Game scene content generation method and device, equipment, medium and program product

Abstract

The invention discloses a game scene content generation method and device, equipment, a medium and a program product, and relates to the technical field of computers.The method comprises the steps that a content generation interaction interface is displayed in a graphic display interface; in response to an interaction operation triggered in the content generation interaction interface, determining content elements generated by the target object for the game scene; generating a scene structured script based on the target scene information represented by the content elements; and rendering the scene structured script, generating a target game scene, and displaying the target game scene in a graphic display interface. By implementing the technical scheme of the invention, the threshold and cost of game plot creation can be reduced, and quick generation and real-time performance verification of the plot can be realized.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to methods, apparatus, devices, media, and program products for generating game scene content. Background Technology

[0002] Story creation, a crucial step in the creation of content such as games and films, has long relied heavily on creators' professional writing skills and in-depth understanding of the specific development process, thus possessing a high professional threshold. While some auxiliary creation tools exist on the market, their functions are mostly limited to grammar checking or simple resource recommendations, failing to provide in-depth, structured support for the creation process. Creators still need to conceive a complete story structure themselves and transform it into a directly executable script format—a time-consuming and complex process. Summary of the Invention

[0003] In view of this, this application provides a scriptwriting assistance method, device, equipment, storage medium, and program product to solve the problems of low efficiency and high professional threshold in the scriptwriting process.

[0004] In a first aspect, this application provides a method for generating content for a game scene, comprising: displaying a content generation interactive interface in a graphical display interface; determining content elements generated by a target object for the game scene in response to an interactive operation triggered in the content generation interactive interface; generating a scene structured script based on the target scene information represented by the content elements; rendering the scene structured script to generate the target game scene and displaying it in the graphical display interface.

[0005] In one optional implementation, in response to an interactive operation triggered on the content generation interactive interface, determining the content elements generated by the target object for the game scene includes: displaying first guidance information and at least one first reply information corresponding to the first guidance information on the content generation interactive interface; in response to the target object's selection operation on the first reply information, determining target reply information and second guidance information corresponding to the target reply information; displaying second guidance information and at least one second reply information corresponding to the second guidance information on the content generation interactive interface; in response to the target object's selection operation on the second reply information, determining a new round of reply information; and determining the content elements generated by the target object for the game scene based on the semantic content of the target reply information and the new round of reply information.

[0006] In one optional implementation, in response to a content input operation triggered by the target object in response to the second guidance information in the content generation interactive interface, target input content is obtained; based on the semantic information corresponding to the target input content, third guidance information related to the semantic information and at least one third response information corresponding to the third guidance information are generated; in response to a selection operation on the third response information, a new round of response information is determined; based on the semantic content of the target response information and the new round of response information, the content elements generated by the target object for the game scene are determined.

[0007] In one optional implementation, the content generation interactive interface includes a script generation control. Based on the target scene information represented by the content elements, a scene structured script is generated, including: in response to a trigger operation on the script generation control, splitting the target scene information represented by the content elements to obtain multiple sub-scene information; and converting each sub-scene information into a scene structured script based on the script structure corresponding to a preset script format.

[0008] In one optional implementation, the target scene information represented by the content element is split into multiple sub-scene information, including: matching the target scene information represented by the content element with multiple preset scene templates to obtain a target scene template that matches the target scene information represented by the content element; based on the scene structure of the target scene template, the content element is split into multiple sub-scene elements, and sub-scene information corresponding to each sub-scene element is generated.

[0009] In one optional implementation, rendering a scene structured script to generate a target game scene includes: displaying the parsing result of the scene structured script, the parsing result including scene information and virtual character information; and in response to a scene rendering operation triggered based on the parsing result, rendering the game scene according to the scene information and virtual character information to generate the target game scene.

[0010] In one alternative implementation, in response to an adjustment operation on the scene structured script, an adjusted scene structured script is determined.

[0011] Secondly, this application provides a content generation device for a game scene, comprising: a display module for displaying a content generation interactive interface in a graphical display interface; a first determining module for determining content elements generated by a target object for a game scene in response to an interactive operation triggered in the content generation interactive interface; a generation module for generating a scene structured script based on the target scene information represented by the content elements; and a rendering module for rendering the scene structured script, generating a target game scene, and displaying it in the graphical display interface.

[0012] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the game scene content generation method described in the first aspect or any corresponding embodiment.

[0013] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the game scene content generation method described in the first aspect or any corresponding embodiment.

[0014] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the game scene content generation method described in the first aspect or any corresponding embodiment.

[0015] The game scene content generation method provided in this application displays a content generation interactive interface in a graphical display interface, providing creators with an intuitive and easy-to-use operation entry point. This allows even users without a professional writing background to easily participate in plot creation, greatly lowering the barrier to entry. Responding to interactive operations triggered on the content generation interactive interface, it can dynamically capture and determine the content elements generated by the target object for the game scene, thereby transforming the creator's vague ideas into concrete and processable data, reducing the burden of manually planning every detail in traditional creation. Based on the target scene information represented by the content elements, a structured script for the scene is automatically generated. This step replaces the process of manually writing complex scripts, not only improving the efficiency of script generation but also ensuring that the script conforms to dramatic theory and game logic, avoiding structural problems caused by insufficient professional competence of the creator. By rendering the structured script for the scene, the target game scene is generated and displayed in real time in the graphical display interface, allowing creators to immediately visualize the plot effects of their ideas, facilitating rapid verification and iterative optimization. This shortens the overall cycle from idea to implementation, improving the flexibility and productivity of game plot development. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this application, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application; Figure 2This is a schematic diagram of the first method for generating content for a game scene according to an embodiment of this application; Figure 3 This is a schematic diagram of a second process for a method of generating content for a game scene according to an embodiment of this application; Figure 4 This is a schematic diagram of an interactive interface generated according to the content of an embodiment of this application; Figure 5 This is a schematic diagram of the target game scene according to an embodiment of this application; Figure 6 This is a structural block diagram of a game scene content generation device according to an embodiment of this application; Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0021] As one optional application scenario in this application embodiment, Figure 1 This diagram illustrates one application scenario of a game scene content generation system. For example... Figure 1 As shown, the system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0022] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0023] Taking role-playing games (RPGs) as an example, a terminal device has an RPG game application installed. By running this application, a corresponding virtual scene can be rendered and displayed to the player using the terminal device's graphical user interface. For example, this virtual scene can be part or all of a simulated three-dimensional (3D) virtual space, including environmental elements (such as forests or cities) and non-player characters (NPCs). Players typically need to participate in or create the storyline in the game to advance the game's progress or enrich the gaming experience.

