Script-centric, interactive, drive scene generation system

Abstract

The application discloses a script-centered interactive driving scene generation system and relates to the technical field of interactive script generation, and specifically comprises the following modules: a script management module, a script arrangement module, a dependency propagation module, a narrative control interactive cooperation module and an execution output module; basic data structures of scripts are created, script attributes are distributed, script elements, constraints and logics are managed; scene nodes and events are identified, three layers of dependencies are constructed and weighted, reverse causal chains are generated through recursive dependency and depth-first search; dependency tables are maintained for each node, event-driven update and dirty node marking are performed, efficient dependency propagation and low-latency update are realized through a priority queue and differential generation; three levels of cooperation are divided to realize dynamic script generation and interaction, script control is realized based on a gated residual connection, a reverse causal chain and a time attention mechanism; an interactive execution layer is constructed, a real-time feedback mechanism is integrated, automatic script generation is realized and an executable format is output and displayed.

Description

Script-centric interactive scene generation system Technical Field

[0001] This invention relates to the field of interactive script generation technology, and more specifically to an interactive scene generation system centered on a script. Background Technology

[0002] With the rapid development of computer technology, artificial intelligence, virtual reality, and augmented reality, traditional linear narrative methods can no longer meet users' demands for personalized and diverse interactive experiences. While existing interactive media can provide basic user choices and plot branches, they still have limitations in handling complex plot dynamics, user behavior feedback, and multi-dimensional interactive experiences. Traditional preset scenes and plot development methods cannot adapt to rapidly changing user behaviors and interaction methods.

[0003] The existing technology has the following shortcomings:

[0004] (1) It is easy to drift in terms of style consistency, emotional direction and character behavior across scenes, making it difficult to always follow the structure and style constraints set by the script, and lacking controllable coverage of complex plots;

[0005] (2) In multiple rounds of dialogue and action decision-making, it is often difficult to maintain a clear causal chain, resulting in plot breaks, misplaced motives or contradictions, which affect the viewing experience and the ability to perform.

[0006] (3) The temporal alignment between text, speech, facial expressions, actions and scene environment is still weak, making it difficult to maintain consistency across different modalities, resulting in a decrease in scene immersion or instability at the execution level;

[0007] (4) Lacking a clear and interpretable path, creators find it difficult to understand the basis for the generation decision and to make precise adjustments to specific scene elements.

[0008] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0009] The purpose of this invention is to provide a script-centric interactive scene generation system to solve the problems mentioned in the background art.

[0010] To achieve the above objectives, the present invention provides the following technical solution: an interactive scene generation system centered on a script, specifically including the following modules: a script management module, a script arrangement module, a dependency propagation module, a narrative control interaction collaboration module, and an execution output module;

[0011] Script Management Module: Creates the basic data structure of a script, assigns script attributes, and manages script elements, constraints, and logic;

[0012] Script arrangement module: Identifies scene nodes and events, constructs and weights three-layer dependencies, and generates reverse causal chains through recursive dependencies and depth-first search;

[0013] Dependency propagation module: Maintains a dependency table for each node, performs event-driven updates and marks dirty nodes, and achieves efficient dependency propagation, fast redraw and low-latency updates through priority queues and differential generation;

[0014] The narrative control and interaction collaboration module is divided into three levels to realize dynamic script generation and interaction, and script control is realized based on gating residual connections, reverse causal chains and time attention mechanisms.

[0015] Execution output module: Constructs an interactive execution layer, integrates a real-time feedback mechanism, and automatically generates and outputs executable formats for scripts.

[0016] As a preferred embodiment of the script-centric interactive scene generation system described in this invention, wherein:

[0017] Create the basic data structure for the script, including nodes and edges between nodes, and assign script attributes to each node, including character, intent, emotion vector, duration cue, and modifiability flag.

[0018] Define the metadata of character script attributes in the character library, specifically including character ID, character attributes, initial state, and available actions / permissions;

[0019] When a character's script attribute is selected, the symbol validator is triggered, including checking for character conflicts and prompting for substitution or prohibition.

