Interactive content generation method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to an interactive content generation method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining a dialogue between a user and a virtual object, determining a plot node in the dialogue, and generating an initial plot tree; generating a plurality of candidate plots at the plot node, and generating a plot branch leading to each plot result according to a target plot selected by the user in the plurality of candidate plots and at least one plot result input by the user; the plot branches and the initial plot tree are combined, a target plot tree is obtained, and the target plot tree serves as a script. According to the method, the plot tree is generated in a man-machine conversation mode, and the generation efficiency can be improved; according to the method, key plot nodes are extracted, various plot trends are predicted, and a plurality of plot branches are automatically generated according to the plot trends and the outcome selected by the user, so that dynamic plot branch generation can be realized, and rich diversity is provided for content creation.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to an interactive content generation method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] With the rapid development of artificial intelligence and natural language processing technologies, the form of human-computer interaction has gradually changed from a single command-based interaction to a more natural and immersive dialogue interaction. As important forms in the digital entertainment field, interactive games and interactive novels are favored by more and more users.

[0003] However, the production of existing interactive games and interactive novels mainly relies on professional teams, with a long production cycle and low efficiency. Summary of the Invention

[0004] The present disclosure provides an interactive content generation method, apparatus, electronic device, computer-readable storage medium, and computer program product to at least solve the problem of low generation efficiency of interactive content in related technologies. The technical solutions of the present disclosure are as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, an interactive content generation method is provided, including:

[0006] Obtaining a conversation between a user and a virtual object, determining plot nodes in the conversation, and generating an initial plot tree;

[0007] Generating a plurality of candidate plots at the plot nodes;

[0008] Generating plot branches leading to each of the plot endings according to a target plot selected by the user from the plurality of candidate plots and at least one plot ending input by the user;

[0009] Performing a merging process on the plot branches and the initial plot tree to obtain a target plot tree, and using the target plot tree as a script.

[0010] In an exemplary embodiment, the determining plot nodes in the conversation includes:

[0011] Performing semantic analysis and sentiment analysis on the conversation to obtain nodes that affect the plot direction;

[0012] Using the nodes that affect the plot direction as the plot nodes in the conversation.

[0013] In an exemplary embodiment, after performing the merging process on the plot branches and the initial plot tree to obtain a target plot tree, the method further includes:

[0014] Display the target plot tree; the target plot tree includes multiple plot nodes, and each plot node is connected by a directed edge;

[0015] Update the target plot tree based on an editing operation on any plot node in the target plot tree.

[0016] In an exemplary embodiment, the updating the target plot tree based on an editing operation on any plot node in the target plot tree includes:

[0017] When the editing operation is to add a plot node, determine the associated plot nodes of the newly added plot node;

[0018] Generate supplementary plot content between the newly added plot node and the associated plot nodes;

[0019] Update the target plot tree according to the newly added plot node and the supplementary plot content.

[0020] In an exemplary embodiment, the updating the target plot tree based on an editing operation on any plot node in the target plot tree further includes:

[0021] Based on a moving operation on the any plot node, adjust the order and structure of the plot branches of the target plot tree to update the target plot tree.

[0022] In an exemplary embodiment, the updating the target plot tree based on an editing operation on any plot node in the target plot tree further includes:

[0023] Based on a deletion operation on the any plot node, synchronously delete the plot nodes in the target plot tree affected by the any plot node to update the target plot tree;

[0024] Alternatively, based on a deletion operation on the any plot node, update the plot between the previous plot node and the next plot node of the any plot node to update the target plot tree.

[0025] In an exemplary embodiment, after merging the plot branches and the initial plot tree to obtain a target plot tree, it further includes:

[0026] Generate a character image of the user, a character image of the virtual object, and a background image of the plot scene according to the role of the user, the role of the virtual object, and the plot scene of the target plot tree;

[0027] Perform composite processing on the two character images and their corresponding character lines respectively to obtain two character animations with lip synchronization to the character lines; and, generate voices with emotional expressions respectively according to the character lines of each character.

[0028] Perform fusion processing on the two character animations, the background image, and the voice to obtain an interactive plot work.

[0029] In an exemplary embodiment, the method further includes:

[0030] At the plot nodes of the target plot tree, display the corresponding character images and background images.

[0031] In response to a preview instruction, display a plot segment of the interactive plot work.

[0032] According to a second aspect of the embodiments of the present disclosure, there is provided an interactive content generation device, including:

[0033] A dialogue analysis unit configured to execute obtaining a dialogue between a user and a virtual object, determining plot nodes in the dialogue, and generating an initial plot tree.

[0034] A plot generation unit configured to execute generating a plurality of candidate plots at the plot nodes.

[0035] A branch generation unit configured to execute generating plot branches leading to each of the plot endings according to a target plot selected by the user from the plurality of candidate plots and at least one plot ending input by the user.

[0036] A plot merging unit configured to execute merging the plot branches and the initial plot tree to obtain a target plot tree, and the target plot tree is used as a script.