[0024] Traditional scriptwriting methods require creators to possess professional writing skills and manually transform ideas into structured scripts. This process is not only time-consuming and labor-intensive but also has a high barrier to entry. Even with the help of existing scriptwriting platforms, they can only provide simple grammar correction or material recommendations, but cannot offer an overall plot plan that conforms to dramatic theory, nor can they provide real-time performance capabilities, making it difficult for creators to quickly verify and adjust the plot content.

[0025] The game scene content generation method provided in this application displays a content generation interactive interface in the graphical user interface of the game application on the terminal device. This interface changes the traditional creation mode, including controls for users to input or select creative elements, such as text input boxes, option buttons, and story outline generation buttons. This allows ordinary users to easily input content elements such as background stories, character settings, and plot directions through natural language dialogue or by selecting preset templates, without needing professional scripting knowledge. The system responds to these interactive operations to determine the content elements and automatically generates a structured scene script. Finally, it renders and displays the corresponding target game scene in real time, allowing creators to immediately and intuitively verify the performance effect of their ideas, thereby improving the efficiency and immersion of game content generation.

[0026] According to an embodiment of this application, a method for generating content for a game scene is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] This embodiment provides a method for generating game scene content, which can be used in electronic devices such as computer 101, mobile terminal 102, etc. Figure 2 This is a flowchart of a game scene content generation method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: Step S201: Display content in the graphical display interface to generate an interactive interface.

[0028] A graphical user interface (GUI) refers to the visual elements displayed on an electronic device, used to present the visual elements of a game or creative tool. The content generation interactive interface supports at least one input method, including text input, option selection, and template filling, allowing users (creators) to interact with an AI assistant to input creative elements and generate game storylines. Specifically, displaying the content generation interactive interface within the graphical user interface is essentially the process of an electronic device initializing and presenting a user interface designed specifically for creative input. When a user activates this assisted creation function on the electronic device, predefined interface resources and layout logic are invoked to render an interactive operation panel on the device's graphical user interface. This interactive interface is typically a graphical user interface whose core purpose is to provide users with an intuitive and low-barrier channel to express their creative intentions. This interface can contain various interactive elements, such as: text input boxes for users to freely input ideas; selection buttons or drop-down menus providing preset story templates or style options; and conversational interfaces where a virtual AI assistant proactively guides and asks questions through natural language, etc. In this way, a complex creative task is successfully broken down into a series of simple interactive operations that can be performed on a graphical interface, thus completing the transformation from system function to a user-perceptible and operable interface.

[0029] Step S202: In response to the interactive operation triggered on the content generation interactive interface, determine the content elements generated by the target object for the game scene.

[0030] The target audience refers to the users (creators) who use the tool to create storylines. Content elements refer to the core creative information input by the user, including key elements such as background story, character settings, and plot development. Specifically, when a user performs any action on the content generation interface, such as clicking a button, selecting an option, or entering text, the electronic device immediately captures these interactions as input signals. Subsequently, an artificial intelligence (AI) model analyzes the semantic information of these interactions to determine the content elements the user wishes to inject into the game scene. This process typically relies on background natural language processing and intent recognition technologies. Through multiple rounds of human-computer interaction, the AI ​​assistant continuously probes for details, gradually clarifying and enriching these elements, ultimately forming a relatively complete set of content elements that represents the user's creative vision. These elements serve as the raw materials and basis for subsequent scene generation.

[0031] Step S203: Generate a scene structured script based on the target scene information represented by the content elements.

[0032] Target scene information refers to the chapter-by-chapter plot structure information generated based on content elements and conforming to dramatic theory, including scene descriptions, character dialogues, and plot progression nodes. The scene structured script refers to converting the target scene information into a structured data format executable by electronic devices to drive the game engine for plot performance. The script can contain elements such as chapter flow, character actions, dialogue branches, and check rules. Specifically, using artificial intelligence models (such as large language models), combined with built-in dramatic creation theories and story templates, these content elements are deeply analyzed and integrated. The model organizes scattered elements such as characters, backgrounds, and plot developments into a target scene information that conforms to narrative logic and includes a beginning, development, climax, and resolution—that is, a detailed, chapter-by-chapter plot outline. Next, a structured script generation module is activated. This module, based on a set of predefined script data specifications, converts the aforementioned natural language-described plot outline into a structured data file, i.e., the scene structured script. This script is no longer a story text for human reading, but a procedural description file containing elements such as character action instructions, dialogue sequences, branch selection conditions, scene switching triggers, etc. It provides the game engine or rendering module with a precise, line-by-line execution script.

[0033] Step S204: Render the scene structure script, generate the target game scene, and display it in the graphical display interface.

[0034] The target game scene refers to the actual game visuals and story presentation generated by rendering a structured scene script, including character animations, scene backgrounds, and dialogue displays, allowing users to intuitively experience the created storyline. Specifically, the generated structured scene script is loaded and parsed; the parsing process involves understanding each instruction in the script. Then, according to the instructions, the corresponding resource libraries are called, such as retrieving specified character models and animations from the character library, loading background images, props, and sound effects from the asset library, and generating speech bubbles or subtitles on the screen based on the dialogue content in the script. Through a game engine or similar rendering technology, these discrete visual and auditory resources are combined, processed, and drawn in real time according to the temporal, logical, and spatial relationships specified in the script, thereby dynamically generating a complete and interactive target game scene on the graphical display interface. Ultimately, users no longer see abstract text or data, but can intuitively watch a game story presentation generated by their own creativity, complete with character performances, dialogue, and scene changes, thus achieving a closed loop from creative conception to visual verification.

[0035] The game scene content generation method provided in this application displays a content generation interactive interface in the graphical user interface of the game application on a terminal device. This interface changes the traditional creation mode, including controls for users to input or select creative elements, such as text input boxes, option buttons, and story outline generation buttons. This allows ordinary users to easily input content elements such as background stories, character settings, and plot directions through natural language dialogue or by selecting preset templates, without needing professional scripting knowledge. The electronic device responds to these interactive operations to determine the content elements and automatically generates a structured scene script. Finally, it renders and displays the corresponding target game scene in real time, allowing creators to immediately and intuitively verify the performance effect of their ideas, thereby improving the efficiency and immersion of game content generation.

