AIGC interactive story creation system, method, device and medium
The AIGC interactive story creation system, which integrates character definition, story construction, and visual generation modules, solves the problems of insufficient multimodal collaboration and creator control in complex interactive narratives of existing AI creation systems, and realizes efficient interactive content creation in multiple scenarios.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-08
- Publication Date
- 2026-04-03
AI Technical Summary
Existing AI creation systems suffer from a lack of structured and complex interaction support, fragmented multimodal collaboration, insufficient creator control, and bottlenecks in creating highly interactive content when generating complex interactive narratives, making it difficult to meet the needs of interactive narratives.
This paper presents an AIGC interactive story creation system that integrates modules for character definition, story construction, interaction settings, and visual generation. Through multimodal collaboration and a visual interface, it supports creators in customizing characters, story flow, and interactive tasks to generate interactive stories with multiple branching nodes, achieving collaborative generation of text and visual content.
It improves creators' efficiency and content quality, lowers the technical threshold for interactive content creation, supports highly interactive content design in various scenarios, and has a highly reusable logical structure.
Smart Images

Figure CN121787523A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of artificial intelligence-generated content technology. Specifically, this invention is applied to interactive narrative content creation scenarios, and particularly relates to an AIGC interactive story creation system, method, device, and medium. Background Technology
[0002] In recent years, AIGC technologies, represented by large language models (LLM, such as the GPT series) and Diffusion models, have made breakthrough progress in the creation of content such as text, images, and speech, significantly improving the efficiency and quality of content generation.
[0003] However, existing AI creation systems still have the following limitations when supporting complex interactive narrative needs:
[0004] First, there is a lack of support for structured and complex interactions: existing systems are unable to generate multi-turn interactive content with inherent logical connections, and cannot build a complete interactive story framework that includes character dialogue logic, mini-game embedding, and multi-branch node jumps. They can only output linear, single-form content, which cannot meet the interactive narrative's requirement for "process controllability".
[0005] Second, multimodal collaboration is fragmented: the generation of different modal content such as text, images, audio, and video relies on independent tools or modules, lacking a unified collaborative framework. This forces creators to switch between multiple platforms to complete content integration, which not only reduces creation efficiency but also easily leads to inconsistent styles of multimodal content.
[0006] Third, creators have insufficient control: the existing system only provides a one-way generation mode of "input prompts - output results", lacks a visual logic control interface for creators, and makes it difficult to realize advanced operations such as story path adjustment, node branch modification, and interaction rule setting. Creators need to repeatedly try to generate to get close to the expected effect, resulting in high creation costs.
[0007] Fourth, there are bottlenecks in the creation of highly interactive content: For scenarios such as interactive films and text adventure games that require "user participation to drive the plot," existing tools cannot provide structured AI assistance capabilities, making it difficult to balance the creativity of AI with the controllability of content, resulting in long development cycles and high technical barriers for highly interactive content.
[0008] In conclusion, with the rapid growth in demand for interactive narrative content, there is an urgent need for an AI-assisted creation system that integrates multimodal collaboration, a structured interactive framework, and deep creator participation to overcome existing technological limitations, lower the threshold for interactive content creation, and improve creation efficiency and quality. Summary of the Invention
[0009] The purpose of this invention is to provide an AIGC interactive story creation system, method, device, and medium to address the aforementioned problems in the prior art, thereby resolving all or one of the problems existing in the prior art.
[0010] To solve the above-mentioned technical problems, the specific technical solution of the present invention is as follows:
[0011] On one hand, the present invention provides an AIGC interactive story creation system, comprising:
[0012] The character definition module is used to: generate character illustrations based on user-defined character parameters, set character attributes, and create sound references;
[0013] The story building module is used to generate a story flow based on multiple branching nodes, based on user-defined story information.
[0014] The interaction module is used to: set interactive tasks for any node in the story flow based on user-defined interaction settings;
[0015] The visual content generation module is used to generate corresponding visual content for any node in the story flow based on user-defined visual generation requirements.
[0016] As an improved solution, the character definition module is also specifically used for: creating character illustrations based on images or prompts uploaded by creators.
[0017] As an improved solution, the character definition module is also specifically used to: improve the character name, gender and basic information based on the information input by the creator.
