generating a conversational digital human. Background Art

[0002] At present, when generating digital humans, the focus is mainly on single-person voice-over scenarios. Although there are multiple digital humans in a video, they are all simply spliced together, making it difficult to accurately match the relationship between the video screen and the dialogue, which affects the scene dialogue effect in the video. Therefore, how to achieve intelligent generation of dialogue digital humans has become a technical problem that needs to be solved urgently. Summary of the Invention

[0003] In view of this, the present disclosure provides a method, apparatus, device, medium and product for generating a conversational digital human to solve the problem of poor generation effect of a conversational digital human.

[0004] In a first aspect, the present disclosure provides a method for generating a dialogue digital human, comprising: displaying a digital human generation interface, the digital human generation interface including a script material area, a preview area, and a generation area; obtaining a target script material in response to a material addition operation generated in the script material area; parsing the material content of the target script material to obtain at least one dialogue role corresponding to the target script material and dialogue content corresponding to at least one dialogue role, and displaying each dialogue role and the dialogue content corresponding to each dialogue role in the script material area; displaying a digital human corresponding to the dialogue role in the preview area; and generating a target dialogue digital human matching the target script material according to the dialogue role and the dialogue content in response to a digital human synthesis operation generated in the generation area.

[0005] In a second aspect, the present disclosure provides a device for generating a dialogue digital human, comprising: an interface display module for displaying a digital human generation interface, the digital human generation interface including a script material area, a preview area and a generation area; a material adding module for obtaining a target script material in response to a material adding operation generated in the script material area; a material parsing module for parsing the material content of the target script material, obtaining at least one dialogue role corresponding to the target script material and dialogue content corresponding to at least one dialogue role, and displaying each dialogue role and the dialogue content corresponding to each dialogue role in the script material area; a preview module for displaying a digital human corresponding to the dialogue role in the preview area; a digital human synthesis module for generating a target dialogue digital human matching the target script material according to the dialogue role and dialogue content in response to a digital human synthesis operation generated in the generation area.

[0006] In a third aspect, the present disclosure provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for generating a conversational digital human according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0007] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for generating a conversational digital human according to the first aspect or any corresponding embodiment thereof.

[0008] In a fifth aspect, the present disclosure provides a computer program product comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the method for generating a conversational digital human according to the first aspect or any corresponding embodiment thereof.

[0009] The methods, devices, equipment, media, and products for generating conversational digital humans provided by the embodiments of the present disclosure provide a digital human generation interface, allowing users to add script materials, preview digital humans, and generate conversational digital humans on the digital human generation interface. Thus, by simply acquiring the target script materials, the conversational characters and their conversational content can be automatically parsed directly. After the parsing is complete, the corresponding digital humans are displayed in the preview area in sequence based on the interactions of each conversational character. When it is determined that the generation of the digital human meets the requirements, the target conversational digital human matching the conversational character and the conversational content is directly generated, realizing the intelligent generation of the conversational digital human and reducing the cost of manual editing. At the same time, it ensures that each conversational character can be accurately matched with its conversational content, achieving a situational dialogue effect for multiple conversational characters, thereby accurately corresponding to the relationship between the video screen and the conversational content. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 is a schematic diagram of an application scenario according to an embodiment of the present disclosure;

[0012] Figure 2 is a flowchart of a method for generating a conversational digital human according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of a digital human generation interface according to an embodiment of the present disclosure;

[0014] Figure 4 is another schematic diagram of a digital human generation interface according to an embodiment of the present disclosure;

[0015] Figure 5 1 is a schematic diagram of a switching control for a dialogue role and an exit role according to an embodiment of the present disclosure;

[0016] Figure 6 is a schematic diagram of modification of the conversation content according to an embodiment of the present disclosure;

[0017] Figure 7 is another schematic diagram of a digital human generation interface according to an embodiment of the present disclosure;

[0018] Figure 8 is a schematic diagram of the parsing progress of the target script material according to an embodiment of the present disclosure;

[0019] Figure 9 is a schematic diagram of conversation content verification according to an embodiment of the present disclosure;

[0020] Figure 10 is a schematic diagram of a new dialogue role according to an embodiment of the present disclosure;

[0021] Figure 11 This is a schematic diagram of prohibiting the creation of the same dialogue role according to an embodiment of the present disclosure;

[0022] Figure 12 is a schematic diagram of image customization according to an embodiment of the present disclosure;

[0023] Figure 13 is a background customization schematic diagram according to an embodiment of the present disclosure;

[0024] Figure 14 is a schematic diagram of dubbing customization according to an embodiment of the present disclosure;

[0025] Figure 15 is a preview diagram of the image, background, and dubbing according to an embodiment of the present disclosure;

[0026] Figure 16 1. is a role identification and role editing diagram of a dialogue role according to an embodiment of the present disclosure;

[0027] Figure 17 is a schematic diagram of digital human switching according to an embodiment of the present disclosure;

[0028] Figure 18 It is a schematic diagram of the design of the dialogue content, exit role switching control, and dialogue role switching control according to an embodiment of the present disclosure;

[0029] Figure 19 is a schematic diagram of different states of conversation content according to an embodiment of the present disclosure;

[0030] Figure 20 is a schematic diagram of adjusting the display format according to an embodiment of the present disclosure;

[0031] Figure 21 is a schematic diagram of adjusting the playback progress according to an embodiment of the present disclosure;

[0032] Figure 22 is a schematic diagram of subtitle display adjustment according to an embodiment of the present disclosure;

[0033] Figure 23 is a schematic diagram of loading a digital human according to an embodiment of the present disclosure;

[0034] Figure 24 This is a schematic diagram of a digital human being being removed from a shelf according to an embodiment of the present disclosure;

[0035] Figure 25 is a schematic diagram of a newly created role according to an embodiment of the present disclosure;

[0036] Figure 26 is a structural block diagram of a device for generating a conversational digital human according to an embodiment of the present disclosure;

[0037] Figure 27 Schematic diagram of the hardware structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present disclosure.

[0039] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0040] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0041] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0042] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0043] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0044] When creating digital humans, the focus is primarily on single-person voiceover scenarios. Although tools exist for creating multiple digital humans in a single video, these tools often rely on simple splicing, resulting in poor interaction between the digital humans and a lack of support for switching between subjects. Alternatively, they employ multi-track editing, resulting in a high barrier to entry. Furthermore, they employ PowerPoint-style layouts, making it difficult to accurately map the relationship between the image and each sentence. This, in turn, impacts the effectiveness of the dialogue scenes in the videos.

[0045] Based on this, the technical solution disclosed in the present invention provides a unified digital human generation interface. You only need to add script materials on the digital human generation interface to automatically parse the dialogue roles and automatically match the dialogue content corresponding to the dialogue roles. The unified framework reduces the cognitive cost and the threshold for digital human generation. It can directly generate multi-dialogue role scenario dialogues and single-role oral broadcasts, ensuring that each dialogue role can be accurately matched with its dialogue content, thereby realizing the intelligent generation of dialogue digital humans.

[0046] As an optional application scenario of the embodiment of the present disclosure, Figure 1 As shown, the application scenario includes a digital human creation application 101 and an electronic device 102, where the digital human creation application 101 is deployed on the electronic device 102. Figure 1 In the figure, only limited components and exemplary connection relationships are shown. It should be understood that this is for the purpose of ease of explanation and illustration and is not intended to limit the scope of the present disclosure, and other different components may also exist. For example, a display component and an input component, etc. By way of example and not limitation, the diagnostic results of the target page can be displayed on the display component, and the problem description and problem type, etc. can be adjusted through the input component.

[0047] According to an embodiment of the present disclosure, users can add script materials through the digital human generation interface 103 provided by the digital human creation application 101. The digital human creation application 101 can automatically parse the script materials, determine the corresponding dialogue roles and dialogue content, and thus realize the intelligent generation of dialogue digital humans according to the dialogue roles and dialogue content.

[0048] Among them, the electronic device 102 represents a device with computing resources or computing capabilities, and can be a device with computing capabilities. For example, the electronic device can be provided with a processor and memory, etc., and can also be equipped with a dedicated accelerator (such as a graphics processing unit (GPU)). In addition, the electronic device can store and maintain data. Examples of the electronic device 102 may include a supercomputer, a personal computer, a laptop computer, a vehicle-mounted computing device, a mobile device (such as a smartphone, a tablet computer, etc.), or a combination of any one or more of the above devices. It should be understood that the computer device described herein is only exemplary and non-restrictive, and for example, other different types of computer devices may also be used.