[0037] In an exemplary embodiment, the dialogue analysis unit is further configured to execute semantic analysis and emotional analysis on the dialogue to obtain nodes affecting the plot direction; and use the nodes affecting the plot direction as the plot nodes in the dialogue.

[0038] In an exemplary embodiment, the device further includes a plot tree adjustment unit configured to execute displaying the target plot tree; the target plot tree includes a plurality of plot nodes, and each plot node is connected by a directed edge; based on an editing operation on any plot node in the target plot tree, update the target plot tree.

[0039] In an exemplary embodiment, the plot tree adjustment unit is further configured to, when the editing operation is to add a plot node, determine the associated plot nodes of the newly added plot node; generate supplementary plot content between the newly added plot node and the associated plot nodes; and update the target plot tree according to the newly added plot node and the supplementary plot content.

[0040] In an exemplary embodiment, the plot tree adjustment unit is further configured to, based on a moving operation on any plot node, adjust the order and structure of the plot branches of the target plot tree to update the target plot tree.

[0041] In an exemplary embodiment, the plot tree adjustment unit is further configured to, based on a deletion operation on any plot node, synchronously delete the plot nodes in the target plot tree that are affected by the any plot node to update the target plot tree; or, based on the deletion operation on the any plot node, update the plot between the previous plot node and the next plot node of the any plot node to update the target plot tree.

[0042] In an exemplary embodiment, the device further includes a work generation unit configured to generate a character image of the user, a character image of the virtual object, and a background image of the plot scene according to the role of the user, the role of the virtual object, and the plot scene of the target plot tree; perform composite processing on the two character images and the corresponding character lines respectively to obtain two character animations with lip-syncing to the character lines; and respectively generate voices with emotional expressions according to the character lines of each character; and perform fusion processing on the two character animations, the background image, and the voices to obtain an interactive plot work.

[0043] In an exemplary embodiment, the device further includes a work display unit configured to display the corresponding character image and background image at the plot node of the target plot tree; and display a plot segment of the interactive plot work in response to a preview instruction.

[0044] According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including:

[0045] A processor;

[0046] A memory for storing executable instructions of the processor;

[0047] Wherein, the processor is configured to execute the instructions to implement the method as described in any one of the above.

[0048] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, which enables an electronic device to execute the method described in any one of the above when instructions in the computer-readable storage medium are executed by a processor of the electronic device.

[0049] According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, which includes instructions that enable an electronic device to execute the method described in any one of the above when the instructions are executed by a processor of the electronic device.

[0050] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects:

[0051] First, based on the conversation between the user and the virtual object, plot nodes in the conversation are determined and an initial plot tree is generated. Then, multiple candidate plots at the plot nodes are generated. According to the target plot selected by the user from the multiple candidate plots and at least one plot ending input by the user, plot branches leading to each plot ending are generated. The plot branches and the initial plot tree are merged to obtain a target plot tree for use as a script. This method can generate a plot tree through human-computer conversation, improve the generation efficiency, lower the threshold of interactive games and story creation, and enable ordinary users to create multi-ending interactive plots. By extracting key plot nodes, predicting multiple plot directions, generating multiple candidate plots, and automatically generating multiple plot branches according to the plot direction and plot ending selected by the user, dynamic plot branch generation can be achieved, providing rich diversity for content creation.

[0052] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure, and do not constitute an improper limitation to the present disclosure.

[0054] Figure 1 is a flowchart showing a method for generating interactive content according to an exemplary embodiment.

[0055] Figure 2 is a flowchart showing a process of adjusting steps of a target plot tree according to an exemplary embodiment.

[0056] Figure 3 is a flowchart showing a process of generating an interactive plot work according to an exemplary embodiment.

[0057] Figure 4It is a schematic structural diagram of a system for implementing an interactive content generation method shown according to an exemplary embodiment.

[0058] Figure 5 It is a block diagram of the structure of an interactive content generation device shown according to an exemplary embodiment.

[0059] Figure 6 It is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0060] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0061] It should be noted that the implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims. It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties.

[0062] In an exemplary embodiment, as Figure 1 shown, an interactive content generation method is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0063] In step S110, obtain the conversation between the user and the virtual object, determine the plot nodes in the conversation, and generate an initial plot tree.

[0064] In a specific implementation, an interaction system is constructed. The interaction system includes an interaction interface. The user can select a role from multiple roles in the interaction interface as their own role identity, and at the same time select a role for the AI (Artificial Intelligence) acting as a virtual object. The user has a conversation with other roles played by the AI in their own role identity. The interaction system can record the entire conversation process in real time, including information such as conversation content, role identity, and emotional expression. Thus, a complete conversation record can be obtained as the initial material for the user's creation. Among them, the roles provided in the interaction interface can be customized by the user, and the background, personality, and image of the roles can be set, etc.