[0018] As an improved solution, the character definition module is further used to: parse the timbre and intonation parameters based on the target audio file uploaded by the creator and store them as character voice reference data.
[0019] As an improved solution, the story building module is further used to: generate a structured story graph containing starting nodes and branch nodes based on the creator's customized story title, opening, task objectives, achievement conditions, and story image descriptions. The structured story graph supports node editing and branch logic configuration.
[0020] As an improved solution, the interaction module is further used to: bind custom interaction types or interaction types in interaction templates according to the target story node selected by the creator.
[0021] As an improved solution, the visual content generation module is further used to: generate prompt words based on the node text according to the target story node selected by the creator, and at the same time generate corresponding candidate background illustrations and interactive CGs.
[0022] On the other hand, the present invention also provides an AIGC interactive story creation method, comprising the following steps:
[0023] Role definition:
[0024] Generate character illustrations based on user-defined character parameters, set character attributes, and create sound references;
[0025] Story Construction:
[0026] Generate a story flow based on multiple branching nodes based on user-defined story information;
[0027] Custom interaction:
[0028] Interactive tasks at any node in the story flow can be set according to user-defined interaction settings;
[0029] Visual content generation:
[0030] Generate corresponding visual content for any node in the story flow based on the user's customized visual generation requirements.
[0031] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the AIGC interactive story creation method.
[0032] On the other hand, the present invention also provides a computer device, the computer device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein:
[0033] The memory is used to store computer programs;
[0034] The processor is configured to execute the steps of the AIGC interactive story creation method by running programs stored in the memory.
[0035] The beneficial effects of the technical solution of this invention are:
[0036] 1. The AIGC interactive story creation system described in this invention can construct a structured creation process through the cooperation of system modules. It breaks down character definition, story design, interaction settings, and visual generation into independent and interconnected modules. With the help of a visual story flowchart, creators can intuitively build complex branch logic and complete highly interactive content design without professional development capabilities. It supports the collaborative generation and management of text and visual content and can be flexibly adapted to different scenarios such as interactive film and television, games, and education and training. Its logical structure and generation functions can be reused for the creation of different types of interactive content, significantly improving the creator experience and the quality of the final content.
[0037] 2. The AIGC interactive story creation method described in this invention can call system modules in an orderly manner, thereby realizing the system logic of the AIGC interactive story creation system described in this invention.
[0038] 3. The computer-readable storage medium of the present invention can enable the guidance system module to cooperate and thus realize the AIGC interactive story creation method of the present invention. Furthermore, the computer-readable storage medium of the present invention also effectively improves the operability of the AIGC interactive story creation method.
[0039] 4. The computer device described in this invention can store and execute the computer-readable storage medium, thereby realizing the AIGC interactive story creation method described in this invention. Attached Figure Description
[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0041] Figure 1 This is a schematic diagram of the architecture of the AIGC interactive story creation system described in Embodiment 1 of the present invention;
[0042] Figure 2 This is a flowchart illustrating the AIGC interactive story creation method described in Embodiment 2 of the present invention;
[0043] Figure 3 This is a schematic diagram of the structure of the computer device described in Embodiment 4 of the present invention;
[0044] The markings in the attached diagram are explained as follows:
[0045] 1501. Processor; 1502. Communication interface; 1503. Memory; 1504. Communication bus. Detailed Implementation
[0046] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby providing a clearer and more explicit definition of the scope of protection of the present invention.
[0047] In the description of this invention, it should be noted that the embodiments described in this invention are only some embodiments of this invention, not all embodiments; based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0048] The terms "first," "second," etc., used in this specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0049] Example 1
[0050] This embodiment provides an AIGC interactive story creation system, such as Figure 1 As shown, it includes:
[0051] The core of this invention lies in its multi-round human-computer collaboration design concept, which enables unified generation, editing, and management of multimodal content. The system integrates a Large Language Model (LLM) for text generation and logic parsing, and a Diffusion model for visual content generation, ensuring the generation capability and quality of multimodal content, as detailed below:
[0052] (1) Role definition module, used for:
[0053] (1.1) Generate character illustrations: Creators can select "upload image" or "enter prompt words" through the module interface;
[0054] In one alternative example, if an image is uploaded, the system calls an image parsing algorithm to extract the image's style features and generate a derivative version of the character illustration in the same style.