[0049] According to an embodiment of the present disclosure, an embodiment of a method for generating a conversational digital human is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0050] In this embodiment, a method for generating a conversational digital human is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 2 is a flow chart of a method for generating a conversational digital human according to an embodiment of the present disclosure. Figure 2 As shown, the process includes the following steps:

[0051] Step S201: Displaying a digital human generation interface, which includes a script material area, a preview area, and a generation area.

[0052] The digital human creation interface is a human-computer interaction interface provided by the digital human creation application. Specifically, the digital human creation application is installed in the electronic device, and the user can click on the digital human creation application to enter the digital human creation interface. Figure 3 As shown, the digital human generation interface includes a script material area 301, a preview area 302, and a generation area 303. The script material area 301 is used to add script materials; the preview area 302 is used to preview the digital humans generated for each dialogue role and their corresponding dialogue content; and the generation area 303 is used to create a target dialogue digital human for a scenario dialogue or a single-person voiceover scenario based on the script materials.

[0053] Step S202: In response to the material adding operation generated in the script material area, a target script material is obtained.

[0054] The "add script" operation is triggered by the user in the script material area. The target script material is the script material used to generate a dialogue digital human, such as a scenario dialogue material or a single-person voice-over material. In one specific example, the user can trigger the "add script" operation by clicking a blank area in the script material area and then upload the corresponding target script material in accordance with the "add script" operation. In another specific example, the user can trigger the "add script" operation by triggering the "add script" control in the script material area, and then obtain the corresponding target script material in accordance with the "add script" operation.

[0055] Step S203, parse the material content of the target script material, obtain at least one dialogue role corresponding to the target script material and the dialogue content corresponding to at least one dialogue role, and display each dialogue role and the dialogue content corresponding to each dialogue role in the script material area.

[0056] Different dialogue roles correspond to different dialogue contents; the material content is the content included in the target script material, which includes at least one dialogue role and its corresponding scenario dialogue content. Specifically, the digital human creation application parses the target script material uploaded by the user, determines one or more dialogue roles contained in the material content, and the dialogue content corresponding to each dialogue role. Then, the parsed dialogue roles and their dialogue content are displayed in the script material area, where different dialogue roles have different role identifiers, such as Figure 4 shown.

[0057] Step S204: Display the digital human corresponding to the dialogue role in the preview area.

[0058] The digital human is the embodiment of the dialogue character, that is, the digital human can generate corresponding body movements or lip movements according to the dialogue content. Specifically, the preview area can display the corresponding digital human according to the dialogue character, or it can display the corresponding digital human and the dialogue content according to the dialogue character, such as Figure 4 shown.

[0059] Step S205, in response to the digital human synthesis operation generated in the generation area, a target dialogue digital human matching the target script material is generated according to the dialogue role and dialogue content.

[0060] The digital human synthesis operation is the fusion operation of the dialogue role and dialogue content triggered by the user in the generation area; the target dialogue digital human is a dialogue digital human that matches the scene of the target script material. The target dialogue digital human can be a digital human in a single-person voice-over scene, or it can be multiple dialogue digital humans participating in the dialogue in a situational dialogue scene.

[0061] Specifically, users can preview the digital human generated based on the target script material in the preview area, and preview the dialogue interactions between the various digital humans based on the dialogue content. If the digital human generation and the interactions between the digital humans meet the requirements, they can trigger the generation of the target dialogue digital human by clicking the Generate control in the Generate area. The materials are quickly synthesized according to the various dialogue roles and their corresponding dialogue content, resulting in the target dialogue digital human for the corresponding scenario.

[0062] The method for generating a conversational digital human, provided in this embodiment, provides a digital human generation interface, allowing users to add script materials, preview the digital human, and generate a conversational digital human. Thus, once the target script materials are acquired, the dialogue characters and their conversational content can be automatically parsed. Once the parsing is complete, the corresponding digital human is displayed sequentially in the preview area based on the interactions of each dialogue character. Once it is determined that the digital human generation meets the requirements, a target conversational digital human matching the dialogue character and the conversational content is directly generated, achieving intelligent generation of conversational digital humans and reducing manual editing costs. Furthermore, each dialogue character is accurately matched to its own conversational content, achieving a scenario-based dialogue effect for multiple dialogue characters, thereby accurately matching the relationship between the video image and the conversational content.

[0063] In some optional implementations, the role identification corresponding to each dialogue role and the dialogue content corresponding to each dialogue role are displayed in the script material area, including: displaying the role identification corresponding to each dialogue role in the role display area of the script material area; displaying the dialogue content corresponding to each dialogue role in the content display area of the script material area.

[0064] The role ID is a unique ID generated based on the dialogue role. Different dialogue roles have different role IDs. The role display area is used to display the role ID. The content display area is used to display the dialogue content. Specifically, Figure 4 As shown, the role display area 401 is set above the script material area, and the role identification of each dialogue role is displayed in the role display area 401. The role identification is used to distinguish the dialogue roles included in the target script material, and the role identification of each dialogue role is displayed in the role display area 401 according to a preset method, for example Figure 4 The flat display shown; the content display area 402 is set below the role display area 401, and the content display area 402 displays various dialogue roles and the dialogue content corresponding to each dialogue role.

[0065] In the above implementation, the role identifiers corresponding to the dialogue roles and the dialogue content are displayed in partitions, so that the user can intuitively view the accuracy of the parsed dialogue roles and their dialogue content.

[0066] In some optional implementations, the above method further includes: displaying description information of the character identifier at a first preset position of the character identifier; and / or displaying character dialogue parameters at a second preset position of the script material area.

[0067] The description information is a visual description of the character identifier, including the character name, character audio information, etc. The first preset position is a pre-set position for displaying the description information. Specifically, Figure 4 As shown, the role identification of each dialogue role is displayed in the role display area 401, the role name is displayed above the role identification, and the role audio information is displayed below the role identification.

[0068] The character dialogue parameters represent the dialogue parameters of the dialogue character during the dialogue process, including speech speed and volume, etc. The second preset position is a pre-set position for displaying the character dialogue parameters. Specifically, Figure 4 As shown, the speech speed and volume required by the dialogue character during the dialogue process are displayed on the right side of the character display area 401. Moreover, by triggering the speech speed, the speech speed of the dialogue character can be adjusted; by triggering the volume, the volume of the dialogue character can be adjusted.

[0069] In the above implementation, it supports displaying the description information of the role identification and the role dialogue parameters, so as to facilitate intuitive understanding of the role attributes and dialogue attributes of each dialogue role.

[0070] In some optional implementations, the above method further includes: in response to a role switching operation on the conversation content, updating the conversation role corresponding to the conversation content.

[0071] When any line of dialogue content is triggered, a role switching control is displayed at a preset position of the line of dialogue content (such as the left side of the dialogue content). The user clicks the role switching control to perform the role switching operation. Accordingly, the role switching control can respond to the user's click operation and display a role list of all dialogue roles of the target script material. The user can then update the dialogue role of the current line of dialogue content from the role list, such as Figure 5 As shown, dialogue role 1 is replaced with dialogue role 2.

[0072] In some optional implementations, the above method further includes: in response to a modification operation on the dialogue content of any dialogue role, updating the dialogue content corresponding to the dialogue role.

[0073] The modification operation is to modify the conversation content of the triggered line, including setting a blank line, modifying the content, etc. Specifically, when any line of conversation content corresponding to any dialogue role is selected, the user can edit the conversation content of that line to update the conversation content of that line; the user can also set a blank line for the conversation content of that line to deploy a blank line of conversation below the conversation content of that line, such as Figure 6 shown.

[0074] In the above implementation, it is supported to change the dialogue role corresponding to the dialogue content, realize the customized update of the dialogue role, and ensure the matching degree between the dialogue content and the dialogue role. It supports the modification of the dialogue content, which is convenient for modifying the dialogue content according to the actual dialogue scene, ensuring the adaptation of the dialogue content to the dialogue scene.

[0075] In some optional implementations, the above method further includes: in response to a clear operation on the dialogue content, deleting the dialogue content and retaining the configuration for the dialogue role; when parsing the script material again, giving priority to matching the corresponding dialogue content for the retained dialogue role.

[0076] A clear control 403 is provided in the content display area 402. The user triggers a clear operation for the conversation content by clicking the clear control 403. Figure 4 After detecting that the user triggers the clear control 403, a secondary confirmation interface pops up. If the user confirms the clearing for the second time, all the conversation contents in the content display area 402 are deleted, and at the same time, the configuration of the current conversation roles is retained.