[0065] Further, after obtaining the conversation record of the role played by the user and other roles played by the AI, the conversation record can be analyzed to extract key nodes affecting the plot development, such as extracting 3-5 key nodes as plot nodes, and the extracted plot nodes can be connected in chronological order to generate an initial plot tree.

[0066] In some embodiments, during the conversation between the role played by the user and other roles played by the AI, the conversation interface of both can be displayed, and the conversation content, role avatars, and emotional expressions of both can be displayed in the conversation interface.

[0067] In step S120, multiple candidate plots at the plot nodes are generated.

[0068] Specifically, for each plot node, an analysis is carried out. Based on the conversation content and role characteristics, the possible plot development directions are predicted. These plot development directions can be: continuing the conversation (enhancing understanding), decision-making conflict (choosing different paths), emotional change (such as friendly relationship or hostile relationship), etc. Multiple candidate plots can be designed for each plot node according to these plot directions. Further, a candidate plot scheme including each plot node and the candidate plots of each plot node can be output. And in the conversation interface, the interaction system can prompt the user about the position of the plot node and display the optional candidate plots.

[0069] In step S130, according to the target plot selected by the user from multiple candidate plots and at least one plot ending input by the user, plot branches leading to each plot ending are generated.

[0070] Specifically, by displaying the positions of the extracted plot nodes and the corresponding candidate plots in the dialogue interface, the user can select the target plot to continue from multiple candidate plots. The target plot can be one or multiple. After receiving the target plot selected by the user for each plot node, the subsequent plot development can be automatically generated. At the same time, the user can propose different plot endings, thereby generating plot branches leading to different endings, ensuring that each plot branch is logical and conforms to the previous dialogue style.

[0071] In some embodiments, in addition to selecting from the provided multiple candidate plots, the user can also input new dialogue content for any plot node by themselves as the target plot at that plot node. After the interactive system receives the content input by the user, it takes it as the target plot and automatically generates the subsequent plot development.

[0072] In step S140, the plot branches and the initial plot tree are merged to obtain a target plot tree, which is used as a script.

[0073] In specific implementation, after obtaining multiple plot branches, each plot branch can be merged into the constructed initial plot tree according to the one-to-one correspondence of the plot nodes to ensure the coherence of the entire plot. Thus, a target plot tree containing multiple plot branches and endings is obtained, and this target plot tree can be used as an interactive script for interacting with players in an interactive scenario.

[0074] Furthermore, a visual interface of the target plot tree can be displayed, enabling the user to intuitively see each plot branch and ending.

[0075] In the above interactive content generation method, first, based on the dialogue between the user and the virtual object, the plot nodes in the dialogue are determined and an initial plot tree is generated, and then multiple candidate plots at the plot nodes are generated; according to the target plot selected by the user from the multiple candidate plots and at least one plot ending input by the user, plot branches leading to each plot ending are generated; the plot branches and the initial plot tree are merged to obtain a target plot tree for use as a script. This method generates a plot tree through human-computer dialogue, which can improve the generation efficiency, lower the threshold of interactive games and story creation, and enable ordinary users to create multi-ending interactive plots; by extracting key plot nodes and predicting multiple plot directions, multiple candidate plots are generated, and multiple plot branches are automatically generated according to the plot direction and plot ending selected by the user, which can achieve dynamic plot branch generation and provide rich diversity for content creation.

[0076] In an exemplary embodiment, determining the plot nodes in step S110 includes: performing semantic analysis and sentiment analysis on the dialogue to obtain the nodes that affect the plot direction; using the nodes that affect the plot direction as the plot nodes in the dialogue.

[0077] In a specific implementation, through natural language processing technology, semantic analysis and sentiment analysis can be performed on the conversation records to identify the nodes that affect the plot direction in the conversation, that is, multiple key plot nodes are extracted.

[0078] More specifically, the conversation records can be first cleaned to remove irrelevant information such as non-verbal symbols and extra spaces. Then, the conversation content in the conversation records is tokenized and part-of-speech tagged for easy analysis. The context and meaning of the conversation are understood through a natural language processing model to identify keywords, intentions, etc.; and a sentiment analysis model can be used to classify the sentiment of each sentence in the conversation to identify sentences with higher sentiment intensity, which generally affect the plot direction. By combining the results of semantic analysis and sentiment analysis, key statements, etc. are identified. Such statements are usually nodes that show changes in user sentiment, important decisions, and conflicts. Therefore, such key statements can be marked as plot nodes. The identified plot nodes are structured to form node data that can be used for constructing a plot tree, including node content, sentiment type, context information, etc.

[0079] In this embodiment, through semantic and sentiment analysis, the conversation content can be better understood, so that the construction of plot branches can be better carried out, providing rich possibilities for plot development.

[0080] In an exemplary embodiment, after merging the plot branches and the initial plot tree in step S140 to obtain the target plot tree, the following steps are further included:

[0081] Step S141, displaying the target plot tree; the target plot tree includes multiple plot nodes, and each plot node is connected by a directed edge;

[0082] Step S142, updating the target plot tree based on an editing operation on any plot node in the target plot tree.