[0020] Associate the current state of the character's script attributes and inject it into the script's context;

[0021] Build an extensible tag library for intent script attributes, provide intent selection controls through a UI interface and allow users to fill in free text descriptions of their ideas, and use the selected intent as the highest priority instruction for attention bias and cue generation in the script narrative layer;

[0022] Construct a list of dimensions for the attributes of the emotional script, and provide an emotional time-series encoder through a visual editor;

[0023] Based on the stage of script generation, the emotional curve of the script is embedded into the script control layer through an emotional time series encoder, and joint encoding is performed based on the timeline and the current world state of the character.

[0024] The duration of the script attribute is used as a constraint in the script generation pipeline. When there are multiple duration constraints, the final market strategy is defined autonomously based on the priority and intensity of the nodes.

[0025] Determine whether a node is marked as a hard constraint when creating it;

[0026] When generating the script, this node is treated as a rule that must be satisfied by the script's narrative layer;

[0027] After generating the script, perform symbol verification. If the hard constraints are not met, immediately trigger local script repair or directly reject the generated script.

[0028] As a preferred embodiment of the script-centric interactive scene generation system described in this invention, wherein:

[0029] Identify, define, and classify the various scene nodes and event nodes in the script;

[0030] Construct a dependency graph between the script narrative layer, script control layer, and script interaction layer, and add weight values ​​for intent, emotion vector, and duration cues to the edges between each node in the dependency graph;

[0031] Based on recursive dependencies, the current node depends on multiple predecessor nodes. When generating the script, the causal relationship of the script is traced according to the recursive dependencies through depth-first search, and a reverse causal chain is generated.

[0032] By tracing the relationship between each emotional node through a reverse causal chain, the logical consistency of the plot is checked.

[0033] Construct a hybrid control architecture of symbolic and neural layers, and enrich the script based on the script narrative layer through a large language model;

[0034] Define a policy network as the controller, prioritizing hard constraints based on the needs of each decision point.

[0035] As a preferred embodiment of the script-centric interactive scene generation system described in this invention, wherein:

[0036] During script interaction, a dependency table is initialized for each node to record the other nodes that each node depends on;

[0037] When a node changes, check the downstream nodes of that node in the dependency graph;

[0038] By traversing the dependency graph, find all affected nodes;

[0039] When a script update is triggered, all affected nodes are iteratively updated based on the modified node as the initial point.

[0040] Dynamically update the dependency graph using an event-driven approach;

[0041] Register an event listener on each node so that an update is triggered immediately when the node content changes;

[0042] By marking the affected nodes, only those marked as dirty will be updated in the next render;

[0043] The processing nodes are updated by scheduling queues, all affected nodes are queued by priority, and latency is reduced by differential generation.

[0044] As a preferred embodiment of the script-centric interactive scene generation system described in this invention, wherein:

[0045] The script narrative layer is used as the context link of the higher level, and the script control layer and script interaction layer are used as the lower level to query the script narrative layer. The lower level is fed back to the higher level through the gated residual connection.

[0046] Based on the script's continuous actions and video sequences, temporal attention is added to the window through a reverse causal chain;

[0047] Configure independent control strategies for each layer, specifically including:

[0048] Script Narrative Layer: Based on the script's emotional curve and node priority, the planner generates a sketch of the script's event sequence, which is then used by the script control layer to develop the script.

[0049] Script control layer: Generates event chains for the script based on event sequence sketches;

[0050] Script Interaction Layer: Connects the fine-grained generator API and the physics post-processor API, allowing direct modification of keyframes in the script's continuous actions and video sequences, and feeding back to higher levels;

[0051] The narrative vectors of the script's narrative layer are brought closer together with the visual codes of the corresponding script's interaction layer in the same batch, while mismatched pairs are pulled apart.

[0052] Similarity regularization is applied to the event vectors of the script control layer and the corresponding interaction action vectors of the script interaction layer to encourage semantic matching;

[0053] Generate expected high-level statistics based on the script's narrative layer, and compare them with the currently generated low-level statistics;

[0054] The narrative vector generated based on the script interaction layer and the reverse causal chain verifies the periodic consistency.

