A split-screen adjustment demonstration system based on artificial intelligence

Abstract

The application discloses a kind of based on artificial intelligence's split lens adjustment demonstration system, specifically relates to video split lens technical field, it includes for parsing user input text and preliminary visual material and it is converted into structured data for subsequent processing split lens input semantic analysis module.This application will text description be converted into structured data and extract scene elements, to provide accurate data support for subsequent shot language analysis, composition optimization and scene scheduling, shot analysis optimization module identifies potential problems and provides optimization suggestions by analyzing shot language and composition, help to improve the accuracy and visual effect of shot, intelligent adjustment video generation module automatically adjusts split lens parameters and generates preliminary demonstration video according to optimization suggestions, video details can be further adjusted through interactive editing module, ensure that video quality reaches expectation, improve the intelligent level of system, to enhance the flexibility, innovation and efficiency of split lens adjustment.

Description

Technical Field

[0001] This invention relates to the field of video storyboard technology, and in particular to an artificial intelligence-based storyboard adjustment demonstration system. Background Technology

[0002] As the film, advertising, and animation industries increasingly demand higher quality and efficiency in video production, the technical requirements for storyboard adjustments and video creation are gradually increasing. Storyboards are a fundamental element of film and television works, determining the narrative style, visual expressiveness, and the audience's visual experience. Traditional storyboard adjustments largely rely on manual operation. Production staff manually adjust shots, compositions, focus, and scene elements based on the script, director's intentions, and visual requirements. This is a massive workload, easily influenced by subjective factors, resulting in low efficiency and difficulty in meeting rapidly changing creative demands. Furthermore, manual storyboard adjustments often fail to fully optimize camera language, composition, and scene arrangement, potentially leading to issues such as inconsistent visuals and poor visual effects, impacting the overall quality of the work.

[0003] While current video production software and systems have introduced some automation and intelligent functions, most remain limited to simple editing or shot transition adjustments. Although image processing technology has made some progress, existing technologies have not yet achieved comprehensive intelligence and precision in storyboard language analysis, composition optimization, and shot adjustment. Existing shot adjustment systems cannot accurately capture the details of each shot and scene, and often cannot automatically adapt to different styles and creative needs, limiting the creative space of creators. Due to the lack of in-depth analysis of shot language and scene elements in existing systems, optimization suggestions and adjustments still require considerable manual intervention, thus affecting creative efficiency and quality. Therefore, we provide an AI-based storyboard adjustment demonstration system. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing an artificial intelligence-based storyboard adjustment demonstration system.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] An AI-based storyboard adjustment demonstration system includes a storyboard input semantic parsing module for parsing user-input text and preliminary visual materials and converting them into structured data for subsequent processing; a shot analysis and optimization module for performing comprehensive shot language and composition analysis on the storyboard; an intelligent adjustment video generation module for automatically applying optimization adjustments and generating demonstration videos; and a feedback iteration system learning module for collecting user feedback and continuously learning and optimizing algorithms.

[0007] The storyboard input semantic parsing module includes an input interface design module for providing a user-friendly interface for inputting storyboard scripts, a natural language parsing module for analyzing and parsing the input text descriptions and converting them into operable structured data, a scene semantic recognition module for identifying and classifying scene categories in the input descriptions and extracting scene elements, and a data management and storage module for storing and managing the input storyboard data and parsing results.

[0008] The shot analysis and optimization module includes a shot language evaluation module for analyzing shot language and identifying potential shot errors based on input storyboard data, a composition and visual optimization module for providing suggestions for composition improvement, a scene scheduling evaluation module for analyzing the scheduling of characters and props to ensure reasonable configuration in the scene, and a creative generation and recommendation module for calling the built-in creative library to provide diverse creative suggestions.