[0055] In one alternative example, if input prompts (such as "cartoon style, short blue hair, ancient style clothing"), the system supplements details (such as "gentle facial expression, clear clothing texture") through prompt optimization algorithms, and then calls the Diffusion model to generate multiple style candidate character illustrations;
[0056] In one alternative example, creators can modify the prompt (e.g., change "cartoon style" to "realistic style") or directly edit the character illustration details, and then click "regenerate" to complete the iteration;
[0057] (1.2) Setting character attributes: Provides an attribute editing form, where creators can manually fill in basic information such as character name and gender;
[0058] In one alternative example, if "AI generation" is selected, the core character settings need to be entered, and the system will call LLM to generate an introduction, opening remarks, and hidden information;
[0059] In one alternative example, the creator can directly modify the generated attribute text, or add additional hints and regenerate;
[0060] (1.3) Voice reference: The creator uploads the target audio file, and the system analyzes the timbre and intonation parameters through the audio feature extraction algorithm and stores them as character voice reference data.
[0061] (2) Story building module, used for:
[0062] (2.1) Input basic story information: The creator inputs the story title, opening remarks, task objectives, achievement conditions, and story image descriptions on the interface;
[0063] (2.2) Generate a structured story graph: Input information is passed into LLM and the initial story flowchart is generated through the plot logic parsing algorithm, including: starting node, branch node, and trigger conditions labeled for each node;
[0064] In one alternative example, the story flowchart is presented visually, with nodes represented by rectangles and branches by arrowed lines, and supports scaling and dragging adjustments;
[0065] (2.3) Setting up node editing and branching logic: Creators can click on any node to enter the editing interface, where they can modify the node text or insert interactive options;
[0066] In one optional example, in the "Branch Logic Settings" section, you can select the trigger condition type:
[0067] If you select "Mini-game success or failure", bind the "XXX" mini-game, and set "If the game succeeds, proceed to the 'XXX' branch; if the game fails, proceed to the 'XXX' branch";
[0068] If you select "Character Response", set "XX's two responses to 'XX' correspond to different branches". After completing the settings, the system will automatically update the story map.
[0069] (3) Interaction module, used for:
[0070] (3.1) Binding Interaction Operations: When the creator selects the target story node, such as by clicking the Bind Interaction button, the system will pop up a list of interaction types, including but not limited to: "Tabletop RPG Check" and "Mini-Game". Ultimately, the interaction results will influence and intervene in the direction of the story branches.
[0071] (3.2) Calling Interaction Templates: If the creator does not need to customize, he / she can select a preset template from the interaction template library (such as "Basic Tabletop RPG Test" or "Question and Answer Game"). The template contains default rules and interface styles. The creator only needs to modify key parameters (such as "Test Attributes" and "Game Score Threshold") to quickly bind the template, thus reducing the threshold of interaction design.
[0072] (4) Visual content generation module, used for:
[0073] (4.1) Generate visual content: The creator selects the node to which visual content needs to be added, and the system calls the prompt word automatic generation unit to generate prompt words based on the node text; the Diffusion model is called to generate candidate background illustrations and interactive CG;
[0074] (4.2) Multi-round optimization and version management: If the creator is not satisfied with a certain background illustration, he / she can modify the prompt words or directly doodle and edit the details to regenerate a new result; the system automatically saves each generated version, and the creator can switch to view different versions through the version management interface and select the best result to bind to the story node.
[0075] It should be noted that the above examples are merely for explaining the present invention and should not be construed as limiting the scope of protection of the present invention.
[0076] Example 2
[0077] This embodiment is based on the same inventive concept as the AIGC interactive story creation system described in Embodiment 1, and provides an AIGC interactive story creation method, such as... Figure 2 As shown, it includes the following steps:
[0078] S100, Role Definition:
[0079] Generate character illustrations based on user-defined character parameters, set character attributes, and create sound references;
[0080] S200, Story Construction:
[0081] Generate a story flow based on multiple branching nodes based on user-defined story information;
[0082] S300, Custom Interaction:
[0083] Interactive tasks at any node in the story flow can be set according to user-defined interaction settings;
[0084] S400, Visual Content Generation:
[0085] Generate corresponding visual content for any node in the story flow based on the user's customized visual generation requirements.