[0077] When the target script material is obtained again, it is pasted into the script material area for material analysis to obtain the dialogue content corresponding to different dialogue characters. The dialogue content is then matched with the retained dialogue characters. If the number of retained dialogue characters does not meet the number of dialogue characters required for the dialogue content, new dialogue characters are added to match the dialogue content.

[0078] In the above implementation, the dialogue content can be cleared. When the dialogue content is cleared, the existing dialogue role configuration is retained to avoid subsequent reconfiguration, saving the dialogue role configuration time and improving the parsing efficiency of the script material.

[0079] In some optional embodiments, such as Figure 7 As shown, the script material area includes a script adding control 801. Accordingly, the above step S202 includes:

[0080] Step a1: In response to a trigger operation on a script adding control, a script material adding interface is displayed, where the script material adding interface includes at least one of a help writing control, a script library control, and a multimedia control.

[0081] Step a2, in response to a trigger operation on the script library control, displaying at least one candidate script material, and in response to a selection operation on the candidate script material, acquiring a target script material; and / or,

[0082] Step a3, in response to a trigger operation on the help writing control, displaying a script editing page, and in response to a script parameter editing operation generated on the script editing page, generating a target script material according to target script parameters determined by the script parameter editing operation; and / or,

[0083] Step a4: in response to a trigger operation on the multimedia control, display at least one candidate multimedia material, and in response to a selection operation on the candidate multimedia material, obtain a target multimedia material, and determine the target multimedia material as a target script material.

[0084] like Figure 7 As shown, a script adding control 801 is provided in the script material area, and the user can click on the script adding control 801 to trigger the adding operation of the script material. Accordingly, the script adding control 801 can respond to the user's click operation and display the script material adding interface, and the script material adding interface is provided with a help writing control 802, a script library control 803 and a multimedia control 804, as shown in FIG. Figure 7 shown.

[0085] Specifically, if the user triggers the helper control 802, a script editing page is displayed. The script editing page contains multiple script parameters to be edited. The user can edit each script parameter in the script editing page to obtain the corresponding target script parameters. The helper control 802 then uses the target script parameters as prompt information, using this prompt information to guide the corresponding material generation model of the helper control 802 to generate the target script material that matches the target script parameters.

[0086] If the user triggers the script library control 803, a display interface of a script material set is displayed, wherein the script material set includes a plurality of candidate script materials, and the user can select a desired target script material from the plurality of candidate script materials.

[0087] If the user triggers multimedia control 804, a display interface of a multimedia material collection is displayed. The multimedia material collection includes multiple candidate multimedia materials. The candidate multimedia materials can be audio materials, video materials, or image materials, which are not specifically limited here. The user can then select the desired target multimedia material from the multiple candidate multimedia materials and determine the selected target multimedia material as the target script material.

[0088] In the above implementation, it supports generating target script materials through helper controls, script library controls, and multimedia controls, thereby improving the diversity of generating target script materials.

[0089] In some optional implementations, when parsing the material content of the target script material, the above method further includes: displaying the parsing progress and parsing prompt information of the target script material in the script material area.

[0090] The parsing progress is used to represent the parsing progress of the target script material, such as 50%, 80%, etc.; the parsing prompt information represents the description information generated for the parsing progress.

[0091] like Figure 8 As shown, if the target script material includes multiple dialogue characters, then in the process of parsing the target script material, the corresponding parsing prompt information such as understanding the script content, parsing the text characters, splitting the dialogue content, matching the character images, and automatically breaking the lines will be displayed in sequence according to the parsing progress.

[0092] If the target script material only includes one dialogue character (i.e. a single character), during the parsing of the target script material, corresponding parsing prompt information such as understanding the script content, parsing the text character, matching the character image, and automatically breaking the line will be displayed in sequence according to the parsing progress.

[0093] If the target script material is a multimedia script material, then during the process of parsing the target script material, corresponding parsing prompt information such as audio separation, text conversion, text understanding, character image matching, and automatic line breaking will be displayed in sequence according to the parsing progress.

[0094] In the above implementation, the user experience is improved by displaying the parsing progress and parsing prompt information.

[0095] In some optional implementations, after completing the material content parsing for the target script material, the above method may further include:

[0096] Step b1: Verify the parsed conversation content and generate a verification result.

[0097] In step b2, if the verification result indicates that the conversation content contains non-compliant content, a prompt message is generated for the non-compliant content.

[0098] The verification result is used to indicate whether there is any non-compliant content in the parsed conversation content. If the verification result indicates that there is any non-compliant content in the conversation content, the corresponding prompt information will be displayed according to the non-compliant content, such as Figure 9 It shows "The script contains sensitive words for digital people, please modify it before continuing", "There are risky words in the script, which have been highlighted, please modify it before use".

[0099] It should be noted that when non-compliant content exists, the generation control in the generation area is set to a disabled state. When the user triggers the generation control, a script error is prompted.

[0100] It should be noted that if the parsing failure is caused by network reasons, then a corresponding prompt message will be generated in the content display area 402 of the script material area, such as "the network is unstable, resulting in parsing interruption, it is recommended to try again later".

[0101] In the above implementation, the conversation content is verified so as to prompt non-compliant content, thereby ensuring the compliance and security of the parsed conversation content.

[0102] In some optional embodiments, such as Figure 12 As shown, a role adding control 404 is provided in the script material area, and a new dialogue role is added through the role adding control 404. Accordingly, the above method further includes:

[0103] Step c1, in response to a trigger operation for adding a control to a character, displaying a character configuration interface, the character configuration interface including an image configuration control, a background configuration control, and a dubbing configuration control;

[0104] Step c2, in response to a trigger operation on the image configuration control, displaying at least one candidate image, and in response to a selection operation on the candidate image, determining a target image;

[0105] Step c3, in response to a trigger operation on the background configuration control, displaying at least one candidate background, and in response to a selection operation on the candidate background, determining a target background;

[0106] Step c4, in response to a trigger operation on the dubbing configuration control, displaying at least one candidate dubbing, and in response to a selection operation on the candidate dubbing, determining a target dubbing;

[0107] Step c5: fuse the target image, target background, and target dubbing to create a digital human corresponding to the dialogue character.

[0108] like Figure 10 As shown, a character adding control 404 is provided in the script material area, and the user can click on the character adding control 404 to trigger the creation of the dialogue character. Accordingly, the character adding control 404 can respond to the user's click operation and display the character configuration interface 405, and the character configuration interface 405 is provided with an image configuration control 406, a background configuration control 407 and a dubbing configuration control 408. Among them, the setting positions of the image configuration control 406, the background configuration control 407 and the dubbing configuration control 408 can be set according to actual needs and are not specifically limited here. Figure 10As shown, an image configuration control 406 , a background configuration control 407 , and a voiceover configuration control 408 may be set at the top of the character configuration interface 405 .

[0109] Specifically, if Figure 10 As shown, if the user triggers the image configuration control 406, a candidate image set is displayed, wherein the candidate image set includes multiple candidate images. The user can then select the candidate image of interest as the target image from the multiple candidate images.

[0110] like Figure 10 As shown, if the user triggers the background configuration control 407, a candidate background set is displayed, wherein the candidate background set includes multiple candidate backgrounds. The user can then select a candidate background of interest from the multiple candidate backgrounds as a target background.

[0111] like Figure 10 As shown, if the user triggers the dubbing configuration control 408, a candidate dubbing set is displayed, in which a plurality of candidate dubbings are provided. The user can then select the candidate dubbing of interest as the target dubbing from the plurality of candidate dubbings.

[0112] Accordingly, the target image, target background and target dubbing are combined and configured to complete the creation of the digital person corresponding to the dialogue role.

[0113] In the above implementation, adaptive configuration of the dialogue character is supported according to the image configuration control, background configuration control and dubbing configuration control, thereby improving the flexibility of creating the dialogue character.

[0114] In some optional implementations, the above method further includes: when the creation of the same dialogue role is detected, prohibiting the creation of the same dialogue role, and generating creation prompt information for the same dialogue role.

[0115] Check whether the currently created dialogue character is the same as the existing dialogue character in terms of image, background and voiceover. If it is determined that the currently created dialogue character is the same as the existing dialogue character in terms of image, background and voiceover, it means that the currently created dialogue character is the same as the existing dialogue character. At this time, the control character generation control is disabled to prohibit the creation of the same dialogue character, such as Figure 11 At the same time, when the user triggers the role generation control (such as hovering over the role generation control), a corresponding creation prompt message is generated, such as "The same role already exists, please do not create it again."

[0116] In the above implementation, by prohibiting the creation of identical dialogue roles, the accuracy of dialogue role creation is ensured.