[0009] The present invention is further configured such that: the intelligent adjustment video generation module includes an automated storyboard adjustment module for automatically adjusting storyboard parameters according to the suggestions of the analysis module, a user feedback integration module for allowing users to view adjustment suggestions and selectively apply them or manually fine-tune them, a rendering and video generation module for generating a preliminary demonstration video from the adjusted storyboard data, and an interactive editing and optimization module for providing a user interface that allows users to directly edit the generated video in detail within the system;

[0010] The feedback iterative system learning module includes a video expectation-actual comparison module for comparing the generated video with the user's expectations to identify differences, an adaptive proposal generation module for generating adjustment suggestions based on comparison analysis to narrow the gap between the expected and actual effects, a learning feedback algorithm optimization module for automatically adjusting the analysis and generation algorithm based on the user's adjustment feedback, and a system update resource management module for regularly updating the system's creative library and analysis model.

[0011] The present invention is further configured such that the automated storyboard adjustment module includes a shot grammar analysis module for detecting and parsing shot language using image processing and grammar analysis techniques, a composition optimization calculation module for calculating the optimal composition based on visual composition principles such as the golden ratio and the rule of thirds, a dynamic focus adjustment module for automatically adjusting the focus position according to scene changes, a scene element scheduling module for optimizing the position and movement path of characters and props in the scene, a multi-shot collaborative adjustment module for coordinating multiple shots to ensure overall visual consistency, a user feedback learning module for optimizing the adjustment algorithm using user feedback data, and a quality assessment decision module for evaluating whether the adjusted storyboard meets the preset quality standards and deciding whether to accept it, further optimize it, or provide feedback to the user for manual adjustment.

[0012] The present invention is further configured such that: the shot grammar analysis module is responsible for parsing the shot language and scene structure, providing necessary visual information for the composition optimization calculation module; the composition optimization calculation module provides the shot composition framework for the dynamic focus adjustment module by calculating the best composition principle; the dynamic focus adjustment module automatically adjusts the focus position according to scene changes and the movement of characters / objects to ensure the focus and clarity of the visual effect, while providing the focus position basis for the scene element scheduling module.

[0013] The present invention is further configured such that: the scene element scheduling module optimizes the position and movement path of characters and props in the scene based on the focus adjustment result, providing accurate element scheduling information for the multi-camera collaborative adjustment module; the multi-camera collaborative adjustment module coordinates the switching and visual transition between multiple cameras to ensure overall visual consistency, providing adjusted camera data for the user feedback learning module; the user feedback learning module adjusts the algorithm strategy based on user feedback to optimize the camera design and adjustment process, providing optimized camera data for the quality assessment decision module.

[0014] The invention is further configured such that: the input interface design module provides a user-friendly interface for inputting storyboard scripts, providing input data to the natural language parsing module, ensuring that the text descriptions input by the user can be received and parsed by the system; the natural language parsing module analyzes and converts the text input by the user into structured data, providing parsed text descriptions to the scene semantic recognition module, helping to identify and classify scene elements; the scene semantic recognition module extracts scene category and element information based on the structured data output by the natural language parsing module, providing necessary data storage and management for the data management and storage module; the data management and storage module stores and manages storyboard data and parsing results, providing structured input data for the subsequent shot analysis and optimization module.

[0015] The invention is further configured as follows: the shot language evaluation module performs shot language analysis based on the input storyboard data, identifies potential shot errors, and provides shot improvement suggestions to the composition and visual optimization module; after receiving the optimization suggestions from the shot language evaluation module, the composition and visual optimization module improves the composition and provides improved composition information to the scene scheduling evaluation module; based on the composition optimization results, the scene scheduling evaluation module analyzes the scheduling of characters and props in the scene to ensure their reasonable configuration and provides scene scheduling evaluation data to the creative generation and recommendation module; the creative generation and recommendation module calls the built-in creative library and generates diverse creative suggestions based on the information provided by the aforementioned modules, providing more creative directions for subsequent storyboard adjustments.