[0036] This embodiment provides a method for generating game scene content, which can be used in electronic devices such as computer 101, mobile terminal 102, etc. Figure 3 This is a flowchart of a game scene content generation method according to an embodiment of this application, such as... Figure 3 As shown, the process includes the following steps: Step S301: Display content in the graphical display interface to generate an interactive interface. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0037] Step S302: In response to the interactive operation triggered on the content generation interactive interface, determine the content elements generated by the target object for the game scene.

[0038] In some optional implementations, step S302 above includes: Step a1: Display the first guidance information and at least one first reply information corresponding to the first guidance information on the content generation interactive interface.

[0039] The first guiding message refers to the initial question or options initiated by the AI ​​assistant to guide the user's creative process. It typically takes the form of a question used to initiate a specific creative topic. For example, the AI ​​might ask, "Which of the following stories resonates with you the most?" This is the first guiding message. The first response message refers to at least one specific option automatically generated in response to the first guiding message, offered to the user for selection. These options are direct responses to the guiding message. For example, following the question above, several story outlines such as "Interstellar Mercenary Zeng'er Crashes on an Unknown Planet..." and "A Useless Junior Sister from a Cultivation Sect Makes a Comeback with Modern Knowledge" are first response messages. Specifically, when the target user enters the content generation interactive interface, the electronic device first invokes predefined dialogue logic, displaying a first guiding message in the interface's dialogue area. This message is essentially an open-ended question or topic guidance, designed to initiate a specific creative topic, such as inquiring about the creator's preferred story type or core idea. Following this, based on the semantics of the first guiding message, at least one first response message is automatically generated and simultaneously displayed using a built-in AI model or a pre-set option library. These responses are presented as specific options that users can choose directly. As a direct response to the guidance information, they provide creators with a clear and limited path to express their creative intentions in a low-barrier way.

[0040] Step a2: In response to the target object's selection operation on the first response information, determine the target response information and the second guidance information corresponding to the target response information.

[0041] The target response information refers to the option that the user actually clicked and selected from the first response information. This selection represents the user's explicit intent in the current round. For example, if the user clicked on the story "Interstellar Mercenary Zeng'er...", this selected story becomes the target response information. Specifically, when the target user makes a selection operation on the displayed first response information (such as clicking on an option), the electronic device immediately responds to the interaction event. First, the specific option selected by the user is formally identified as the target response information, representing the user's explicit choice in the first round of dialogue. Subsequently, using the aforementioned identified target response information as the core input, semantic analysis or logical mapping rules are used to deduce the creative dimensions that need further refinement, and a new second guiding information is generated accordingly. This second guiding information is a more targeted follow-up question, aiming to guide the user to provide more specific and detailed creative content based on the choices already made, thereby achieving iterative dialogue and gradual refinement of creative intent.

[0042] Step a3: Display the second guidance information and at least one second reply information corresponding to the second guidance information on the content generation interactive interface.

[0043] The second guiding message refers to a new round of guiding questions automatically raised based on the user's selected target response information, to further refine the content and deepen the dialogue and creation. For example, after the user selects the interstellar mercenary story, the AI ​​then asks, "Great! So, after Zeng'er crashes on this unknown planet, in what kind of environment do you think she should discover this ancient mecha legacy?" This is the second guiding message. The second response message refers to a new round of specific options provided in response to the second guiding message. For example, in response to the question about "discovering the environment," the AI ​​might offer options such as "discovering a legendary mecha that has been sleeping for thousands of years in an abandoned underground base, and gaining powerful combat capabilities after activation," "accidentally entering a mysterious ruin and triggering a mecha summoning ritual, only to discover a mysterious connection between one's bloodline and an ancient civilization," or "being rescued by an indigenous tribe and learning about the mecha guardian legend, requiring trials to gain recognition." These are examples of second response messages. Specifically, the generated second guiding message is rendered on the content generation interface, usually immediately following the previous dialogue. This new guiding message will raise more in-depth questions to continue the dialogue. Simultaneously, based on the new topic pointed to by this second guiding message, at least one corresponding second response message is prepared and displayed, either generated by AI or retrieved from the option library. These new options provide users with possible choices in the current more granular context, enabling the creation of dialogues to continuously enrich their details and layers around a core story framework.

[0044] Step a4: In response to the target object's selection operation for the second response information, determine the new round of response information.

[0045] A new round of responses refers to the response finally determined by the user in the introductory information and any subsequent round of dialogue. It represents the continuous progress of the dialogue flow and the ongoing accumulation of content. Specifically, when the target makes a new choice from the provided second round of responses, the electronic device captures this interaction. This newly selected option is collectively referred to as the new round of responses. The new round of responses summarizes all valid choices made by the user in any subsequent rounds after the initial target response. Determining the new round of responses means that the electronic device records another step in the user's downward exploration of the dialogue tree; these successive choices together constitute a continuously growing and specific dataset of content creation.

[0046] Step a5: Based on the semantic content of the target response information and the new round of response information, determine the content elements generated by the target object for the game scene.

[0047] Here, a global analysis and summary of the semantic content confirmed by the user in all previous rounds is performed. Specifically, the target response information selected by the user in the first round and the response information selected in all subsequent rounds are considered as a complete semantic set. By performing natural language understanding, contextual analysis, and information extraction on this set, electronic devices can identify and extract the core elements that are crucial for constructing the game scene. These elements are structured and ultimately identified as content elements. They typically clearly define abstract concepts and entities necessary for constructing a complete game scene, such as story background, core conflict, key characters, and important plot points, providing a solid data foundation for the subsequent generation of structured scripts and scene performances.