[0117] In some optional embodiments, the above method further includes:

[0118] Step d1, in response to the selection operation for the dialogue character, displaying the character configuration interface, the character configuration interface includes an image configuration control, a background configuration control and a dubbing configuration control.

[0119] Step d2, in response to the character configuration modification generated in the character configuration interface, obtaining an updated dialogue character; the character configuration modification includes at least one of image modification, background modification and dubbing modification.

[0120] When the user selects the character ID corresponding to any created dialogue character, the character configuration interface 405 is displayed. The character configuration interface 405 is provided with an image configuration control 406, a background configuration control 407, and a dubbing configuration control 408. Among them, the image configuration control 406 is used to update the image parameters, the background configuration control 407 is used to update the background parameters, and the dubbing configuration control 408 is used to update the dubbing parameters. Figure 10 shown.

[0121] When the user triggers any one of the image configuration control 406, the background configuration control 407 and the dubbing configuration control 408, the image modification, background modification or dubbing modification of the dialogue character is triggered, and the dialogue character with the modified character configuration is obtained.

[0122] In the above implementation, image modification, background modification and dubbing modification of the dialogue characters are supported, which improves the modification flexibility of the dialogue characters.

[0123] In some optional embodiments, such as Figure 3 As shown, when creating a dialogue character for the first time, the script material area includes an image initialization control 305, a background initialization control 306, and a dubbing initialization control 307. Accordingly, the above method further includes:

[0124] Step e1, in response to a trigger operation on the image initialization control, displaying the image configuration interface in the character configuration interface, and in response to an image parameter configuration operation generated in the image configuration interface, performing image customization according to target image parameters determined by the image parameter configuration operation to generate an initialized character image;

[0125] Step e2, in response to a trigger operation on the background initialization control, displaying the background configuration interface in the character configuration interface, and in response to a background parameter configuration operation generated in the background configuration interface, customizing the background according to the target image parameters determined by the background parameter configuration operation to generate an initialization background;

[0126] Step e3, in response to a trigger operation on the dubbing initialization control, displaying the dubbing configuration interface in the character configuration interface, and in response to a dubbing parameter configuration operation generated in the dubbing configuration interface, performing dubbing customization according to target dubbing parameters determined by the dubbing parameter configuration operation, and generating an initialized dubbing;

[0127] Step e4, based on the fusion configuration of the initialized character image, the initialized background and the initialized dubbing, obtains the dialogue character created for the first time.

[0128] The location of the image initialization control 305, the background initialization control 306 and the dubbing initialization control 307 can be set according to actual needs and is not specifically limited here. Figure 3 As shown, the image initialization control 305, the background initialization control 306 and the dubbing initialization control 307 can be set at the top of the script material area.

[0129] When creating a dialogue character for the first time, if the user triggers the image initialization control 305, the image configuration interface will be displayed in the character configuration interface. The image configuration interface includes multiple candidate images and image parameter configuration for each candidate image. The user can configure the image parameters in the image configuration interface. Correspondingly, the image configuration interface can respond to the image material screening, image customization and other image parameter configuration operations generated in the image configuration interface, determine the corresponding target image parameters, and customize the image according to the target image parameters to generate the initialized character image. Figure 12 shown.

[0130] If the user triggers the background initialization control 306, the background configuration interface is displayed in the character configuration interface, which includes multiple candidate backgrounds and background parameter configurations for each candidate background. The user can configure the background parameters in the background configuration interface. Correspondingly, the background configuration interface can respond to the background parameter configuration operations such as background type screening, background material screening, and background generation generated in the background configuration interface, determine the corresponding target background parameters, and customize the background according to the target background parameters to generate an initialization background, such as Figure 13 shown.

[0131] If the user triggers the dubbing initialization control 307, the dubbing configuration interface is displayed in the character configuration interface, which includes multiple candidate dubbings and dubbing parameter configurations for each candidate dubbing. The user can configure the dubbing parameters in the dubbing configuration interface. Accordingly, the dubbing configuration interface can respond to the dubbing parameter configuration operations such as dubbing cloning and dubbing material screening generated in the dubbing configuration interface, determine the corresponding target dubbing parameters, and customize the background according to the target dubbing parameters to generate the initialization dubbing, such as Figure 14 shown.

[0132] Accordingly, the initialization character image, initialization background and initialization dubbing are combined and configured to complete the creation of the initialization dialogue character.

[0133] In the above implementation, it is supported to initialize the creation of the dialogue character according to the image initialization control, the background initialization control and the dubbing initialization control, so as to realize the customized generation of the dialogue character.

[0134] In some optional implementations, the above method further includes: in response to a triggering operation on the current image, previewing the action of the current image.

[0135] like Figure 15 As shown, when browsing various images in the image configuration interface, when you browse to an image you are interested in, you can hover over the current image for a preset time (such as 300ms) to preview the action effects of the current image.

[0136] In some optional implementations, the method further includes: in response to a trigger operation on the current background, previewing the current background; if there is a selected image, previewing the selected image in combination with the current background.

[0137] like Figure 15 As shown, when browsing various backgrounds in the background configuration interface and browsing to a background of interest, you can hover over the current background for a preset time (such as 300ms) to preview the current background in large format. Furthermore, if there is a selected image, the selected image is merged with the current background, and the fused result is previewed. Of course, the preview here can be dynamic or static, and those skilled in the art can determine it based on actual needs.

[0138] In some optional implementations, the above method further includes: in response to a selection operation on the current dubbing, playing the current dubbing and displaying timbre attribute information corresponding to the current dubbing.

[0139] like Figure 15 As shown, when browsing various dubbings in the dubbing configuration interface, when you browse to the dubbing you are interested in, you can select the current dubbing, and the current dubbing will be played, and the dubbing logo (such as dubbing avatar) corresponding to the current dubbing will move up, and the timbre attribute information will be displayed below the dubbing logo. The timbre attribute information is used to characterize the timbre characteristics of the current dubbing, including main copy information (such as energetic female voice, etc.) and sub-copy information (such as relaxed and bright, etc.). When the length of the timbre attribute information exceeds the preset length, only the content of the preset length is displayed. Of course, the dubbing logo (such as dubbing avatar) can also move to other directions and display the timbre attribute information in other locations, which is not specifically limited here. Further, if there is no sub-copy, only the main copy information is displayed.

[0140] In the above implementation, it supports previewing the actions of each image in the image configuration interface so that the desired image can be selected through preview; it supports previewing the actions of each background in the background configuration interface so that the desired background can be selected through preview, and it also supports previewing the combination of background and image so as to determine whether the selected background and the selected image are compatible; it supports playing each dubbing in the dubbing configuration interface so that the desired dubbing can be selected through playback preview.

[0141] In some optional implementations, the above method further includes: in response to different trigger operations generated for the dialogue role, displaying the role status of the dialogue role according to different trigger operations; and in response to dialogue role editing operations generated in different role statuses, editing the dialogue role.

[0142] After the creation of the dialogue role is completed, the role identifier of the dialogue role has different triggering methods, and different triggering methods will display different role states. Therefore, different editing operations can be performed on the role identifier in different role states. Specifically, if a role identifier is clicked and selected, the conversation content corresponding to the role identifier will be highlighted in the content display area 402. The user can then check whether the highlighted conversation content is accurate and modify it if it is inaccurate. If the role identifier is hovered over, operation controls for the dialogue role, such as delete control and edit control, will be displayed, and the user can then delete or modify the dialogue role.

[0143] In the above implementation, different role states are displayed through different triggers, so that the dialogue roles can be edited according to the different role states, thereby achieving flexible adjustment of the dialogue roles.

[0144] In some optional embodiments, the above method also includes: when the number of dialogue characters reaches a first preset value, displaying the role identification corresponding to each dialogue character at a first preset position in the script material area in a preset manner; when the number of dialogue characters reaches a second preset value, prohibiting the deletion of dialogue characters.

[0145] The first preset value is the number of dialogue characters allowed to be created, such as 5; the second preset value is the minimum number of dialogue characters allowed to be created, such as 1; and the preset mode is the display method of the dialogue characters in the script material area, such as flat folding, independent management, etc. The first preset value, the second preset value, and the preset mode are not specifically limited here, and those skilled in the art can determine them based on actual needs.

[0146] like Figure 16As shown, when the number of created dialogue roles reaches a first preset value, the role identifiers corresponding to the respective dialogue roles can be displayed in a folded-to-right manner; the role identifiers corresponding to the respective dialogue roles can also be displayed in a folded-to-left manner; or they can be displayed in a flat manner.