[0016] The invention is further configured as follows: the automated storyboard adjustment module automatically adjusts the storyboard parameters based on the suggestions provided by the shot analysis and optimization module, and transmits the adjusted storyboard data to the user feedback integration module, allowing the user to view the suggestions and selectively apply or fine-tune them; the user feedback integration module allows the user to view the automatic adjustment suggestions and fine-tune or selectively apply them, and transmits the adjusted data after user feedback to the rendering and video generation module to generate a preliminary demonstration video; the rendering and video generation module converts the adjusted storyboard data into a preliminary demonstration video and provides a video file to the interactive editing and optimization module, allowing the user to further edit the video in detail; the interactive editing and optimization module provides a user interface, allowing the user to edit and optimize the generated video within the system, and ultimately adjust the video quality.

[0017] The invention is further configured as follows: the video expectation-to-actual comparison module compares the generated video with the user's expectation, identifies the differences, and passes the results to the adaptive proposal generation module; the adaptive proposal generation module generates adjustment suggestions based on the analysis results of the video expectation-to-actual comparison module, narrows the gap between the expectation and the actual effect, and passes the adjustment suggestions to the learning feedback algorithm optimization module for adjusting the analysis and generation algorithms; the learning feedback algorithm optimization module continuously optimizes the analysis and generation algorithms based on the user's adjustment feedback, improves the intelligence level of storyboard adjustment, and provides updated data and models for the system update resource management module; the system update resource management module regularly updates the system creative library and analysis model, providing the entire system with the latest creative resources and analysis tools.

[0018] The beneficial effects of this invention are as follows:

[0019] 1. This invention uses a storyboard input semantic parsing module to transform text descriptions into structured data and extract scene elements, thereby providing accurate data support for subsequent shot language analysis, composition optimization, and scene scheduling. The shot analysis and optimization module analyzes shot language and composition, identifies potential problems, and provides optimization suggestions to help improve the accuracy and visual effects of shots. The intelligent adjustment video generation module automatically adjusts the storyboard parameters based on the optimization suggestions and generates a preliminary demonstration video. Users can further adjust video details through the interactive editing and optimization module to ensure that the video quality meets expectations. The feedback iterative system learning module analyzes the differences between user feedback and generated videos, continuously optimizes and adjusts the algorithm, improves the system's intelligence level, and thus enhances the flexibility, innovation, and efficiency of storyboard adjustments.

[0020] 2. This invention uses image processing and grammatical analysis techniques to analyze shot language and scene structure, providing crucial visual information for subsequent composition optimization. The composition optimization calculation module calculates the optimal composition based on principles such as the golden ratio and the rule of thirds, ensuring that the shot is more visually impactful. The dynamic focus adjustment module automatically adjusts the focus according to scene changes or character movement, improving image clarity and focusing effect. The scene element scheduling module optimizes the layout and movement paths of characters and props, making the scene more reasonable and improving the consistency of visual effects. The multi-shot collaborative adjustment module coordinates the switching and visual transitions between multiple shots, ensuring the overall visual smoothness and unity of the video. Finally, through automated shot optimization and learning adjustments based on user feedback, the system reduces manual intervention, improves the efficiency and accuracy of shot adjustments, and provides greater creative space and flexibility for creators. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the system modules in this invention.

[0022] Figure 2 This is a schematic diagram of the system flow of the automated storyboard adjustment module in this invention. Detailed Implementation

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0024] Example 1

[0025] like Figure 1 As shown, an AI-based storyboard adjustment demonstration system includes a storyboard input semantic parsing module for parsing user-input text and preliminary visual materials and converting them into structured data for subsequent processing; a shot analysis and optimization module for performing comprehensive shot language and composition analysis on the storyboard; an intelligent adjustment video generation module for automatically applying optimization adjustments and generating demonstration videos; and a feedback iteration system learning module for collecting user feedback and continuously learning and optimizing algorithms.