[0048] The game scene content generation method provided in this application, by sequentially displaying guidance information and its corresponding multiple preset response options in the interactive interface, decomposes the open-ended content conception task into a series of specific and controllable selection steps, thereby effectively reducing the user's cognitive load and input difficulty, and avoiding ambiguity, misunderstanding, or information loss caused by free expression. Secondly, based on the user's selection of the previous round of responses, the guidance information and response options for the next round are dynamically determined and displayed. This design achieves a context-related, progressive dialogue guidance. It can intelligently guide the user to supplement and improve necessary subsequent information based on the user's expressed intentions, making the entire conception process logically coherent and naturally smooth. Furthermore, this application does not view the user's single choice in isolation, but rather comprehensively determines the final content elements based on the overall semantic content of all response information selected by the user in multiple rounds of dialogue. This semantic integration analysis based on the context of multi-round dialogue can more comprehensively and accurately capture and refine the user's complete creative intentions and core concepts scattered throughout multiple rounds of interaction, laying a high-quality, structured input foundation for subsequent processing.

[0049] In some optional implementations, step S302 above further includes: Step b1: In response to the target object's content input operation triggered by the second guidance information in the content generation interactive interface, obtain the target input content.

[0050] The target input content refers to the text content that the user enters themselves through the input box without choosing any response information provided by the AI. This gives the user the freedom to go beyond the preset options. For example, if the AI ​​provides options such as "Discover a legendary mech that has been sleeping for thousands of years in an abandoned underground base, and activate it to gain powerful combat capabilities," "Mistakenly enter a mysterious ruin and trigger a mech summoning ritual, only to discover that your bloodline has a mysterious connection with an ancient civilization," or "After being rescued by an indigenous tribe, learn about the legend of the mech guardian, and need to pass a trial to gain recognition," and the user is dissatisfied with all the preset options, they will enter "Zhao Yun" themselves. "Zhao Yun" is the target input content. Specifically, when the target user receives the second guidance information and does not choose any second response information provided by the AI, but instead directly enters a custom text (or voice input) through the text input box on the interface and confirms sending, a content input operation is triggered. The electronic device will immediately respond to this operation, capturing the original text string submitted by the user through the input box. This text data containing the user's personalized creative intent is the target input content.

[0051] Step b2: Based on the semantic information corresponding to the target input content, generate third guidance information related to the semantic information and at least one third response information corresponding to the third guidance information.

[0052] Third-round prompting refers to the next round of prompting questions generated after receiving the user's target input, based on an understanding of its semantics. For example, in response to the user's input of "Zhao Yun," the AI ​​might ask, "Wow, Zhao Yun! Do you want Zeng'er, the female knight-errant, to have some special connection with the famous Three Kingdoms general Zhao Yun?" This is third-round prompting. Third-round response information refers to a new round of options provided by the AI ​​in response to the third-round prompting. For example, options such as "Zeng'er is Zhao Yun's long-lost sister, who unexpectedly reunites with him in the martial arts world, and the siblings join forces to fight against treacherous officials," "Zeng'er travels back to the Three Kingdoms era, becoming Zhao Yun's deputy general, assisting him in protecting Liu Bei's son, Liu Shan, from an encirclement," and "Modern female knight-errant Zeng'er obtains the martial arts manual inherited by Zhao Yun, learns the Hundred Crows Paying Homage to the Phoenix Spear Technique, and roams the martial arts world" are third-round response information. Specifically, after obtaining the target input, natural language processing technology is used to analyze it to understand the semantic information contained in the text, such as identifying the themes, entities, emotions, or potential plot development directions involved. Based on a deep understanding of this semantic information, the AI ​​generates a new third guiding message, which is usually a follow-up question or confirmation aimed at continuing and refining the idea just mentioned by the user. At the same time, based on the same semantic understanding, the AI ​​dynamically generates or retrieves several options closely related to the third guiding message from the knowledge base, that is, at least one third response message, thereby guiding the user's free and linear text input back to the AI-controlled and structured multi-turn dialogue track.

[0053] Step b3, in response to the selection operation for the third reply information, determines the reply information for the next round.

[0054] Once the target user makes a selection from the third response provided by the AI, the electronic device responds to the interaction. At this point, the specific option selected by the user in this round of dialogue is designated as the new response. This new response, like all the responses confirmed by the user in previous rounds, is recorded by the electronic device as a valid node in the user's creative intent chain, collectively forming the material for subsequent content elements.

[0055] Step b4: Based on the semantic content of the target response information and the new round of response information, determine the content elements generated by the target object for the game scene.

[0056] The user's initial target response and subsequent responses in standard rounds are considered a complete and ordered semantic sequence. Through global semantic analysis, information extraction, and logical association of this sequence, all core elements crucial for constructing the game scenario can be identified and extracted, and these elements can be structurally organized into the final content elements. These content elements clearly define the core setting of the story, providing a complete and detailed creative blueprint for subsequent script generation.

[0057] For example, such as Figure 4 As shown, the content generation interface includes the following core controls and areas: The left-hand function option area offers three modes: AI interactive creation, custom script creation, and imported data creation. Users can choose to create from scratch or import and refine the plot based on existing data, depending on their needs. When the user selects the AI ​​interactive creation mode, the central dialogue interaction area is presented in natural language dialogue format. The AI ​​assistant proactively initiates questions and provides guidance, then gradually guides the user based on their selections or inputs, providing more specific environment options (Option A, Option B, Option C, such as three environments for discovering mech inheritance) or related options (such as generating story-related options related to Zhao Yun based on the user's input of "Zhao Yun"). The bottom input and control area includes a text input box, a voice button, and a send button, supporting free input from the user. It also includes a "I don't like it, please generate some more" button to request the AI ​​to regenerate options; a "Generate Story Outline" button to trigger the structured script generation process; a "Start Audition" button to directly trigger the plot performance; and a "Stop Dialogue" button to terminate the current dialogue interaction at any time, without preset round limits, entirely controlled by the user.

[0058] Furthermore, considering the potentially low level of expertise among the target creators, the AI ​​assistant incorporates specific prompts containing key creative elements of the script, content style, and plot progression logic. Through multiple rounds of dialogue, it gradually guides users to complete necessary elements such as background information, character information, and plot development. For example, when a user inputs the vague keyword "Zhao Yun," the AI ​​proactively asks, "Wow, Zhao Yun! Do you want Zeng'er, the heroine, to have some special connection with the famous Three Kingdoms general Zhao Yun?" and provides specific options such as "Zeng'er is Zhao Yun's long-lost sister, and they reunite to fight the enemy," "Zeng'er travels back in time to become Zhao Yun's deputy general to protect A Dou," and "Zeng'er obtains Zhao Yun's martial arts manual and ventures into the martial world," allowing users to complete their creation through natural dialogue. The AI ​​character, as a human-like guidance tool, can also be replaced with other forms, such as providing a plain text input interface, allowing users to directly input story background, general plot development, and other information, achieving the same goal of guiding creation. In this way, a complex creative task is successfully broken down into a series of simple interactive operations that can be executed on a graphical interface, thus completing the transformation from system function to a user-perceptible and operable interface.