[0086] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific logical process of the method described above can be referred to the corresponding working process of the system, device and unit in the foregoing method embodiments, and will not be repeated here.
[0087] Example 3
[0088] This embodiment provides a computer-readable storage medium, including:
[0089] The storage medium is used to store computer software instructions for implementing the AIGC interactive story creation method described in Embodiment 2 above. It includes programs for executing the AIGC interactive story creation method. Specifically, the executable program can be built into the AIGC interactive story creation system described in Embodiment 1. In this way, the AIGC interactive story creation system can implement the AIGC interactive story creation method described in Embodiment 2 by executing the built-in executable program.
[0090] Furthermore, the computer-readable storage medium in this embodiment can be any combination of one or more readable storage media, wherein the readable storage medium includes an electrical, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
[0091] Example 4
[0092] This embodiment provides an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 1501, a communication interface 1502, a memory 1503, and a communication bus 1504, wherein the processor 1501, the communication interface 1502, and the memory 1503 communicate with each other through the communication bus 1504.
[0093] Memory 1503 is used to store computer programs;
[0094] When the processor 1501 executes the computer program stored in the memory 1503, it implements the steps of the AIGC interactive story creation method described in Embodiment 1 above.
[0095] As one embodiment of the present invention, the communication bus mentioned in the terminal above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0096] As one embodiment of the present invention, the communication interface is used for communication between the aforementioned terminal and other devices.
[0097] In one embodiment of the present invention, the memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.
[0098] As one embodiment of the present invention, the processor described above may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0099] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.
[0100] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.
[0101] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.
[0102] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.
[0103] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.
[0104] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0105] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this paper, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0106] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.
Claims
1. An AIGC interactive story creation system, characterized in that, include: The character definition module is used to: generate character illustrations based on user-defined character parameters, set character attributes, and create sound references; The story building module is used to generate a story flow based on multiple branching nodes, based on user-defined story information. The interaction module is used to: set interactive tasks for any node in the story flow based on user-defined interaction settings; The visual content generation module is used to generate corresponding visual content for any node in the story flow based on user-defined visual generation requirements.
2. The AIGC interactive story creation system according to claim 1, characterized in that: The character definition module is also specifically used for: creating character illustrations based on images or prompts uploaded by creators.
3. The AIGC interactive story creation system according to claim 1, characterized in that: The character definition module is also specifically used to: improve the character name, gender and basic information based on the information input by the creator.
4. The AIGC interactive story creation system according to claim 1, characterized in that: The character definition module is further used to: parse the timbre and intonation parameters based on the target audio file uploaded by the creator and store them as character voice reference data.
5. The AIGC interactive story creation system according to claim 1, characterized in that: The story building module is further used to generate a structured story graph containing starting nodes and branch nodes based on the story title, opening, task objectives, achievement conditions and story image descriptions customized by the creator. The structured story graph supports node editing and branch logic configuration.
6. The AIGC interactive story creation system according to claim 1, characterized in that: The interaction module is further used to: bind custom interaction types or interaction types in an interaction template based on the target story node selected by the creator.
7. The AIGC interactive story creation system according to claim 1, characterized in that: The visual content generation module is further used to: generate prompt words based on the node text according to the target story node selected by the creator, and at the same time generate corresponding candidate background illustrations and interactive CGs.
8. An AIGC interactive story creation method based on the AIGC interactive story creation system according to any one of claims 1 to 7, characterized in that, The method includes the following steps: Role definition: Generate character illustrations based on user-defined character parameters, set character attributes, and create sound references; Story Construction: Generate a story flow based on multiple branching nodes based on user-defined story information; Custom interaction: Interactive tasks at any node in the story flow can be set according to user-defined interaction settings; Visual content generation: Generate corresponding visual content for any node in the story flow based on the user's customized visual generation requirements.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the AIGC interactive story creation method of claim 8.
10. A computer device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: The memory is used to store computer programs; The processor is configured to execute the steps of the AIGC interactive story creation method of claim 8 by running a program stored in the memory.