[0083] In a specific implementation, an editing interface of the target plot tree can be displayed and editing and adjustment tools can be provided, enabling users to perform operations such as modifying, adding, deleting, and reorganizing any plot node in the target plot tree in this visual interface to adjust, trim, and add plot branches to update the target plot tree.

[0084] Specifically, first, the target plot tree is presented in a graphical form. Each plot node is represented as a graphical element (such as a circle or a square), and the content of the node shows the corresponding plot information. Arrows or directed edges are used to connect the various plot nodes to represent the causal relationships or choice paths between the plot nodes. Among them, each edge should clearly point to its subsequent node so that users can easily understand the plot progression. And a visual editing interface can be designed to display and edit the target plot tree. This visual editing interface can have functions such as zooming and node highlighting (such as highlighting), enabling users to focus on specific plot nodes and better understand their context. When the user hovers over or clicks on a plot node, the detailed information of the node is displayed, including the node content, emotional state, related choices, and subsequent nodes, etc. This visual editing interface can provide an editing function that allows users to operate on any node in the target plot tree, such as adding, deleting, or modifying the node content, etc.

[0085] In some embodiments, in the editing interface, the target plot tree can be updated in real time, and any modification to the plot node can be reflected in the display of the target plot tree in real time to ensure that the user sees the latest plot structure. And the editing interface can highlight the node that the user is currently operating on. This dynamic display method enables users to intuitively see the impact of each modification operation on the plot development.

[0086] In some embodiments, a function to save / undo the editing result can also be provided, and a version management mechanism can be implemented to record different versions of the plot tree by the user so that a certain historical version can be restored to achieve traceability.

[0087] In this embodiment, by providing intuitive editing tools and an editing interface to provide functions for modifying, adding, deleting, and reorganizing the plot branches of the generated target plot tree, the complexity of plot tree editing is reduced, the interactivity is improved, and it enables users to interact with the plot tree more conveniently and explore various possibilities of plot development.

[0088] In an exemplary embodiment, as Figure 2 shown, step S142 updates the target plot tree based on an editing operation on any plot node in the target plot tree, including:

[0089] Step S210, when the editing operation is to add a plot node, determine the associated plot nodes of the newly added plot node.

[0090] In specific implementation, the operation of adding a plot node can be specifically completed by means of drag-and-drop or menu selection. If it is detected that the user's editing operation is to add a new plot node, a prompt message can be displayed to prompt the user to select an existing node associated therewith. Determine the existing plot nodes that are relevant or logically closely related to the content of the new plot node as the associated plot nodes. The determination of the associated plot nodes can be determined according to the user's selection, or can be identified and determined by recognizing the plot content of the newly added plot node. After obtaining the associated plot nodes, the information of the newly added plot node and the associated plot nodes can be stored to facilitate connecting these two nodes subsequently and prepare for generating plot content.

[0091] Step S220, generate supplementary plot content between the newly added plot node and the associated plot nodes.

[0092] In specific implementation, reasonable plot content can be generated according to the relationship between the newly added plot node and the associated plot nodes. Specifically, supplementary plot content can be generated according to the context, emotional changes and narrative logic between the two to make the generated content conform to the entire story line. In some embodiments, the user can also continue to dialogue with the virtual object at the newly added plot node to jointly complete the construction of the plot direction.

[0093] Further, after generating the supplementary plot content, the generated content can be displayed to the user and the user is allowed to edit it to ensure that the content meets their expectations or narrative style.

[0094] In some embodiments, it is also possible to verify the consistency of the logic of the generated supplementary plot content with the existing plot to ensure that the newly added content will not cause logical loopholes or inconsistencies in the plot. If the verification result is inconsistent or the generated content is not reasonable enough, an iterative mechanism can be used to generate different versions for the user to select or fine-tune.

[0095] Step S230, update the target plot tree according to the newly added plot node and the supplementary plot content.

[0096] In specific implementation, the newly added plot node and its supplementary content can be integrated into the target plot tree to ensure that the newly added plot node and its associated plot nodes are correctly connected by directed edges, update the structure of the target plot tree to ensure that the new relationship can be effectively represented in the system. And the visualization interface can be refreshed to reflect the updates made to the target plot tree, enabling the user to see that the new nodes and content have been added to the appropriate positions.

[0097] In some embodiments, it is also possible to save the updated target plot tree to record the current changes in the tree structure. At the same time, the historical versions of the plot tree can be saved through a version management system, allowing the user to revert to a previous state.

[0098] In this embodiment, by allowing users to add new plot nodes, users can create storylines that better meet their needs according to their own ideas, greatly improving the creative freedom. Thus, flexible editing and expansion of the target plot tree are achieved, enhancing the interactivity.

[0099] In one exemplary embodiment, step S142 updates the target plot tree based on an editing operation on any plot node in the target plot tree, and further includes: based on a moving operation on any plot node, adjusting the order and structure of the plot branches of the target plot tree to update the target plot tree.