[0059] In the above implementation, after receiving the second guidance information from the system, users are not limited to choosing from preset options, but can trigger a content input operation to actively input custom text content. This design breaks through the expressive limitations that pure option-based guidance may have, respects the creator's original thinking, and allows unique ideas or detailed descriptions that cannot be covered by preset options to be directly input. Subsequently, based on the semantic information of the target input content, a highly relevant third guidance information and a corresponding new set of response options are dynamically generated. This means that the system can understand the user's free expression and adjust the subsequent dialogue path and question focus accordingly, realizing an intelligent adaptive capability of user input-driven dialogue evolution. This mechanism ensures that the interaction process will not be interrupted or out of control due to the user's free expression, but can organically integrate and guide the user's custom input into the structured information collection. By comprehensively considering the user's previous selection (target response information) and the results of the new round of selections triggered by their custom input, the complete content elements are determined. This not only ensures the semantic coherence and integrity of the final generated elements, but also achieves a better balance between system guidance and user dominance in the entire creative process, significantly improving the tool's ability to capture and support complex and personalized creative intentions.

[0060] Step S303: Generate a scene structured script based on the target scene information represented by the content elements.

[0061] Specifically, step S303 includes: matching the content elements with a preset story template using an AI model to generate a chapter-based plot that conforms to dramatic theory; and generating a scene structured script based on the chapter-based plot according to a preset script format.

[0062] Pre-set story templates refer to standardized story structure models or frameworks pre-stored within electronic devices, abstracted and refined from a large number of classic narrative works (such as scripts, novels, and game plots). They can also be called pre-set scene templates. Chapter-based plots refer to detailed plot outlines generated by AI models based on user-input content elements and matching pre-set story templates, conforming to dramatic theory and featuring chapter divisions. Specifically, after acquiring the user-input content elements, the AI ​​model analyzes and understands this set of elements, identifying its core themes, character relationships, conflict types, and other abstract features. Subsequently, these features are intelligently compared and matched with one or more pre-set story templates, selecting the one that best fits the creative intent as the target template. Then, based on the inherent dramatic structure and plot progression logic of the target template, the AI ​​model reorganizes, fills in, and expands the user's scattered content elements, automatically generating a complete, chapter-based plot outline that conforms to professional narrative theory. This outline constitutes an intermediate result that macroscopically plans the entire story's development and clarifies the core objectives and key plot points of each chapter.

[0063] A predefined script format refers to a predefined structured data format or specification used to describe the game's plot, such as a specific JSON schema, XML template, or custom table format. Specifically, after obtaining the aforementioned chapter-by-chapter plot outline, the plot description of each chapter is further translated procedurally according to a predefined script data specification (i.e., the predefined script format) used by the game engine. This process typically involves decomposing and mapping the chapter-by-chapter plot, described in natural language, into various structured fields required by the predefined format, such as chapter identifiers, scene descriptions, character dialogue sequences, player interaction options, and conditional triggers. Ultimately, a uniformly formatted, machine-readable structured scene script is output. This script strictly adheres to the predefined data structure and can be directly parsed and executed by the subsequent game rendering engine, thereby driving the generation of in-game plot presentations.

[0064] More specifically, step S303 above includes: Step S3031: In response to the trigger operation of the script generation control, the target scene information represented by the content elements is split to obtain multiple sub-scene information.

[0065] Script generation controls refer to visual elements (such as icons or buttons) on the content generation interface. Clicking one triggers a process that transforms all dialogue content (content elements) into a structured script. Sub-scene information refers to the description of smaller narrative units obtained by breaking down a complete story outline (target scene information) according to dramatic structure. It typically corresponds to a chapter, scene, or key plot point in the story. For example, the complete story "Yongfu Dynasty" can be broken down into "Chapter 2 Yellow River Disaster Relief - Officialdom," "Chapter 3 Yellow River Disaster Relief - Fundraising," etc., where the specific content of each chapter (including objectives, processes, and branches) constitutes a sub-scene. Specifically, when the target user clicks a script generation control on the interface (such as the "Generate Story Outline" button), the electronic device responds to the trigger. Subsequently, the complete, macro-level target scene information (i.e., the entire story concept) represented by the previously determined content elements is processed. The breakdown process first requires decomposing this complete story information into a series of narrative units that are sequential in time and logically connected, based on a structured narrative framework. Each such unit is a sub-scene information, which corresponds to a chapter, scene, or key plot segment in the story, thus transforming a complex story into a series of story fragments that are easier to manage and implement.

[0066] In some optional implementations, the target scene information representing the content elements is broken down into multiple sub-scene information, including: Step c1: Match the target scene information represented by the content elements with multiple preset scene templates to obtain a target scene template that matches the target scene information represented by the content elements.

[0067] Pre-set scene templates refer to standardized story frameworks or models pre-stored within electronic devices, extracted from numerous classic script structures, such as the Hero's Journey model or the three-act play structure. Target scene templates refer to a specific template selected from the pre-set scene templates through a matching algorithm that best matches the content elements currently conceived by the user. Specifically, electronic devices store multiple pre-set scene templates, which are standardized story structure models abstracted from numerous classic narrative works. The matching process compares the target scene information represented by the content elements with these pre-set templates. By analyzing key features in the content elements (such as story type, core conflict, character relationships, etc.) and calculating their fit with each pre-set template, the template that best matches in narrative logic, plot rhythm, and structural elements is ultimately selected as the target scene template.

[0068] Step c2: Based on the scene structure of the target scene template, the content elements are split into multiple sub-scene elements, and the sub-scene information corresponding to each sub-scene element is generated.