[0026] The storyboard input semantic parsing module includes an input interface design module for providing a user-friendly interface for inputting storyboard scripts, a natural language parsing module for analyzing and parsing the input text descriptions and converting them into operable structured data, a scene semantic recognition module for identifying and classifying scene categories in the input descriptions and extracting scene elements, and a data management and storage module for storing and managing the input storyboard data and parsing results.

[0027] The shot analysis and optimization module includes a shot language evaluation module for analyzing shot language and identifying potential shot errors based on input shot data, a composition and visual optimization module for providing suggestions for composition improvement, a scene scheduling evaluation module for analyzing the scheduling of characters and props to ensure reasonable configuration in the scene, and a creative generation and recommendation module for calling the built-in creative library to provide diverse creative suggestions.

[0028] The intelligent adjustment video generation module includes an automated storyboard adjustment module for automatically adjusting storyboard parameters based on the analysis module's suggestions, a user feedback integration module for allowing users to view adjustment suggestions and selectively apply them or manually fine-tune them, a rendering and video generation module for generating a preliminary demonstration video from the adjusted storyboard data, and an interactive editing and optimization module for providing a user interface that allows users to directly edit the generated video in detail within the system.

[0029] The feedback iterative system learning module includes a video expectation-actual comparison module for comparing the generated video with the user's expectation to identify differences, an adaptive proposal generation module for generating adjustment suggestions based on comparison analysis to narrow the gap between the expected and actual effects, a learning feedback algorithm optimization module for automatically adjusting the analysis and generation algorithm based on the user's adjustment feedback, and a system update resource management module for regularly updating the system's creative library and analysis model.

[0030] The input interface design module provides a user-friendly interface for inputting storyboard scripts, providing input data to the natural language processing module and ensuring that the user's text descriptions can be received and parsed by the system. The natural language processing module analyzes and converts the user's input text into structured data, providing parsed text descriptions to the scene semantic recognition module to help identify and classify scene elements. The scene semantic recognition module extracts scene category and element information based on the structured data output by the natural language processing module, providing necessary data storage and management for the data management and storage module. The data management and storage module stores and manages storyboard data and parsing results, providing structured input data for the subsequent shot analysis and optimization module.

[0031] The shot language evaluation module analyzes the input storyboard data to identify potential shot errors and provides shot improvement suggestions to the composition and visual optimization module. After receiving the optimization suggestions from the shot language evaluation module, the composition and visual optimization module improves the composition and provides improved composition information to the scene scheduling evaluation module. Based on the composition optimization results, the scene scheduling evaluation module analyzes the scheduling of characters and props in the scene to ensure their reasonable configuration and provides scene scheduling evaluation data to the creative generation and recommendation module. The creative generation and recommendation module calls the built-in creative library and generates diverse creative suggestions based on the information provided by the aforementioned modules, providing more creative directions for subsequent storyboard adjustments.

[0032] The automated storyboard adjustment module automatically adjusts storyboard parameters based on suggestions from the shot analysis and optimization module, and transmits the adjusted storyboard data to the user feedback integration module, allowing users to view the suggestions and selectively apply or fine-tune them. The user feedback integration module allows users to view the automatic adjustment suggestions and make fine-tuning or selective applications, and transmits the adjusted data to the rendering and video generation module to generate a preliminary demo video. The rendering and video generation module converts the adjusted storyboard data into a preliminary demo video and provides video files to the interactive editing and optimization module, allowing users to further refine the video. The interactive editing and optimization module provides a user interface, allowing users to edit and optimize the generated video within the system, ultimately adjusting the video quality.

[0033] The video expectation-to-actual comparison module compares the generated video with the user's expectations, identifies differences, and passes the results to the adaptive proposal generation module. Based on the analysis results from the video expectation-to-actual comparison module, the adaptive proposal generation module generates adjustment suggestions to narrow the gap between expectations and actual results, and passes these suggestions to the learning feedback algorithm optimization module for adjusting the analysis and generation algorithms. The learning feedback algorithm optimization module continuously optimizes the analysis and generation algorithms based on user feedback, improving the intelligence of storyboard adjustments and providing updated data and models to the system update resource management module. The system update resource management module regularly updates the system's creative library and analysis models, providing the entire system with the latest creative resources and analysis tools.