[0055] The interaction depth is layered based on the script, specifically including:

[0056] Low-level interaction: Only the script narrative layer and script control layer are used to automatically generate interactive actions for the script interaction layer;

[0057] Medium-level interaction: Through editing nodes in the script control layer, interactive actions in the script interaction layer are generated based on the script narrative layer;

[0058] Highly interactive: By directly editing the interactive actions of the script interaction layer, a bottom-up consistency check is performed and local script updates are sent to the script control layer and the script narrative layer.

[0059] As a preferred embodiment of the script-centric interactive scene generation system described in this invention, wherein:

[0060] Build an interactive execution layer to dynamically adjust the plot and the order of events based on user input;

[0061] It integrates a real-time feedback mechanism to quickly update the plot status and character behavior, while maintaining the consistency of the script's logic;

[0062] The automated script generation algorithm automatically generates script content under given context or input conditions and adjusts it according to preset conditions.

[0063] The final output of the script is converted into an executable format, including text, actions, camera transitions, sound, and background music;

[0064] The generated script's interactive scenes are displayed on different platforms.

[0065] On the other hand, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements the steps of the script-centric interactive scene generation system as described above.

[0066] On the other hand, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements the steps of the script-centric interactive scene generation system as described above.

[0067] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0068] (1) By combining emotional vectors, intentional script attributes and emotional time sequence encoders, the emotions and behaviors of the characters can be adjusted in real time during the script generation process to ensure the consistency and logic of the plot, while adapting to the input and interaction needs of users.

[0069] (2) By introducing recursive dependency and reverse causal chain, the relationship between each node can be traced more accurately, reducing logical errors and inconsistencies in the plot. It can also dynamically identify and adjust the affected nodes, making the entire script generation process more natural and smooth.

[0070] (3) By introducing an emotion curve embedded into the script control layer and combining it with duration prompts, the duration of character behavior in the script can be precisely adjusted. The script content can be adjusted based on the priority and intensity of different nodes, so as to better realize the dynamic performance of the characters and the smooth transition of emotional changes.

[0071] (4) Through hard constraint marking, symbol verification and script repair mechanism, the preset rules can be forced to be met during the generation process, avoiding the generation of content that does not meet the constraints, ensuring the compliance of the generated script, and being able to repair it in time.

[0072] (5) By designing an interactive execution layer, the plot can be dynamically adjusted according to the user's input, and the behavior of the characters and the order of plot events can be updated in real time, so that the script generation can be highly personalized according to the user's needs, thereby enhancing the user experience and interactivity.

[0073] (6) By combining the symbolic layer and the neural layer through a hybrid control architecture and using a policy network as the controller, a more intelligent decision-making mechanism can be realized, which can adjust the generation strategy according to the complexity and needs of the script, thereby improving the quality and flexibility of script generation. Attached Figure Description

[0074] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0075] Figure 1 is a flowchart of the interactive scene generation system centered on the script according to the present invention.

[0076] Figure 2 is a schematic diagram of the interactive scene generation system centered on the script according to the present invention. Detailed Implementation

[0077] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0078] Example 1, referring to Figures 1 and 2, is the first embodiment of the present invention. This embodiment provides a script-centric interactive scene generation system, which specifically includes the following modules: script management module, script arrangement module, dependency propagation module, narrative control interaction collaboration module, and execution output module.

[0079] Script Management Module: Creates the basic data structure of a script, assigns script attributes, and manages script elements, constraints, and logic;

[0080] Create the basic data structure for the script, including nodes and edges between nodes, and assign script attributes to each node, including character, intent, emotion vector, duration cue, and modifiability flag.

[0081] Define the metadata of character script attributes in the character library, specifically including character ID, character attributes, initial state, and available actions / permissions;

[0082] When a character's script attribute is selected, the symbol validator is triggered, including checking for character conflicts and prompting for substitution or prohibition.

[0083] Associate the current state of the character's script attributes and inject it into the script's context;

[0084] Build an extensible tag library for intent script attributes, provide intent selection controls through a UI interface and allow users to fill in free text descriptions of their ideas, and use the selected intent as the highest priority instruction for attention bias and cue generation in the script narrative layer;

[0085] Construct a list of dimensions for the attributes of the emotional script, and provide an emotional time-series encoder through a visual editor;

[0086] Based on the stage of script generation, the emotional curve of the script is embedded into the script control layer through an emotional time series encoder, and joint encoding is performed based on the timeline and the current world state of the character.