[0069] Scene structure refers to the narrative framework and organization defined by the target scene template itself, including the number of stages the story should be divided into, the core conflict of each stage, and the objectives. Sub-scene elements refer to the specific content blocks into which user content elements are allocated and filled according to the scene structure of the target scene template. It is the concretization of content elements within a specific story structure. Specifically, based on the scene structure defined by the target scene template (i.e., the story stage divisions and core functions of each stage as specified by the template), the previously collected, loosely organized content elements are reorganized and allocated. Different content elements (such as introducing the protagonist, triggering a crisis, the final battle, and other key plot points) are filled into the corresponding positions in the template structure, thereby instantiating the macro-level content elements into a series of specific sub-scene elements that meet the template requirements. Finally, based on these allocated sub-scene elements, sub-scene information containing detailed content such as specific narrative text, character actions, and dialogue is generated, fully preparing for the final generation of an executable script.

[0070] In the above implementation, the user-conceptualized target scene information is matched with multiple pre-set scene templates to find the most suitable target scene template. This matching step is not a simple mechanical segmentation, but introduces a pattern recognition-based intelligent guidance, allowing the segmentation process to draw on mature and validated narrative or game scene structures, laying a solid foundation for subsequent processing that conforms to dramatic theory or game design logic. Next, based on the specific scene structure embedded in the matched target scene template, the user-provided content elements are systematically segmented to generate multiple logically coherent and functionally clear sub-scene elements, and further generating complete sub-scene information corresponding to each sub-scene element. This template-structure-based segmentation method ensures that the parsed sub-scenes are not only clearly distinguishable from each other, but their arrangement and combination naturally conform to an effective narrative or interactive flow, greatly enhancing the internal consistency and structural quality of the final generated script.

[0071] Step S3032: Based on the script structure corresponding to the preset script format, convert the information of each sub-scene into a scene structured script.

[0072] The default script format specifies which fields and data types should be included in the script so that the game engine can recognize and execute it. For example, Table 1 is a visual representation of a default script format, which includes fixed fields such as chapter ID, objective, check rules, and branches. The script structure refers to the data organization framework defined by the default script format. It determines how the generated scene structured script is logically and data-wise constructed.

[0073] Table 1

[0074] The transformation is performed according to a predefined script structure, a standardized data organization framework (e.g., specifying that a script must include fields such as chapter ID, scene description, character dialogue, branch options, and their hierarchical relationships). Specifically, the generated, still independent sub-scene information is used as raw material and systematically organized, mapped, and encapsulated according to the script structure specifications. For example, chapter targets from the sub-scene information are filled into the target field of the script structure, character dialogues are filled into the dialogue field, and all data is ensured to conform to preset format requirements, such as JSON, XML, or a specific table format. Finally, a complete scene-structured script is output. This script strictly follows the established structure logically and fully contains the details of all sub-scenes, thus becoming a standard data document that is easy for computer programs to parse and execute, as well as easy for users to read and modify.

[0075] The game scene content generation method provided in this application, by setting up a dedicated script generation control, hands over the initiative of script generation to the user. This allows the user to decide when to start the script generation process after confirming the completion of the concept and being satisfied with the content elements, avoiding the problem of inappropriate timing or interference with the user's continuous conception due to automatic system processing, thus improving the user's sense of control and experience in the creative process. Secondly, when generating the script, instead of simply packaging all content elements as a whole, the target scene information is first logically broken down to obtain multiple sub-scene information. This step essentially decomposes the complex overall concept into independent units that are easier to manage and process, making the subsequent script conversion more organized and precise, and helping to ensure the integrity of the final script in terms of structure and details. In addition, based on the script structure corresponding to the preset script format, the information of each sub-scene is converted into a unified structured script. This not only ensures that the generated script meets the requirements of specific technical specifications or game engines, achieving a high degree of standardization and executability, but also makes the conversion process reusable and adaptable. Only the preset format needs to be adjusted to generate scripts suitable for different performance media or platforms, greatly enhancing the flexibility and applicability of this application.

[0076] Step S304: Render the scene structure script, generate the target game scene, and display it in the graphical display interface.

[0077] Specifically, step S304 includes: Step S3041: Display the parsing results of the scene structured script. The parsing results include scene information and virtual character information.

[0078] The parsing results refer to the complete set of data used to drive the game scene performance, obtained after deconstructing and analyzing the structured script of the scene. Scene information refers to all the data in the parsing results used to describe and construct the virtual environment and its rules in which the plot takes place. For example, it may include environmental background, atmosphere rendering, interactive elements within the scene, chapter objectives, etc. Virtual character information refers to the detailed behavioral and attribute data of all non-player characters (NPCs) participating in the plot performance in the parsing results. For example, it may include character appearance, character attributes, character behavior, etc. Specifically, parsing the structured script of the scene means deeply interpreting its data content and structure to extract the core, displayable elements. This parsing result mainly includes two parts: first, scene information, which is a description of the environment in which the plot takes place, such as location, background, atmosphere, objectives, etc.; second, virtual character information, which is a description of non-player characters participating in the plot, such as character name, attributes, key actions or lines, etc. Subsequently, this parsed information is displayed in a graphical interface using one or more intuitive formats (e.g., listing key data in tables, showing plot branches in tree diagrams, or describing the plot outline in natural language summaries). The aim is to allow creators to quickly and clearly review and understand the core content and logical structure of the AI-generated script without reading the original code or data.

[0079] Step S3042: In response to the scene rendering operation triggered based on the parsing result, the game scene is rendered according to the scene information and virtual character information to generate the target game scene.

[0080] When the creator reviews the analysis results and triggers a scene rendering operation (such as clicking the "Start Audition" or "Play Story" button), the electronic device responds to the command. The rendering engine then begins working, such as... Figure 5 As shown, based on the scene information in the analysis results, it calls and instantiates corresponding background images, 3D scene models, environmental sound effects, and lighting effects from the resource library to construct a virtual space where the plot takes place. Simultaneously, based on the virtual character information, the engine loads the specified character models or portraits, places them in appropriate positions within the scene, and drives them to execute the actions and expressions specified in the script, displaying dialogue text at designated times. Through real-time graphics rendering technology, all visual and auditory elements are synthesized according to the script's sequence and logic, ultimately dynamically and immersively presenting the complete target game scene on the graphical display interface. This allows creators to intuitively experience their created plot, much like watching a short film. Furthermore, it can display the character attributes corresponding to the character models, such as Strength 15, Agility 15, and Constitution 15, as well as the text plot corresponding to the current game scene, facilitating user comparison and association.