[0100] In specific implementation, the moving operation on the plot node can specifically be a dragging operation. When it is detected that the user performs a dragging operation on any plot node, determine the starting position and the new position of this plot node. According to the new position of the plot node being moved, adjust the order and structure of the plot branches of the target plot tree to update the target plot tree.

[0101] More specifically, the connections between each plot node can be updated to ensure that the new order reflects the development of the plot. For example, if the user moves a certain plot node after another plot node, update the directed edge so that the subsequent relationship is correct. Also, moving a plot node may change the relationship with the nodes directly connected to this node. Therefore, it is also necessary to evaluate and update this associated information to ensure the consistency of the plot logic. Visualize the adjusted relationship of the plot nodes.

[0102] In this embodiment, in addition to the function of adding new plot nodes, a function of adjusting the order and structure of the plot branches of the target plot tree based on a moving operation on any plot node is also provided, enabling users to reorganize the storyline in an intuitive way and enhancing the flexibility and user experience of interactive creation.

[0103] In one exemplary embodiment, step S142 updates the target plot tree based on an editing operation on any plot node in the target plot tree, and further includes: based on a deletion operation on any plot node, synchronously deleting the plot nodes in the target plot tree affected by any plot node to update the target plot tree; or, based on a deletion operation on any plot node, updating the plot between the previous plot node and the next plot node of any plot node to update the target plot tree.

[0104] In specific implementation, for the deletion operation performed by the user on any plot node in the target plot tree, the target plot tree can be synchronously updated in two ways: one is to synchronously delete the affected plot nodes, and the other is to update the plot between the relevant nodes. The following elaborates on the two ways in detail.

[0105] The first method: Based on the deletion operation of any plot node, synchronously delete the plot nodes in the target plot tree that are affected by any plot node to update the target plot tree.

[0106] Specifically, after receiving the user's deletion operation on a certain plot node in the target plot tree, first identify the nodes affected by the deleted plot node. For example, only its directly connected child nodes and parent nodes. Perform the deletion operation on these nodes and update the target plot tree. For example, the connection relationships between other nodes can be updated to ensure that there are no interrupted connection edges or invalid references. At the same time, refresh the visualization interface and dynamically delete the affected plot nodes from the displayed target plot tree so that the user can see the deletion result in a timely manner.

[0107] The second method: Based on the deletion operation of any plot node, update the plot between the previous plot node and the next plot node of any plot node to update the target plot tree.

[0108] Specifically, after receiving the user's deletion operation on a certain plot node in the target plot tree, first identify the previous plot node (such as node B) and the next plot node (such as node C) connected to the deleted plot node (such as node A). After node A is deleted, establish a connection between node B and node C, and update the plot between the two according to the content of node B and node C to ensure the coherence and fluency of the plot logic. Refresh the visualization interface to display this updated plot structure and ensure that the user can observe the changes between the upper and lower nodes.

[0109] In this embodiment, by improving the deletion and update operations based on the deleted nodes, it is possible to ensure the structural integrity and narrative fluency of the target plot tree on the basis of enhancing the flexibility of interactive creation and the user experience.

[0110] In an exemplary embodiment, as Figure 3 shown, after merging the plot branch and the initial plot tree in step S140 to obtain the target plot tree, it further includes:

[0111] Step S310, generate the character image of the user, the character image of the virtual object, and the background image of the plot scene according to the role of the user, the role of the virtual object, and the plot scene of the target plot tree.

[0112] In specific implementation, after obtaining the complete target plot tree and plot text content, visual and audio content can also be generated to obtain an interactive plot work, specifically including generating character images, character animations, and background images, and performing fusion. Among them, for the generation of character images, image generation technology can be used to generate character images of the user-played character and the character played by the virtual object according to the character settings. When generating character images, details such as the appearance, clothing, expression, and posture of the character need to be considered. For the generation of background images of the plot scene, they can be generated according to the plot scene corresponding to the target plot tree. For example, background images that match the plot scene and are consistent with the style of the character images can be selected from the material library, or background images that match the plot scene and are consistent with the style of the character images can be generated through image generation technology.

[0113] In some embodiments, character images and background images uploaded by the user can also be received.

[0114] Step S320: Perform synthesis processing on the two character images and the corresponding character lines respectively to obtain two character animations with lip-sync to the character lines; and, generate voices with emotional expressions respectively according to the character lines of each character.

[0115] In specific implementation, the user and the virtual object respectively have corresponding character lines. After obtaining the character images of the user and the virtual object, the character lines can be synthesized with the character images to obtain character animations. Specifically, for any character image, the character image can be synthesized with the corresponding lines through lip synthesis technology to achieve lip-sync between the character's mouth shape and the character lines. At the same time, for each character, text-to-speech (TTS) technology can be used to generate voices with emotional expressions for the character.

[0116] Step S330: Perform fusion processing on the two character animations, the background image, and the voice to obtain an interactive plot work.