[0087] The duration of the script attribute is used as a constraint in the script generation pipeline. When there are multiple duration constraints, the final market strategy is defined autonomously based on the priority and intensity of the nodes.

[0088] Determine whether a node is marked as a hard constraint when creating it;

[0089] When generating the script, this node is treated as a rule that must be satisfied by the script's narrative layer;

[0090] After generating the script, perform symbol verification. If the hard constraints are not met, immediately trigger local script repair or directly reject the generated script.

[0091] Script arrangement module: Identifies scene nodes and events, constructs and weights three-layer dependencies, and generates reverse causal chains through recursive dependencies and depth-first search;

[0092] Identify, define, and classify the various scene nodes and event nodes in the script;

[0093] Construct a dependency graph between the script narrative layer, script control layer, and script interaction layer, and add weight values ​​for intent, emotion vector, and duration cues to the edges between each node in the dependency graph;

[0094] Based on recursive dependencies, the current node depends on multiple predecessor nodes. When generating the script, the causal relationship of the script is traced according to the recursive dependencies through depth-first search, and a reverse causal chain is generated.

[0095] By tracing the relationship between each emotional node through a reverse causal chain, the logical consistency of the plot is checked.

[0096] Construct a hybrid control architecture of symbolic and neural layers, and enrich the script based on the script narrative layer through a large language model;

[0097] Define a policy network as the controller, prioritizing hard constraints based on the needs of each decision point.

[0098] Dependency propagation module: Maintains a dependency table for each node, performs event-driven updates and marks dirty nodes, and achieves efficient dependency propagation, fast redraw and low-latency updates through priority queues and differential generation;

[0099] During script interaction, a dependency table is initialized for each node to record the other nodes that each node depends on;

[0100] When a node changes, check the downstream nodes of that node in the dependency graph;

[0101] By traversing the dependency graph, find all affected nodes;

[0102] When a script update is triggered, all affected nodes are iteratively updated based on the modified node as the initial point.

[0103] Dynamically update the dependency graph using an event-driven approach;

[0104] Register an event listener on each node so that an update is triggered immediately when the node content changes;

[0105] By marking the affected nodes, only those marked as dirty will be updated in the next render;

[0106] The processing nodes are updated by scheduling queues, all affected nodes are queued by priority, and latency is reduced by differential generation.

[0107] The narrative control and interaction collaboration module is divided into three levels to realize dynamic script generation and interaction, and script control is realized based on gating residual connections, reverse causal chains and time attention mechanisms.

[0108] The script narrative layer is used as the context link of the higher level, and the script control layer and script interaction layer are used as the lower level to query the script narrative layer. The lower level is fed back to the higher level through the gated residual connection.

[0109] Based on the script's continuous actions and video sequences, temporal attention is added to the window through a reverse causal chain;

[0110] Configure independent control strategies for each layer, specifically including:

[0111] Script Narrative Layer: Based on the script's emotional curve and node priority, the planner generates a sketch of the script's event sequence, which is then used by the script control layer to develop the script.

[0112] Script control layer: Generates event chains for the script based on event sequence sketches;

[0113] Script Interaction Layer: Connects the fine-grained generator API and the physics post-processor API, allowing direct modification of keyframes in the script's continuous actions and video sequences, and feeding back to higher levels;

[0114] The narrative vectors of the script's narrative layer are brought closer together with the visual codes of the corresponding script's interaction layer in the same batch, while mismatched pairs are pulled apart.

[0115] Similarity regularization is applied to the event vectors of the script control layer and the corresponding interaction action vectors of the script interaction layer to encourage semantic matching;

[0116] Generate expected high-level statistics based on the script's narrative layer, and compare them with the currently generated low-level statistics;

[0117] The narrative vector generated based on the script interaction layer and the reverse causal chain verifies the periodic consistency.

[0118] The interaction depth is layered based on the script, specifically including:

[0119] Low-level interaction: Only the script narrative layer and script control layer are used to automatically generate interactive actions for the script interaction layer;

[0120] Medium-level interaction: Through editing nodes in the script control layer, interactive actions in the script interaction layer are generated based on the script narrative layer;

[0121] Highly interactive: By directly editing the interactive actions of the script interaction layer, a bottom-up consistency check is performed and local script updates are sent to the script control layer and the script narrative layer.