[0081] The game scene content generation method provided in this application clearly displays the results of parsing the structured script of the scene to the user before directly executing the rendering operation. These results explicitly include the core elements constituting the game scene—scene information and virtual character information. This step is equivalent to providing the user with a reviewable, structured "blueprint" or preview before the final visual presentation, allowing the user to intuitively confirm whether the system's understanding of their creative intent is accurate and whether the key elements are complete. Secondly, the rendering operation is not automatic but requires a response to user-triggered instructions based on the parsing results. This design gives the user the final decision-making power over rendering, allowing them to initiate the resource-intensive rendering process only after confirming satisfaction with the parsing results. This two-stage "preview first, execute later" mechanism not only respects the user's control throughout the creative process and enhances the interactive experience but also effectively avoids invalid rendering caused by script parsing errors or user changes of mind, saving computational resources.

[0082] In some optional implementations, step S304 further includes: in response to the adjustment operation for the scene structured script, determining the adjusted scene structured script, and re-rendering to generate the updated target game scene.

[0083] When a creator is dissatisfied with the content after reviewing the analysis results or previewing the performance and triggers an adjustment operation (e.g., directly modifying text in the script editing interface, dragging and dropping to adjust the plot order, or changing character attribute values), the electronic device immediately captures these modification instructions. These operations are essentially direct or indirect modifications to the original scene structured script data model. Based on these operations, the electronic device updates the internally stored script data in real time or after verification, thereby generating a new data version that includes all the user's modification intentions. This updated data version is then identified as the adjusted scene structured script. Subsequently, the electronic device responds to the adjustment operation, re-executes the rendering process based on the adjusted scene structured script, generates the updated target game scene, and displays it in the graphical display interface, allowing the creator to see the modified effects in real time and achieving a rapid iterative closed loop of "creation-preview-adjustment-re-preview".

[0084] For example, while the electronic device is performing AI parsing and structured script generation in the background, the page displays a loading status. Once processing is complete, a pop-up appears asking the user if they want to view the structured script. If the user selects "yes," the script content is displayed on the screen, allowing the user to manually modify it. After modification, the user can click the "Start Audition" button on the same interface to trigger a scene reenactment.

[0085] In the above implementation, users are allowed to directly adjust the generated structured script itself. This design acknowledges and supports the inherent iterative and optimization properties of creative work, preventing users from being forced to abandon their current progress and restart the creative process due to minor deviations in the initial generated result or the emergence of new inspiration. By responding to such adjustment operations and determining the updated script accordingly, the efficient generation capabilities of artificial intelligence are effectively combined with the creator's final review rights, attention to detail, and subjective aesthetic judgment. Users can fine-tune structured information such as plot points, dialogue content, scene descriptions, or character behaviors according to personal preferences or specific needs, thereby ensuring that the final script used for rendering matches their creative intentions and quality requirements. This greatly improves user satisfaction and personalization of the output results.

[0086] In the following embodiment, the content generation method of the above game scene will be illustrated by taking the specific scenario of "creating a side story with a personal style for a role-playing game" as an example.

[0087] Players launch the game and access the AI-assisted creation tool provided in this application embodiment via the main game interface or a specific mode. When a player selects the "AI Interactive Creation" mode, a dialogue interface appears in the graphical user interface. The AI ​​assistant initiates guidance in a friendly and natural dialogue style, asking, "Hello! What kind of story would you like to create?" and providing multiple story options. After the player selects a story option, the AI ​​assistant generates and displays guidance information based on its built-in drama model and knowledge base, while also providing multiple response options. After the player selects a response, the AI ​​assistant immediately uses that as the target response, generating more targeted guidance information and providing multiple response options. During this process, if the player is not satisfied with the options, they can click "I don't like it, please generate some more" or directly enter free input in the input box at the bottom. The AI ​​assistant can instantly understand this target input and generate associated guidance information and options, thus achieving a balance between structured guidance and free creation.

[0088] Through multiple rounds of natural and accessible dialogue, players, guided step-by-step by the AI, gradually grasp the story's background, core characters, core conflicts, and key plot points. When players feel their ideas are sufficiently developed, they click the "Generate Story Outline" button on the interface. The electronic device then responds, summarizing all content elements accumulated during the dialogue in the background and invoking the AI ​​parsing and processing module. This module first performs a high-precision match between the theme and a pre-set scene template to determine the target scene template. Then, based on the template's three-act structure, it automatically breaks down and fills in the content elements, generating a detailed story outline containing multiple chapters. Next, the structured script generation module, using a preset script format recognizable by the game engine, transforms each chapter's outline into a structured script containing specific scene descriptions, character dialogue text, player choice branches, attribute check conditions, and other elements.

[0089] Once generated, a prompt appears asking the player, "Do you want to view and adjust the structured script?" The player selects "Yes," and a script editing interface clearly displaying the chapter flow, character dialogue, and branching options appears. The player can directly modify a line of dialogue or adjust the trigger conditions for a branch, just like editing a document. Once satisfied with the modifications, the player clicks the "Start Audition" button on the same interface. The story presentation module immediately starts, loading and parsing the adjusted scene structured script. The game screen switches, first rendering the initial environment of the first chapter based on the scene information. Then, based on the virtual character information, character A appears in the scene, and their attribute panel is displayed on one side of the interface. The preset camera language begins to operate, accompanied by ambient sound effects. The character performs corresponding actions according to the script, while dialogue bubbles display AI-generated lines that match the character's personality and historical context. The entire presentation is like an interactive short film, allowing the player to jump from inputting a few keywords to witnessing their conceived story vividly unfold in the game world within minutes. If a player is not satisfied with a particular performance, they can pause at any time, return to the script interface for fine-tuning, and then "test" again, achieving an efficient closed loop of creation, verification, and iteration.

[0090] The game scene content generation method provided in this application deeply integrates professional drama creation theory with powerful AI natural language understanding and generation capabilities. Through highly integrated graphical interaction and real-time rendering technology, it offers ordinary users a "zero-threshold, one-stop, instant feedback" game story creation solution, from a flash of inspiration to a visual result. This not only greatly lowers the creative threshold and stimulates user creativity, but also provides a powerful productivity tool for the continuous generation and diversification of game content.