[0147] Since dialogue characters can be deleted, when a deletion request is triggered for a dialogue character, a second confirmation pop-up appears. If the second confirmation is passed, the dialogue character is deleted. At the same time, a check is performed to see if the number of dialogue characters currently in use has reached a second preset value. If so, the deletion operation for the dialogue character will fail, meaning the dialogue character will not be deleted.

[0148] In the above implementation, the display effect of multiple dialogue roles is ensured by displaying the role identifications of multiple dialogue roles in a preset manner; deletion of dialogue roles is supported, and when the number of dialogue roles reaches a second preset value, deletion is prohibited to ensure the configuration accuracy of the dialogue roles.

[0149] In some optional implementations, displaying a digital human corresponding to a dialogue role in a preview area includes: obtaining the currently triggered target dialogue content and a target dialogue role corresponding to the target dialogue content; and displaying a digital human corresponding to the target dialogue role in the preview area.

[0150] The user can browse the conversation content in the content display area 402. When the user needs to view the display of a certain conversation in the preview area, the user can trigger the conversation (i.e., the target conversation content). At this time, the target conversation role corresponding to the conversation is analyzed, and the digital person corresponding to the target conversation role is displayed in the preview area, such as Figure 4 shown.

[0151] In the above implementation, different digital humans can be displayed according to different target dialogue roles, thereby improving the preview effect of the digital humans.

[0152] In some optional implementations, the above method further includes: obtaining an outbound character corresponding to the currently triggered target dialogue content; determining a target outbound character corresponding to the target dialogue content in response to a switching operation for the outbound character in the script material area; and displaying a digital human corresponding to the target outbound character in the preview area.

[0153] When any line of dialogue content (i.e., target dialogue content) is triggered, a character switching control is displayed at a preset position of the line of dialogue content (e.g., to the right of the dialogue content). The user clicks the character switching control to switch the character. Accordingly, the character switching control can respond to the user's click operation and display a character list of all characters in the target script material. The user can then update the character list of the target dialogue content, such as Figure 5 As shown, the outbound character A is replaced with the outbound character B. Correspondingly, the preview area will perform adaptive switching according to the switching of the outbound character, that is, the digital human corresponding to the target outbound character determined by the switching operation is displayed in the preview area, as shown in FIG. Figure 17 shown.

[0154] In the above implementation, the switching of the exiting characters is supported, which improves the flexible control of the exiting characters and ensures the dialogue effect shown in the video screen.

[0155] In some optional implementations, the dialogue content is displayed in the content display area according to a first preset width (such as a fixed width of N px); the switch control of the exit character is adaptively right-aligned according to a second preset width (such as a width of 3 characters); the switch control of the dialogue character is adaptively aligned, such as Figure 18 shown.

[0156] In some optional implementations, for each line of dialogue in the dialogue content, the role identification of the dialogue character can be displayed in front of each line of dialogue; when there are multiple lines of dialogue for a certain dialogue character, the role identification of the dialogue character can also be displayed in the first line of dialogue, and not displayed in other lines.

[0157] Each line of dialogue has different triggering methods, and different triggering methods will display different states. Therefore, in different states, different operations can be performed on each line of dialogue. Specifically, if you click to select a line of dialogue content, it will enter the selected state, at this time, the dialogue content of this line is highlighted; if you double-click to select a line of dialogue content, it will enter the editing state, at this time, you can edit the dialogue content of this line; if you hover over a line of dialogue content, you can display the dialogue role switching control and exit role switching control corresponding to the dialogue content of this line, such as Figure 19 shown.

[0158] In some optional embodiments, such as Figure 20 As shown, the preview area includes a layout control 501, a play control 502, and a subtitle control 503. The layout control 501 is used to select the display layout; the play control 502 is used to control the movement playback of the digital human; and the subtitle control 503 is used to control whether the dialogue content is displayed in the preview area.

[0159] Accordingly, the above method further includes: switching the display layout of the preview area in response to a trigger operation on the layout control. Figure 20 As shown, by triggering the layout control 501 to display the layout list, the desired layout can be selected from the layout list to update the display layout of the preview area.

[0160] Accordingly, the above method further includes: in response to a trigger operation on the play control, controlling the play of the target dialogue digital human's actions in the preview area. Figure 21 As shown, the play and pause of the digital human in the preview area are controlled by triggering the play control 502.

[0161] Accordingly, the above method further includes: displaying the dialogue content in the preview area or turning off the display of the dialogue content in response to a trigger operation on the subtitle control. Figure 22 As shown, when the subtitle control 503 is in the subtitle-on state, the display of the preview area within the dialog is turned off by triggering the subtitle control 503; when the subtitle control 503 is in the subtitle-off state, the display of the preview area within the dialog is turned on by triggering the subtitle control 503.

[0162] In the above implementation, it supports switching of display formats, which facilitates flexible adjustment of display formats according to actual needs; it supports motion playback control of the target dialogue digital human, which realizes flexible preview of the video screen where the target dialogue digital human is located; it supports turning subtitles on and off, which facilitates flexible control of the display of dialogue content in the preview area.

[0163] In some optional embodiments, the above method also includes: playing the action video of the target dialogue digital human and displaying the video playback progress control; responding to the progress adjustment operation generated on the video playback progress control, jumping to the video frame specified by the progress adjustment operation; and / or responding to the progress adjustment trigger operation generated on the video playback progress control, displaying a preview screen of the video frame specified by the progress adjustment trigger operation.

[0164] like Figure 21 As shown, by triggering the play control 502, the action video of the target dialogue digital human is played in the preview area, and the corresponding video play progress control 504 is displayed below the action video. The play progress control 504 represents the play status of the action video, such as playing, not played, finished, etc.

[0165] The video playback progress control 504 supports progress adjustment. For example, dragging the progress bar to trigger a progress adjustment operation, and the preview area can jump to the playback position determined by the progress adjustment operation to display the video frame corresponding to the playback position.

[0166] The video playback progress control 504 also supports progress adjustment triggering, such as hovering over a certain position of the progress bar to implement the progress adjustment triggering operation. At this time, a preview of the video frame specified by the progress adjustment triggering operation can be displayed in the form of a small preview above the video playback control.

[0167] In the above implementation, it supports jumping to the video frame specified by the progress adjustment operation, realizing a quick preview of the video; it supports displaying a preview screen of the video frame specified by the progress adjustment trigger operation, so as to jump to the video frame of interest for playback according to the preview screen.

[0168] In some optional embodiments, the above method further includes: displaying corresponding status prompt information in the preview area based on the loading status of the digital human; and / or, when the digital human corresponding to the dialogue character is deleted, generating a prompt information in the preview area indicating that the digital human does not exist.

[0169] like Figure 23 As shown in the figure, after the analysis of the dialogue characters and their content is completed, the corresponding digital humans are automatically generated. At this time, the digital humans will be displayed in the preview area according to the order of the dialogue content. When the digital humans are loading, the playback controls are disabled and the video playback progress control is in the "Loading" state. At this time, when the digital humans in the preview area are triggered, the corresponding status prompt information will be displayed, such as "Audio Generating, Please Wait".

[0170] like Figure 24 As shown in the figure, when a dialogue character is deleted, the corresponding digital human will also be deleted. Therefore, when the digital human is played again, a prompt message indicating that the digital human does not exist will be generated in the preview area, such as "Sorry, this digital human has been removed from the shelves."

[0171] In the above implementation, the user's preview experience is enhanced by displaying the status prompt information of the digital human or the prompt information that the digital human does not exist in the preview area.

[0172] In some optional implementations, the above method further includes: when the target script material does not exist, displaying the preview area in a preset format, and displaying prompt information at a third preset position in the preview area, the prompt information being used to prompt the user to add material to the script material area.

[0173] like Figure 3 As shown, when the target script material does not exist, that is, when creating the target script material for the first time or creating a new target script material, the preview area will be displayed in a preset format, such as a light and dark grid. At the same time, a prompt message indicating that you need to add materials will be displayed in the third preset position in the preview area (such as the upper left corner), for example, "Please enter the script matching digital human on the left first."

[0174] In the above embodiment, by displaying the preview area in a preset format and displaying prompt information for adding materials in the preview area, it is convenient to guide the user to add materials, thereby reducing the learning cost of generating digital humans.

[0175] In some optional implementations, the method further includes: in response to a subtitle content adjustment operation generated in the generation area, displaying the dialogue content in the preview area according to subtitle parameters determined by the subtitle content adjustment operation.

[0176] like Figure 3 As shown, a corresponding subtitle content adjustment control is provided in the generation area, and the user can trigger the subtitle content adjustment operation through the subtitle content adjustment control, determine the subtitle parameters selected by the subtitle content adjustment operation, and display the dialogue content in the preview area according to the subtitle parameters.