[0122] Execution output module: Constructs an interactive execution layer, integrates a real-time feedback mechanism, and automatically generates and outputs executable formats for scripts;

[0123] Build an interactive execution layer to dynamically adjust the plot and the order of events based on user input;

[0124] It integrates a real-time feedback mechanism to quickly update the plot status and character behavior, while maintaining the consistency of the script's logic;

[0125] The automated script generation algorithm automatically generates script content under given context or input conditions and adjusts it according to preset conditions.

[0126] The final output of the script is converted into an executable format, including text, actions, camera transitions, sound, and background music;

[0127] The generated script's interactive scenes are displayed on different platforms.

[0128] By combining emotion vectors, intentional script attributes, and emotion time-series encoders, the emotions and behaviors of characters can be adjusted in real time during script generation to ensure the consistency and logic of the plot, while also adapting to user input and interaction needs.

[0129] By introducing recursive dependencies and reverse causal chains, we can more accurately trace the relationships between each node, reduce logical errors and inconsistencies in the plot, and dynamically identify and adjust affected nodes, making the entire script generation process more natural and smooth.

[0130] By introducing an emotion curve embedded into the script control layer and combining it with duration prompts, the duration of character actions in the script can be precisely adjusted. The script content can be adjusted based on the priority and intensity of different nodes, so as to better achieve the dynamic performance of the characters and the smooth transition of emotional changes.

[0131] Through hard constraint marking, symbol verification, and script repair mechanisms, preset rules can be enforced during the generation process to avoid generating content that does not meet the constraints, ensuring the compliance of the generated script, and enabling immediate repair.

[0132] By designing an interactive execution layer, the plot can be dynamically adjusted based on user input, and the behavior of characters and the order of plot events can be updated in real time. This allows the script generation to be highly personalized according to user needs, enhancing user experience and interactivity.

[0133] By combining symbolic and neural layers through a hybrid control architecture and using a policy network as the controller, a more intelligent decision-making mechanism is achieved. This allows the generation strategy to be adjusted according to the complexity and needs of the script, thereby improving the quality and flexibility of script generation.

[0134] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A script-centric interactive scene generation system, characterized in that, Specifically, it includes the following modules: script management module, script arrangement module, dependency propagation module, narrative control interaction and collaboration module, and execution output module; script management module: creates the basic data structure of the script, assigns script attributes, and manages script elements, constraints and logic; script arrangement module: identifies scene nodes and events, builds and weights three-layer dependencies, and generates reverse causal chains through recursive dependencies and depth-first search; The script arrangement module is used to identify, define and classify various scene nodes and event nodes in the script; construct a dependency graph between the script narrative layer, script control layer and script interaction layer, and add weight values ​​of intent, emotion vector and duration cues to the edges between each node in the dependency graph; Based on recursive dependencies, the current node depends on multiple predecessor nodes. When generating the script, the causal relationship of the script is traced according to the recursive dependencies through depth-first search, and a reverse causal chain is generated. The relationship between each emotional node is traced through the reverse causal chain, and the logical consistency of the plot is checked. A hybrid control architecture of symbolic layer and neural layer is constructed, and the script is enriched based on the script narrative layer through a large language model. The dependency propagation module maintains a dependency table for each node and performs event-driven updates and dirty node marking. It achieves efficient dependency propagation, fast redrawing, and low-latency updates through priority queues and differential generation. The narrative control and interaction collaboration module divides the collaboration into three layers to achieve dynamic script generation and interaction. It implements script control based on gated residual connections, reverse causal chains, and temporal attention mechanisms. This module uses the script narrative layer as a high-level context link and the script control layer and script interaction layer as the bottom layers to query the script narrative layer. It then uses gated residual connections to feed back from the bottom layer to the top layer. Based on the script's continuous actions and video sequences, it incorporates temporal attention into the window through reverse causal chains. Set independent control strategies for each layer; bring the narrative vectors of the script narrative layer closer to the visual codes of the corresponding script interaction layer in the same batch, and distance mismatched pairs; perform similarity regularization on the event vectors of the script control layer and the interaction action vectors of the corresponding script interaction layer to encourage semantic matching; generate expected high-level statistics based on the script narrative layer and compare the currently generated low-level statistics; generate reverse-predicted narrative vectors based on the script interaction layer and reverse causal chain to verify periodic consistency; expand the interaction depth layer based on the script; execute the output module: build an interaction execution layer, integrate a real-time feedback mechanism, automatically generate the script and output an executable format.