[0091] This embodiment also provides a game scene content generation device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0092] This embodiment provides a content generation device for game scenes, such as... Figure 6 As shown, it includes: Display module 601 is used to display content and generate an interactive interface in a graphical display interface; The first determining module 602 is used to determine the content elements generated by the target object for the game scene in response to the interactive operation triggered on the content generation interactive interface. The generation module 603 is used to generate a scene structured script based on the target scene information represented by content elements; Rendering module 604 is used to render the scene structured script, generate the target game scene, and display it in the graphical display interface.

[0093] In some alternative implementations, the first determining module 602 includes: The first display submodule is used to display first guidance information and at least one first reply information corresponding to the first guidance information on the content generation interactive interface. The first determining submodule is used to determine the target response information and the second guiding information corresponding to the target response information in response to the target object's selection operation on the first response information. The second display submodule is used to display the second guidance information and at least one second reply information corresponding to the second guidance information on the content generation interactive interface. The second determination submodule is used to determine the new round of response information in response to the target object's selection operation for the second response information; The third determination submodule is used to determine the content elements generated by the target object for the game scene based on the semantic content of the target response information and the new round of response information.

[0094] In some alternative implementations, the first determining module 602 further includes: The first acquisition submodule is used to acquire the target input content in response to the content input operation triggered by the second guidance information in the content generation interactive interface of the target object. The generation submodule is used to generate third guidance information related to the semantic information and at least one third response information corresponding to the third guidance information based on the semantic information corresponding to the target input content. The fourth determination submodule is used to determine the new round of response information in response to the selection operation of the third response information; The fifth determination submodule is used to determine the content elements generated by the target object for the game scene based on the semantic content of the target response information and the new round of response information.

[0095] In some optional implementations, the content generation interface includes script generation controls, and the generation module 603 includes: The sub-module is used to respond to the trigger operation of the script generation control, and to split the target scene information represented by the content elements to obtain multiple sub-scene information. The conversion submodule is used to convert the information of each sub-scene into a scene structured script based on the script structure corresponding to the preset script format.

[0096] In some alternative implementations, the split submodules include: The matching unit is used to match the target scene information represented by the content element with multiple preset scene templates to obtain a target scene template that matches the target scene information represented by the content element. The splitting unit is used to split content elements into multiple sub-scene elements based on the scene structure of the target scene template, and generate sub-scene information corresponding to each sub-scene element.

[0097] In some alternative implementations, the rendering module 604 includes: The third display submodule is used to display the parsing results of the scene structured script, which include scene information and virtual character information. The second generation submodule is used to respond to scene rendering operations triggered based on the parsing results, and to render the game scene according to the scene information and virtual character information to generate the target game scene.

[0098] In some optional implementations, the game scene content generation apparatus further includes: The second determination module is used to determine the adjusted scene structured script in response to the adjustment operation for the scene structured script.

[0099] The game scene content generation apparatus provided in this application can execute the game scene content generation method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0100] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0101] The following is a detailed reference. Figure 7The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0102] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0103] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from memory 708, or installed from ROM 702. When the computer program is executed by processor 701, it performs the functions defined in the game scene content generation method of embodiments of this application.

[0104] Figure 7 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0105] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the content generation method for the game scene shown in the above embodiments is implemented.

[0106] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0107] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for generating content for a game scene, characterized in that, The method includes: Display content in a graphical interface to generate an interactive interface; In response to an interactive operation triggered by the content generation interface, determine the content elements generated by the target object for the game scene; Based on the target scene information represented by the content elements, a scene structured script is generated; The scene structure script is rendered to generate the target game scene, which is then displayed in the graphical display interface.

2. The method according to claim 1, characterized in that, The process of determining the content elements generated by the target object for the game scene in response to an interactive operation triggered on the content generation interface includes: The content generation interactive interface displays first guidance information and at least one first reply message corresponding to the first guidance information. In response to the target object's selection operation on the first reply information, a target reply information and the second guidance information corresponding to the target reply information are determined; The content generation interactive interface displays the second guidance information and at least one second reply information corresponding to the second guidance information; In response to the target object's selection operation on the second response information, a new round of response information is determined; Based on the semantic content of the target response information and the new round of response information, the content elements generated by the target object for the game scene are determined.

3. The method according to claim 2, characterized in that, The method further includes: In response to the content input operation triggered by the target object in the content generation interactive interface in response to the second guidance information, the target input content is obtained; Based on the semantic information corresponding to the target input content, generate third guidance information related to the semantic information and at least one third response information corresponding to the third guidance information; In response to the selection operation for the third response information, a new round of response information is determined; Based on the semantic content of the target response information and the new round of response information, the content elements generated by the target object for the game scene are determined.

4. The method according to claim 1, characterized in that, The content generation interactive interface includes a script generation control. The generation of a structured script based on the target scene information represented by the content elements includes: In response to a trigger operation on the script generation control, the target scene information represented by the content element is split to obtain multiple sub-scene information; Based on the script structure corresponding to the preset script format, the information of each sub-scene is converted into the scene structured script.

5. The method according to claim 4, characterized in that, The target scene information represented by the content elements is decomposed to obtain multiple sub-scene information, including: The target scene information represented by the content element is matched with multiple preset scene templates to obtain a target scene template that matches the target scene information represented by the content element. Based on the scene structure of the target scene template, the content elements are divided into multiple sub-scene elements, and sub-scene information corresponding to each sub-scene element is generated.

6. The method according to claim 1, characterized in that, The rendering of the scene structured script to generate the target game scene includes: The parsing results of the scene structured script are displayed, including scene information and virtual character information; In response to the scene rendering operation triggered based on the parsing result, the game scene is rendered according to the scene information and the virtual character information to generate the target game scene.

7. The method according to claim 6, characterized in that, The method further includes: In response to the adjustment operation on the scene structured script, the adjusted scene structured script is determined.

8. A content generation device for a game scene, characterized in that, The device includes: The display module is used to display content and generate interactive interfaces in a graphical display interface. The first determining module is used to determine the content elements generated by the target object for the game scene in response to the interactive operation triggered by the content generation interactive interface. The generation module is used to generate a scene structured script based on the target scene information represented by the content elements; The rendering module is used to render the scene structured script, generate the target game scene, and display it in the graphical display interface.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the content generation method for the game scene according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the content generation method for a game scene according to any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes computer instructions, which are used to cause a computer to perform the content generation method for the game scene according to any one of claims 1 to 7.

Images