[0117] In specific implementation, after obtaining the background image, the character images of the two characters, the animation with synchronized lip movements, and the voice files of the characters, these results can be fused to obtain an interactive plot work.

[0118] In this embodiment, by generating dynamic character images and vivid background images, users can be visually immersed in the plot in depth, enhancing the immersive experience of users; through voices with different emotional expressions and synchronized lip-sync animations, the lines of characters can be made more expressive, enhancing the appeal of the story; the characters and scenes generated according to user input make each generated interactive work have personalized characteristics; this scenario combining user characters, virtual object characters, and the target plot tree, from generating character images, animation synchronization to the final interactive integration, not only makes users more involved, but also significantly enhances the expressiveness and interactivity of the plot.

[0119] In some embodiments, in the plot nodes or dialogue content of the target plot tree, the corresponding character images and background images can be displayed, and a preview function can be provided. If a preview instruction is received, in response to this instruction, a plot segment of the interactive plot work can be displayed, allowing users to watch the plot segment with sound and animation.

[0120] Furthermore, in some embodiments, the obtained interactive plot works can also be published and shared. Specifically, the multimedia content of the target plot tree and the interactive plot work can be packaged into an executable or playable interactive game file, and the interactive game file can be uploaded to a publishing platform to generate a work link or QR code for other users to access and experience. In the user's work list, the newly published works can be displayed, and an excuse to share the work to social media can be provided. In some embodiments, users can also set the public scope of the work and choose whether to allow others to create derivative works or leave comments.

[0121] In this embodiment, by displaying character images and background images, users can better understand the emotions of the characters and the atmosphere of the scene, thus enhancing the overall immersion; the preview function allows users to experience plot segments, which helps to better understand the development of the story and possible choice results.

[0122] In another exemplary embodiment, as Figure 4 shown, it is a schematic structural diagram of a system for implementing an interactive content generation method according to an exemplary embodiment. The system may include a user interaction layer 410, a dialogue analysis and generation layer 420, an editing and adjustment layer 430, a multimedia generation layer 440, and a work publishing layer 450, where

[0123] The user interaction layer 410 is used to support the user to have a dialogue interaction with the AI, as well as edit and adjust the plot branches.

[0124] Specifically, in the user interaction layer, the user selects a character and has a dialogue with other characters played by the AI in his own character identity. The system records the entire dialogue process in real time and outputs a complete dialogue record as the input of the dialogue analysis layer 420.

[0125] The dialogue analysis and generation layer 420 is used to perform semantic and sentiment analysis on the dialogue content between the user and the AI, extract key plot nodes, and generate plot branches and plot trees.

[0126] Specifically, in the dialogue analysis layer, based on natural language processing technology, semantic and sentiment analysis is performed on the dialogue content, key plot nodes that have a significant impact on the plot development are extracted from the dialogue, and the possible plot development directions at such plot nodes are inferred to generate multiple candidate plots. The user can select the plot divergence options provided by the AI at the key nodes or input new dialogue content by themselves; according to the user's selection or new input, the subsequent plot development is automatically generated. The user can propose different plot endings and generate plot branches leading to different endings. The output target plot tree (including multiple plot branches and endings) is used as the input to the editing and adjustment layer 430.

[0127] The editing and adjustment layer 430 is used to provide a visual editing interface to support the user in adjusting the plot branches.

[0128] Specifically, in the editing and adjustment layer, the target plot tree can be visually edited. For example, the order and structure of the plot branches can be adjusted by dragging the plot nodes; unsatisfactory plot branches can be deleted, or new plot developments can be added at any node. For the newly added plot nodes, the intermediate plot content is automatically generated to maintain the coherence of the plot. The user can also continue to dialogue with the AI at the new plot nodes to jointly complete the plot development. The output plot tree (including the adjusted plot branches and content) after the user's personalized adjustment is used as the input to the multimedia generation layer 440.

[0129] The multimedia generation layer 440 is used to generate character images, background images, and generate audible content through text-to-speech and lip-sync synthesis technologies.

[0130] Specifically, in the multimedia generation layer, according to the character settings and plot scenarios, image generation technology is used to generate character portraits (or character images) and scene backgrounds. Combining the character portraits and character lines, through lip-sync synthesis technology, the character mouth shapes are synchronized with the dialogue; and, using TTS technology, emotional voice is generated for the characters. The output includes character portraits, background images, animations with synchronized mouth shapes, and voice files of the characters, which are used as the input to the work publishing layer 450.

[0131] The work publishing layer 450 is used to publish the finally generated interactive plot for other users to experience.

[0132] Specifically, at the work release layer, the plot tree and multimedia content are packaged into an executable or playable interactive game file, and the work is uploaded to the platform to generate a work link or QR code for other users to access and experience. Users can set permissions, for example, they can set the public scope of the work and choose whether to allow others to remix or comment on it.

[0133] Examples of user operations and system feedback are as follows:

[0134] For example, the user operation is: at a key plot node, the user selects candidate plot option A recommended by the AI or enters new dialogue content.