2. The script-centric interactive scene generation system according to claim 1, characterized in that: The script management module assigns script attributes, including roles, intentions, emotion vectors, duration cues, and modifiability flags, by creating nodes and edges between them. The role script attributes define metadata in the role library; when a role script attribute is selected, a symbol validator is triggered, including checking for role conflicts and prompting for substitution or prohibition. The current state of the role script attribute is associated with and injected into the script's context. The intention script attributes construct an extensible tag library, providing intention selection controls through a UI interface and allowing users to freely fill in their ideas in free text. The selected intention serves as the highest priority instruction for attention bias and prompt generation in the script's narrative layer. The emotion vector attributes construct a dimensional list of emotion script attributes and provide an emotion time-series encoder through a visual editor. Based on the stage of script generation, the emotion curve of the script is embedded into the script control layer using the emotion time-series encoder, and joint encoding is performed based on the timeline and the character's current world state. The duration hint attribute: The duration hint script attribute is used as a constraint in the script generation pipeline. When there are multiple duration constraints, the final market strategy is autonomously defined based on the priority and strength of the nodes. The modifiable flag attribute: When creating a node, it is determined whether to mark it as a hard constraint. When generating a script, the node is used as a rule that must be met in the script narrative layer. After generating the script, symbol verification is performed. If the hard constraint is not met, local script repair is immediately triggered or the script generation result is directly rejected.

3. The script-centric interactive scene generation system according to claim 1, characterized in that: During script interaction, the dependency propagation module initializes a dependency table for each node, recording the other nodes that each node depends on. When a node changes, it checks the downstream nodes of that node in the dependency graph. It then traverses the dependency graph to find all affected nodes. When a script update is triggered, it iteratively updates all affected nodes based on the modified node as the starting point. The dependency graph is dynamically updated using an event-driven approach. Event listeners are registered on each node, and an update is triggered immediately when the node's content changes. By marking affected nodes and updating only those marked as dirty in the next render; by scheduling nodes to update processing nodes, all affected nodes are prioritized and latency is reduced through differential generation.

4. The script-centric interactive scene generation system according to claim 1, characterized in that: The independent control strategy for each layer specifically includes: Script Narrative Layer: Based on the script's emotional curve and node priorities, it generates an event sequence sketch of the script through a planner, which is then used by the script control layer for script development; Script Control Layer: Generates the event chain of the script based on the event sequence sketch; Script Interaction Layer: Connects the fine-grained generator API and the physical post-processor API, allowing direct modification of continuous actions in the script and keyframes in the video sequence, and feeding back to higher layers; The layered development based on script interaction depth specifically includes: Low-level interaction: Automatically generates interactive actions for the script interaction layer using only the script narrative layer and the script control layer; Medium-level interaction: Generates interactive actions for the script interaction layer based on the script narrative layer by editing nodes in the script control layer; High-level interaction: Performs bottom-up consistency checks and sends local script updates to the script control layer and the script narrative layer by directly editing the interactive actions of the script interaction layer.

5. The script-centric interactive scene generation system according to claim 1, characterized in that: The execution output module constructs an interactive execution layer, which dynamically adjusts the plot and the order of events based on user input; It integrates a real-time feedback mechanism to quickly update the plot status and character behavior while maintaining the coherence of the script logic; it automatically generates script content under given circumstances or input conditions through an automated script generation algorithm and adjusts it according to preset conditions. The final output of the script is converted into an executable format, including text, actions, camera transitions, sound, and background music; The generated script's interactive scenes are displayed on different platforms.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the module of the script-centric interactive scene generation system as described in any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the modules of the script-centric interactive scene generation system according to any one of claims 1 to 5.

Images