[0177] In the above implementation, the conversation content in the preview area is supported to be adjusted to ensure the display effect of the conversation content.

[0178] In some optional embodiments, such as Figure 4 As shown, the digital human generation interface includes a material parameter area, which includes multiple material controls, such as video, music, floral text, pictures, etc. Accordingly, the above method further includes: displaying candidate materials in response to a trigger operation on the material control; in response to a selection operation on the candidate material, loading the selected target material into the preview area for display;

[0179] The user can trigger any of the material controls, which will then respond to the user's triggering operation and display the corresponding candidate materials. The user can then browse the candidate materials and select the desired target material, which will then be loaded into the preview area and displayed in conjunction with the digital human.

[0180] In a specific example, a user triggers an image material control, which in turn displays candidate image materials in response to the user's triggering operation. The user can then select a desired target image material from the candidate image materials, which will then be loaded into the preview area and displayed in conjunction with the digital human.

[0181] Accordingly, the above method further includes: in response to a material adjustment operation generated in the generation area, displaying the target material in the preview area according to material parameters determined by the material adjustment operation.

[0182] When a user triggers a target material in the preview area, the material parameters will be displayed in the build area. The user can then fine-tune the target material's parameters in the build area. The build area responds to these adjustments and determines the material parameters. The preview area then displays the target material based on these parameters.

[0183] It should be noted that when the user triggers the material control, the corresponding material adjustment control will be displayed in the generation area at the same time. When the user selects the target material, the material can also be fine-tuned in the generation area.

[0184] In the above implementation, it supports adding target materials to the dialogue digital human to ensure the generation effect of the dialogue digital human; it supports modifying the target materials to ensure that the target materials in the dialogue digital human meet the needs, thereby improving the richness of the materials for generating the dialogue digital human.

[0185] In some optional embodiments, when the target script material is a single-character script material, the above method further includes: determining the target character parameters corresponding to the dialogue character in response to a switching operation on any parameter of the dialogue character's image, background, and dubbing.

[0186] like Figure 25 As shown, when the target script material is a single-character script material, there is only one dialogue character. For this dialogue character, the corresponding image, background, and voiceover will be displayed in the script material area. Users can switch the image, background, or voiceover corresponding to the dialogue character according to actual needs, and determine the dialogue character's current image parameters, background parameters, and voiceover parameters. The image parameters, background parameters, and voiceover parameters obtained after switching are the target character parameters corresponding to the dialogue character. Subsequently, the corresponding image, background, and voiceover of the dialogue character are displayed in the script material area according to the target character parameters corresponding to the dialogue character, and the digital human corresponding to the dialogue character displayed in the preview area is updated according to the image, background, and voiceover corresponding to the target character parameters.

[0187] In the above implementation, for a single-role script material, it supports adjusting the image, background, and dubbing of the dialogue character to ensure the creation effect of the dialogue character.

[0188] In some optional implementations, when the target script material is a single-character script material, the above method further includes: in response to a character creation operation for any line of dialogue content, creating a dialogue digital human corresponding to any line of dialogue content.

[0189] When the target script material is a single-role script material, you can also create a new dialogue role for any line of dialogue content. Figure 25As shown, when any line of dialogue content is triggered, a new character control 701 is displayed. The user can click on this control to trigger the character creation operation. Accordingly, a character configuration interface pops up, where the user can configure the corresponding image, background, and voiceover for the new dialogue character. Following the configuration of the image, background, and voiceover for the new dialogue character, the corresponding dialogue digital human is created and displayed in the preview area. For the relevant operations for configuring the image, background, and voiceover, please refer to the corresponding description of the above embodiment and will not be repeated here.

[0190] In the above implementation, for single-role script materials, the creation of dialogue roles is supported, flexible creation of dialogue roles is achieved, and it is convenient to adjust a single role into multiple dialogue roles to achieve a situational dialogue effect with multiple dialogue roles.

[0191] This embodiment also provides a device for generating a conversational digital human, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0192] This embodiment provides a device for generating a dialogue digital human, such as Figure 26 Shown, including:

[0193] The interface display module 901 is used to display the digital human generation interface, which includes a script material area, a preview area and a generation area.

[0194] The material adding module 902 is used to obtain target script material in response to a material adding operation generated in the script material area.

[0195] The material analysis module 903 is used to analyze the material content of the target script material, obtain at least one dialogue role corresponding to the target script material and the dialogue content corresponding to at least one dialogue role, and display each dialogue role and the dialogue content corresponding to each dialogue role in the script material area.

[0196] The preview module 904 is used to display the digital human corresponding to the dialogue role in the preview area.

[0197] The digital human synthesis module 905 is used to generate a target dialogue digital human that matches the target script material according to the dialogue role and dialogue content in response to the digital human synthesis operation generated in the generation area.

[0198] In some optional implementations, the material parsing module 903 includes:

[0199] The role identification display unit is used to display the role identification corresponding to each dialogue role in the role display area of the script material area.

[0200] The dialogue content display unit is used to display the dialogue content corresponding to each dialogue role in the content display area of the script material area.

[0201] In some optional embodiments, the above device further includes:

[0202] The information display module is used to display the description information of the role identifier at a first preset position of the role identifier; and / or display the role dialogue parameters at a second preset position of the script material area.

[0203] In some optional embodiments, the above device further includes:

[0204] The role switching module is used to update the dialogue role corresponding to the dialogue content in response to the role switching operation on the dialogue content.

[0205] The content modification module is used to update the dialogue content corresponding to any dialogue role in response to a modification operation on the dialogue content of any dialogue role.

[0206] In some optional embodiments, the above device further includes:

[0207] A content clearing module, configured to delete the conversation content in response to a clearing operation on the conversation content and retain the configuration for the conversation role;

[0208] The priority matching module is used to give priority to matching corresponding dialogue content for the retained dialogue characters when parsing the script material again.

[0209] In some optional implementations, the script material area includes a script adding control. Accordingly, the material adding module 902 includes:

[0210] The interface display unit is used to display a script material adding interface in response to a trigger operation on a script adding control, wherein the script material adding interface includes at least one of a help writing control, a script library control and a multimedia control.

[0211] The script material determination unit is used to display at least one candidate script material in response to a trigger operation on the script library control, and to obtain a target script material in response to a selection operation on the candidate script material.

[0212] The script editing unit is used to display the script editing page in response to the trigger operation of the help writing control, and generate the target script material according to the target script parameters determined by the script parameter editing operation in response to the script parameter editing operation generated on the script editing page.

[0213] The multimedia material determination unit is used to display at least one candidate multimedia material in response to a trigger operation on the multimedia control, and to obtain a target multimedia material in response to a selection operation on the candidate multimedia material, and to determine the target multimedia material as a target script material.

[0214] In some optional implementations, the material parsing module 903 further includes:

[0215] The parsing status display unit is used to display the parsing progress and parsing prompt information of the target script material in the script material area.

[0216] In some optional implementations, the material parsing module 903 further includes:

[0217] The verification unit is used to verify the parsed conversation content and generate a verification result.

[0218] The first prompt unit is configured to generate prompt information for the non-compliant content if the verification result indicates that the conversation content contains non-compliant content.

[0219] In some optional implementations, the script material area includes a role adding control, and accordingly, the above-mentioned device further includes:

[0220] The first role configuration display module is used to display a role configuration interface in response to a trigger operation for adding controls to a role. The role configuration interface includes an image configuration control, a background configuration control, and a dubbing configuration control.

[0221] The target image determination module is configured to display at least one candidate image in response to a trigger operation on the image configuration control, and to determine a target image in response to a selection operation on the candidate image.

[0222] The target background determination module is configured to display at least one candidate background in response to a trigger operation on the background configuration control, and determine a target background in response to a selection operation on the candidate background.

[0223] The target dubbing determination module is configured to display at least one candidate dubbing in response to a trigger operation on the dubbing configuration control, and determine a target dubbing in response to a selection operation on the candidate dubbing.

[0224] The fusion module is used to fuse the target image, target background and target dubbing to create a digital human corresponding to the dialogue character.

[0225] In some optional embodiments, the above device further includes:

[0226] The role disabling module is used to prohibit the creation of the same dialogue role when the creation of the same dialogue role is detected, and generate a creation prompt message for the same dialogue role.

[0227] In some optional embodiments, the above device further includes:

[0228] The second role configuration display module is used to display a role configuration interface in response to a selection operation on a dialogue role. The role configuration interface includes an image configuration control, a background configuration control, and a dubbing configuration control.