[0135] The system feedback includes plot updates and prompts:

[0136] Among them, the plot update means that the AI generates subsequent plot branches according to the user's choice and displays them in the plot tree.

[0137] Among them, the prompt is that the system prompts the user that this choice will lead to a major change in the plot direction.

[0138] In terms of page changes: the new plot branches are highlighted in the plot tree interface, and the user can click on the nodes to view the specific content.

[0139] Through the interactive content generation method provided in this embodiment, the following effects can be achieved: (1) Lower the creation threshold: Through the method of human-computer dialogue, users can create complex and multi-ending interactive plots without professional skills. (2) Improve user participation: Users are deeply involved in plot creation and branch design, enhancing creativity and satisfaction. (3) Enrich the work content: The AI automatically generates character images, background pictures, and audio content, improving the expressiveness and attractiveness of the work. (4) Support personalized customization: Users can adjust plot branches and endings according to their personal preferences to meet personalized needs. (5) Enhance interactivity: Other users can participate in the experience and remix of the work, forming a good interactive ecosystem. (6) Improve creation efficiency: The AI assists in generating plots and multimedia content, significantly shortening the production cycle of the work.

[0140] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0141] It can be understood that the same / similar parts among the various embodiments of the above method in this specification can be referred to each other. Each embodiment focuses on the differences from other embodiments. For the related parts, refer to the descriptions of other method embodiments.

[0142] Based on the same inventive concept, the embodiments of the present disclosure also provide an interactive content generation device for implementing the above-mentioned interactive content generation method.

[0143] Figure 5 is a structural block diagram of an interactive content generation device shown according to an exemplary embodiment. Referring to Figure 5 , the device includes:

[0144] A dialogue analysis unit 510, configured to execute obtaining a dialogue between a user and a virtual object, determining plot nodes in the dialogue, and generating an initial plot tree;

[0145] A plot generation unit 520, configured to execute generating a plurality of candidate plots at the plot nodes;

[0146] A branch generation unit 530, configured to execute generating plot branches leading to various plot endings according to a target plot selected by the user from the plurality of candidate plots and at least one plot ending input by the user;

[0147] A plot merging unit 540, configured to execute merging the plot branches and the initial plot tree to obtain a target plot tree, and the target plot tree is used as a script.

[0148] In an exemplary embodiment, the dialogue analysis unit 510 is further configured to execute semantic analysis and sentiment analysis on the dialogue to obtain nodes that affect the plot direction; and use the nodes that affect the plot direction as the plot nodes in the dialogue.

[0149] In an exemplary embodiment, the device further includes a plot tree adjustment unit configured to execute the display of a target plot tree; the target plot tree includes a plurality of plot nodes, and each plot node is connected by a directed edge; based on an editing operation on any plot node in the target plot tree, the target plot tree is updated.

[0150] In an exemplary embodiment, the plot tree adjustment unit is further configured to execute, when the editing operation is to add a plot node, determine the associated plot nodes of the newly added plot node; generate supplementary plot content between the newly added plot node and the associated plot nodes; and update the target plot tree according to the newly added plot node and the supplementary plot content.

[0151] In an exemplary embodiment, the plot tree adjustment unit is further configured to execute, based on a moving operation on any plot node, adjust the order and structure of the plot branches of the target plot tree to update the target plot tree.

[0152] In an exemplary embodiment, the plot tree adjustment unit is further configured to execute, based on a deletion operation on any plot node, synchronously delete the plot nodes in the target plot tree affected by the any plot node to update the target plot tree; or, based on a deletion operation on any plot node, update the plot between the previous plot node and the next plot node of the any plot node to update the target plot tree.

[0153] In an exemplary embodiment, the device further includes a work generation unit configured to execute generating a character image of the user, a character image of the virtual object, and a background image of the plot scene according to the role of the user, the role of the virtual object, and the plot scene of the target plot tree; respectively performing a synthesis process on the two character images and the corresponding character lines to obtain two character animations with the mouth shapes synchronized with the character lines; and respectively generating voices with emotional expressions according to the character lines of each character; performing a fusion process on the two character animations, the background image, and the voices to obtain an interactive plot work.

[0154] In an exemplary embodiment, the device further includes a work display unit configured to execute displaying the corresponding character image and background image at the plot node of the target plot tree; and in response to a preview instruction, display a plot segment of the interactive plot work.

[0155] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0156] Figure 6FIG. 600 is a block diagram of an electronic device for implementing an interactive content generation method according to an exemplary embodiment. For example, the electronic device 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0157] Referring Figure 6 , the electronic device 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an input / output (I / O) interface 612, a sensor component 614, and a communication component 616.

[0158] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0159] The memory 604 is configured to store various types of data to support the operation of the electronic device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, optical disk, or graphene memory.

[0160] The power component 606 provides power to the various components of the electronic device 600. The power component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 600.

[0161] The multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operation mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0162] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 600 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 further includes a speaker for outputting audio signals.