[0229] The character configuration change module is used to obtain an updated dialogue character in response to the character configuration modification generated in the character configuration interface; the character configuration modification includes at least one of image modification, background modification and dubbing modification.

[0230] In some optional implementations, when creating a dialogue character for the first time, the script material area includes an image initialization control, a background initialization control, and a dubbing initialization control; the above-mentioned device further includes:

[0231] The image customization module is used to respond to the trigger operation of the image initialization control, display the image configuration interface in the character configuration interface, and respond to the image parameter configuration operation generated in the image configuration interface, customize the image according to the target image parameters determined by the image parameter configuration operation, and generate an initialized character image.

[0232] The background customization module is used to respond to the trigger operation of the background initialization control, display the background configuration interface in the character configuration interface, and respond to the background parameter configuration operation generated in the background configuration interface, customize the background according to the target image parameters determined by the background parameter configuration operation, and generate an initialization background.

[0233] The dubbing customization module is used to respond to the trigger operation of the dubbing initialization control, display the dubbing configuration interface in the role configuration interface, and respond to the dubbing parameter configuration operation generated in the dubbing configuration interface, customize the dubbing according to the target dubbing parameters determined by the dubbing parameter configuration operation, and generate the initialization dubbing;

[0234] A configuration fusion module is used to obtain a dialogue character created for the first time based on the fusion configuration of the initial character image, the initial background and the initial dubbing.

[0235] In some optional embodiments, the above device further includes:

[0236] The first preview module is configured to preview the action of the current image in response to a trigger operation on the current image.

[0237] A second preview module is configured to preview the current background in response to a trigger operation on the current background; if there is a selected image, the selected image and the current background are combined for preview;

[0238] The third preview module is used to play the current dubbing and display the timbre attribute information corresponding to the current dubbing in response to the selection operation on the current dubbing.

[0239] In some optional embodiments, the above device further includes:

[0240] The role status display module is used to respond to different trigger operations generated for the dialogue role and display the role status of the dialogue role according to different trigger operations.

[0241] The editing module is used to edit the dialogue role in response to the dialogue role editing operation generated in different role states.

[0242] In some optional embodiments, the above device further includes:

[0243] A first display module is configured to display the role identifiers corresponding to the respective dialogue roles at the first preset position in the script material area according to a preset method when the number of dialogue roles reaches a first preset value;

[0244] The deletion prohibition module is used to prohibit the deletion of the dialogue role when the number of the dialogue roles reaches a second preset value.

[0245] In some optional implementations, the preview module 904 includes:

[0246] The target role acquisition unit is used to acquire the currently triggered target dialogue content and the target dialogue role corresponding to the target dialogue content.

[0247] The digital human preview unit is used to display the digital human corresponding to the target dialogue role in the preview area.

[0248] In some optional implementations, the preview module 904 further includes:

[0249] The exit role acquisition unit is used to acquire the exit role corresponding to the currently triggered target dialogue content.

[0250] An exit character switching unit, configured to determine a target exit character corresponding to a target dialogue content in response to a switching operation on an exit character in the script material area;

[0251] The exit determination unit is used to display the digital human corresponding to the target exit role in the preview area.

[0252] In some optional implementations, the preview area includes a layout control, a play control, and a subtitle switch control, and the apparatus further includes:

[0253] The layout determination module is used to switch the display layout of the preview area in response to a triggering operation on the layout control.

[0254] The playback control module is used to control the playback of the target dialogue digital human's actions in the preview area in response to a trigger operation on the playback control.

[0255] The subtitle control module is used to display the dialogue content in the preview area or turn off the display of the dialogue content in response to a trigger operation on the subtitle control.

[0256] In some optional embodiments, the above device further includes:

[0257] The progress display module is used to play the action video of the target dialogue digital human and display the video playback progress control.

[0258] The jump module is used to jump to the video frame specified by the progress adjustment operation in response to the progress adjustment operation generated on the video playback progress control.

[0259] The screen preview module is used to respond to the progress adjustment trigger operation generated on the video playback progress control and display the preview screen of the video frame specified by the progress adjustment trigger operation.

[0260] In some optional embodiments, the above device further includes:

[0261] The status loading prompt module is used to display corresponding status prompt information in the preview area based on the loading status of the digital human.

[0262] The non-existence prompt module is used to generate a prompt message in the preview area that the digital human does not exist when the digital human corresponding to the dialogue role is deleted.

[0263] In some optional embodiments, the above device further includes:

[0264] The preview display control module is used to display the preview area in a preset format when the target script material does not exist, and to display prompt information at the third preset position of the preview area, the prompt information being used to prompt the user to add materials to the script material area.

[0265] In some optional embodiments, the above device further includes:

[0266] The subtitle adjustment module is used to respond to the subtitle content adjustment operation generated in the generation area and display the dialogue content in the preview area according to the subtitle parameters determined by the subtitle content adjustment operation.

[0267] In some optional implementations, the digital human generation interface includes a material parameter area, which includes a plurality of material controls; and the above-mentioned apparatus further includes:

[0268] A candidate display module, configured to display candidate materials in response to a trigger operation on a material control;

[0269] The target material determination module is used to load the selected target material into the preview area for display in response to a selection operation on the candidate material; and / or, in response to a material adjustment operation generated in the generation area, display the target material in the preview area according to the material parameters determined by the material adjustment operation.

[0270] In some optional implementations, when the target script material is a single-role script material, the apparatus further includes:

[0271] a target parameter determination module for determining target character parameters corresponding to a dialogue character in response to a switching operation on any parameter of the dialogue character's image, background, and dubbing;

[0272] The role creation module is used to respond to the role creation operation for any line of dialogue content and create a dialogue digital person corresponding to any line of dialogue content.

[0273] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0274] The device for generating a conversational digital human provided in the embodiments of the present disclosure can execute the conversational digital human generation method provided in any embodiment of the present disclosure, and possesses the corresponding functional modules and beneficial effects of the execution method. By providing a digital human generation interface, users can add script materials, preview digital humans, and generate conversational digital humans on the digital human generation interface. Thus, simply by acquiring the target script materials, the dialogue characters and their conversation content can be automatically parsed. After the parsing is complete, the corresponding digital humans are displayed in the preview area based on the interactions of each dialogue character. When it is determined that the digital human generation meets the requirements, the target conversational digital human matching the dialogue character and the conversation content is directly generated, achieving intelligent generation of conversational digital humans and reducing manual editing costs. At the same time, each dialogue character is ensured to be accurately matched to its conversation content, achieving a scenario-based dialogue effect for multiple dialogue characters, thereby accurately matching the relationship between the video image and the conversation content.

[0275] Figure 27 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

[0276] The following specific reference Figure 27, which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a memory 1008 into a random access memory (RAM) 1003. Various programs and data required for the operation of the electronic device are also stored in the RAM 1003. The processor 1001, ROM 1002, and RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0277] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 27 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all of the devices shown, and more or fewer devices may be implemented or possessed instead.

[0278] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 1009, or installed from the memory 1008, or installed from the ROM 1002. When the computer program is executed by the processor 1001, the above-mentioned functions defined in the method for generating a conversational digital human in the embodiment of the present disclosure are performed.

[0279] Figure 27 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0280] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded via a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor or hardware, the method for generating a conversational digital human shown in the above embodiment is implemented.

[0281] A portion of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes but is not limited to a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0282] Although the embodiments of the present disclosure have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for generating a conversational digital human, characterized in that: The method comprises: Displaying a digital human generation interface, the digital human generation interface including a script material area, a preview area, and a generation area; In response to a material adding operation generated in the script material area, obtaining a target script material; Parsing the material content of the target script material to obtain at least one dialogue role corresponding to the target script material and the dialogue content corresponding to the at least one dialogue role, and displaying each of the dialogue roles and the dialogue content corresponding to each of the dialogue roles in the script material area; Displaying the digital human corresponding to the dialogue role in the preview area; In response to the digital human synthesis operation generated in the generation area, a target dialogue digital human matching the target script material is generated according to the dialogue role and the dialogue content.

2. The method according to claim 1, characterized in that The displaying of each of the dialogue characters and the dialogue content corresponding to each of the dialogue characters in the script material area includes: Displaying the role identification corresponding to each of the dialogue roles in the role display area of the script material area; The dialogue content corresponding to each of the dialogue characters is displayed in the content display area of the script material area.

3. The method according to claim 2, characterized in that Also includes: Displaying description information of the role identifier at a first preset position of the role identifier; And / or, displaying character dialogue parameters at a second preset position in the script material area.