[0163] The I / O interface 612 provides an interface between the processing component 602 and a peripheral interface module, and the peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a power button, and a lock button.

[0164] The sensor component 614 includes one or more sensors for providing status assessments of various aspects of the electronic device 600. For example, the sensor component 614 can detect the on / off state of the electronic device 600, the relative positioning of components, such as the display and the keypad of the electronic device 600. The sensor component 614 can also detect a change in the position of the electronic device 600 or components of the electronic device 600, the presence or absence of user contact with the electronic device 600, the orientation or acceleration / deceleration of the device 600, and a change in the temperature of the electronic device 600. The sensor component 614 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 614 can also include a light sensor, such as a CMOS or a CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 614 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0165] The communication component 616 is configured to facilitate communication between the electronic device 600 and other devices in a wired or wireless manner. The electronic device 600 can access a communication standard-based wireless network, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0166] In an exemplary embodiment, the electronic device 600 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above method.

[0167] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the above instructions can be executed by a processor 620 of the electronic device 600 to complete the above method. For example, the computer-readable storage medium can be a ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0168] In an exemplary embodiment, a computer program product is also provided, and the computer program product includes instructions that can be executed by a processor 620 of the electronic device 600 to complete the above method.

[0169] It should be noted that the above-mentioned device, electronic device, computer-readable storage medium, computer program product, etc. may also include other implementation manners according to the description of the method embodiments. The specific implementation manners can refer to the description of the relevant method embodiments and will not be elaborated here one by one.

[0170] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0171] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for generating interactive content, characterized in that: include: Obtaining a conversation between a user and a virtual object, determining plot nodes in the conversation and generating an initial plot tree; generating a plurality of candidate plots at the plot nodes; Generate plot branches leading to each of the plot endings according to the target plot selected by the user from the multiple candidate plots and at least one plot ending input by the user; The plot branch and the initial plot tree are merged to obtain a target plot tree, and the target plot tree is used as a script.

2. The method according to claim 1, characterized in that: Determining the plot nodes in the dialogue includes: Perform semantic analysis and sentiment analysis on the dialogue to obtain nodes that affect the direction of the plot; The nodes that affect the direction of the plot are used as the plot nodes in the dialogue.

3. The method according to claim 1, characterized in that After merging the plot branch and the initial plot tree to obtain a target plot tree, the method further includes: Display the target plot tree; the target plot tree includes a plurality of plot nodes, and each of the plot nodes is connected by directed edges; Based on the editing operation on any of the plot nodes in the target plot tree, the target plot tree is updated.

4. The method according to claim 3, characterized in that: The updating of the target plot tree based on the editing operation of any plot node in the target plot tree comprises: In the case where the editing operation is to add a plot node, determining the associated plot nodes of the newly added plot node; Generating supplementary plot content between the newly added plot node and the associated plot node; The target plot tree is updated according to the newly added plot nodes and the supplementary plot content.

5. The method according to claim 3, characterized in that: The updating of the target plot tree based on the editing operation of any plot node in the target plot tree further includes: Based on the move operation on the arbitrary plot node, the order and structure of the plot branches of the target plot tree are adjusted to update the target plot tree.

6. The method according to claim 3, characterized in that The updating of the target plot tree based on the editing operation of any plot node in the target plot tree further includes: Based on the deletion operation of the arbitrary plot node, the plot nodes affected by the arbitrary plot node in the target plot tree are synchronously deleted to update the target plot tree; Alternatively, based on the deletion operation on the arbitrary plot node, the plot between the previous plot node and the next plot node of the arbitrary plot node is updated to update the target plot tree.

7. The method according to claim 1, characterized in that After merging the plot branch and the initial plot tree to obtain a target plot tree, the method further includes: Generate a character image of the user, a character image of the virtual object, and a background image of the plot scene according to the character of the user, the character of the virtual object, and the plot scene of the target plot tree; The two character images and the corresponding character lines are synthesized to obtain two character animations with lip movements synchronized with the character lines; and, based on the character lines of each character, speech with emotional expression is generated; The two character animations, the background image and the voice are fused to obtain an interactive plot work.

8. The method according to claim 7, characterized in that The method further comprises: At the plot node of the target plot tree, display the corresponding character image and background image; In response to the preview instruction, a plot segment of the interactive plot work is displayed.

9. An interactive content generating device, characterized in that: include: A dialogue analysis unit, configured to obtain a dialogue between a user and a virtual object, determine plot nodes in the dialogue and generate an initial plot tree; A plot generation unit, configured to generate a plurality of candidate plots at the plot node; a branch generating unit, configured to generate a plot branch leading to each of the plot endings according to the target plot selected by the user from the plurality of candidate plots and at least one plot ending input by the user; The plot merging unit is configured to perform a merging process on the plot branch and the initial plot tree to obtain a target plot tree, and the target plot tree is used as a script.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the interactive content generation method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the interactive content generating method as described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the interactive content generation method according to any one of claims 1 to 8 is implemented.

Images