4. The method according to claim 2, characterized in that Also includes: In response to a role switching operation on the conversation content, updating the conversation role corresponding to the conversation content; And / or, in response to a modification operation on the dialogue content of any of the dialogue roles, updating the dialogue content corresponding to the dialogue role.

5. The method according to any one of claims 1 to 4, characterized in that Also includes: In response to a clear operation on the conversation content, deleting the conversation content and retaining the configuration for the conversation role; When parsing the script material again, priority is given to matching the corresponding dialogue content for the retained dialogue characters.

6. The method according to claim 1, characterized in that The script material area includes a script adding control; the target script material is obtained in response to the material adding operation generated in the script material area, including: In response to a triggering operation on the script adding control, displaying a script material adding interface, wherein the script material adding interface includes at least one of a help writing control, a script library control, and a multimedia control; In response to a trigger operation on a script library control, displaying at least one candidate script material, and in response to a selection operation on the candidate script material, acquiring the target script material; and / or, In response to a triggering operation on the help writing control, a script editing page is displayed, and in response to a script parameter editing operation generated on the script editing page, the target script material is generated according to the target script parameters determined by the script parameter editing operation; and / or, In response to a triggering operation on the multimedia control, at least one candidate multimedia material is displayed, and in response to a selection operation on the candidate multimedia material, a target multimedia material is acquired and the target multimedia material is determined as the target script material.

7. The method according to claim 1 or 6, characterized in that When parsing the material content of the target script material, it also includes: The parsing progress and parsing prompt information of the target script material are displayed in the script material area.

8. The method according to claim 1 or 6, characterized in that Also includes: Verifying the parsed conversation content and generating a verification result; If the verification result indicates that the conversation content contains non-compliant content, a prompt message is generated for the non-compliant content.

9. The method according to claim 1, characterized in that The script material area includes a role adding control, and the method further includes: In response to a triggering operation of adding a control for the character, displaying a character configuration interface, the character configuration interface including an image configuration control, a background configuration control, and a dubbing configuration control; In response to a trigger operation on the image configuration control, display at least one candidate image, and in response to a selection operation on the candidate image, determine a target image; In response to a trigger operation on the background configuration control, display at least one candidate background, and in response to a selection operation on the candidate background, determine a target background; In response to a trigger operation on the dubbing configuration control, displaying at least one candidate dubbing, and in response to a selection operation on the candidate dubbing, determining a target dubbing; The target image, the target background and the target dubbing are integrated to create a digital human corresponding to the dialogue character.

10. The method according to claim 9, characterized in that Also includes: When the creation of the same dialogue role is detected, the creation of the same dialogue role is prohibited, and creation prompt information for the same dialogue role is generated.

11. The method according to claim 9, characterized in that Also includes: In response to a selection operation on the dialogue character, displaying a character configuration interface, the character configuration interface including an image configuration control, a background configuration control, and a dubbing configuration control; In response to the character configuration modification generated in the character configuration interface, the updated dialogue character is obtained; the character configuration modification includes at least one of image modification, background modification and dubbing modification.

12. The method according to claim 1, characterized in that When the dialogue character is created for the first time, the script material area includes an image initialization control, a background initialization control, and a dubbing initialization control; the method further includes: In response to a trigger operation on the image initialization control, an image configuration interface in the character configuration interface is displayed, and in response to an image parameter configuration operation generated in the image configuration interface, the image is customized according to target image parameters determined by the image parameter configuration operation to generate an initialized character image; In response to a trigger operation on the background initialization control, a background configuration interface in the character configuration interface is displayed, and in response to a background parameter configuration operation generated in the background configuration interface, the background is customized according to target image parameters determined by the background parameter configuration operation to generate an initialization background; In response to a trigger operation on the dubbing initialization control, a dubbing configuration interface in the character configuration interface is displayed, and in response to a dubbing parameter configuration operation generated in the dubbing configuration interface, the dubbing is customized according to target dubbing parameters determined by the dubbing parameter configuration operation to generate an initialized dubbing; Based on the fusion configuration of the initialization character image, the initialization background and the initialization dubbing, the dialogue character created for the first time is obtained.

13. The method according to any one of claims 9 to 12, characterized in that: Also includes: In response to a trigger operation on a current image, previewing an action of the current image; and / or, In response to a trigger operation on a current background, previewing the current background; If there is a selected image, the selected image and the current background are combined for preview; and / or, In response to a selection operation on a current dubbing, the current dubbing is played and timbre attribute information corresponding to the current dubbing is displayed.

14. The method according to claim 1, wherein Also includes: In response to different triggering operations generated for the dialogue role, displaying the role status of the dialogue role according to the different triggering operations; In response to a dialogue role editing operation generated in different role states, the dialogue role is edited.

15. The method according to claim 14, characterized in that Also includes: When the number of the dialogue characters reaches a first preset value, displaying the character identifiers corresponding to the dialogue characters at the first preset position of the script material area in a preset manner; When the number of the dialogue roles reaches a second preset value, deleting the dialogue roles is prohibited.

16. The method according to claim 1, wherein The displaying of the digital human corresponding to the dialogue character in the preview area includes: Obtain the currently triggered target conversation content and the target conversation role corresponding to the target conversation content; The digital human corresponding to the target dialogue role is displayed in the preview area.

17. The method according to claim 16, characterized in that Also includes: Obtain the exit role corresponding to the target conversation content currently triggered; In response to a switching operation on the exit character in the script material area, determining a target exit character corresponding to the target dialogue content; The digital human corresponding to the target exit character is displayed in the preview area.

18. The method according to claim 16 or 17, characterized in that The preview area includes a layout control, a play control, and a subtitle switch control, and the method further includes: In response to a triggering operation on the layout control, switching the display layout of the preview area; and / or, in response to a triggering operation on the playback control, controlling the playback of the target dialogue digital human's actions in the preview area; And / or, in response to a triggering operation on the subtitle control, displaying the conversation content in the preview area, or turning off the display of the conversation content.

19. The method according to claim 16 or 17, characterized in that Also includes: Play the action video of the target dialogue digital human and display the video playback progress control; In response to a progress adjustment operation generated on the video playback progress control, jumping to a video frame specified by the progress adjustment operation; And / or, in response to a progress adjustment triggering operation generated on the video playback progress control, a preview screen of the video frame specified by the progress adjustment triggering operation is displayed.

20. The method according to claim 16, wherein Also includes: Based on the loading status of the digital human, corresponding status prompt information is displayed in the preview area; And / or, when the digital human corresponding to the dialogue role is deleted, a prompt message indicating that the digital human does not exist is generated in the preview area.

21. The method according to claim 1, wherein Also includes: When the target script material does not exist, the preview area is displayed in a preset format, and prompt information is displayed at a third preset position in the preview area, wherein the prompt information is used to prompt the script material area to add material.

22. The method according to claim 1, wherein Said also includes: In response to a subtitle content adjustment operation generated in the generation area, the dialogue content is displayed in the preview area according to subtitle parameters determined by the subtitle content adjustment operation.

23. The method according to claim 1, wherein The digital human generation interface includes a material parameter area, which includes multiple material controls; and further includes: In response to a triggering operation on the material control, displaying candidate materials; In response to a selection operation on the candidate material, the selected target material is loaded into the preview area for display; and / or, in response to a material adjustment operation generated in the generation area, the target material is displayed in the preview area according to the material parameters determined by the material adjustment operation.

24. The method according to claim 1, wherein When the target script material is a single-role script material, the method further includes: In response to a switching operation on any parameter of the dialogue character's image, background, and dubbing, determining a target character parameter corresponding to the dialogue character; And / or, in response to a role creation operation for any line of the dialogue content, a dialogue digital person corresponding to any line of the dialogue content is created.

25. A device for generating a conversational digital human, characterized in that: The device comprises: An interface display module, used to display a digital human generation interface, which includes a script material area, a preview area, and a generation area; A material adding module, configured to obtain target script material in response to a material adding operation generated in the script material area; a material parsing module, configured to parse the material content of the target script material, obtain at least one dialogue role corresponding to the target script material and the dialogue content corresponding to the at least one dialogue role, and display each of the dialogue roles and the dialogue content corresponding to each of the dialogue roles in the script material area; A preview module, configured to display the digital human corresponding to the dialogue role in the preview area; The digital human synthesis module is used to generate a target dialogue digital human that matches the target script material according to the dialogue role and the dialogue content in response to the digital human synthesis operation generated in the generation area.

26. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for generating a conversational digital human according to any one of claims 1 to 24 by executing the computer instructions.

27. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the method for generating a conversational digital human according to any one of claims 1 to 24.

28. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for generating a conversational digital human according to any one of claims 1 to 24.

Images