[0034] In the above embodiments, the storyboard input semantic parsing module parses the user-input storyboard script, converting the text into structured data and extracting scene categories and element information. Then, the shot analysis and optimization module analyzes shot language and composition, identifies potential problems, and provides optimization suggestions to further optimize shot composition, scene scheduling, and creative direction. Next, the intelligent adjustment video generation module automatically applies these optimization suggestions to generate a preliminary demonstration video, and allows users to further fine-tune video details through an interactive editing and optimization module. The system also uses a feedback iterative system learning module to compare the generated video with user expectations, automatically generating adjustment suggestions and continuously optimizing the storyboard adjustment algorithm and creative library based on user feedback, thereby constantly improving the system's intelligence level.

[0035] Example 2

[0036] like Figure 1-2 As shown, an AI-based storyboard adjustment demonstration system includes an automated storyboard adjustment module comprising: a shot grammar analysis module for detecting and parsing shot language using image processing and grammar analysis techniques; a composition optimization calculation module for calculating the optimal composition based on visual composition principles such as the golden ratio and the rule of thirds; a dynamic focus adjustment module for automatically adjusting the focus position according to scene changes; a scene element scheduling module for optimizing the position and movement path of characters and props in the scene; a multi-shot collaborative adjustment module for coordinating multiple shots to ensure overall visual consistency; a user feedback learning module for optimizing the adjustment algorithm using user feedback data; and a quality assessment decision module for evaluating whether the adjusted storyboard meets preset quality standards and deciding whether to accept it, further optimize it, or provide feedback to the user for manual adjustment.

[0037] The shot grammar analysis module is responsible for parsing shot language and scene structure, providing necessary visual information for the composition optimization calculation module; the composition optimization calculation module provides the shot composition framework for the dynamic focus adjustment module by calculating the best composition principle; the dynamic focus adjustment module automatically adjusts the focus position according to scene changes and character / object movement to ensure the visual effect is focused and clear, and at the same time provides the focus position basis for the scene element scheduling module.

[0038] The scene element scheduling module optimizes the position and movement path of characters and props in the scene based on the focus adjustment results, providing accurate element scheduling information for the multi-camera collaborative adjustment module; the multi-camera collaborative adjustment module coordinates the switching and visual transition between multiple cameras to ensure overall visual consistency, providing adjusted camera data for the user feedback learning module; the user feedback learning module adjusts the algorithm strategy based on user feedback to optimize the camera design and adjustment process, providing optimized camera data for the quality assessment decision module.

[0039] In the above embodiments, the shot grammar analysis module utilizes image processing and grammar analysis techniques to analyze shot language and scene structure, providing necessary visual information for subsequent composition optimization. The composition optimization calculation module calculates the optimal composition scheme based on visual composition principles such as the golden ratio and the rule of thirds, and provides a composition framework for the dynamic focus adjustment module, ensuring that focus adjustment is consistent with scene composition. Figure 1 The dynamic focus adjustment module automatically adjusts the focus position based on scene changes and object movement, ensuring visual focus and clarity. It also provides focus position information to the scene element scheduling module, optimizing the layout and movement paths of characters and props. The scene element scheduling module further optimizes the distribution and paths of elements within the scene, providing precise scheduling information to the multi-camera collaborative adjustment module. This ensures visual transitions and coordination between multiple shots. The multi-camera collaborative adjustment module coordinates the switching of multiple shots, ensuring visual consistency between them. It then transmits the adjusted data to the user feedback learning module, using user feedback to further optimize the adjustment algorithm strategy, ultimately supporting video quality assessment and optimization.

[0040] The quality assessment decision module uses the SVM machine learning classification algorithm combined with a scoring function to assess quality and classify videos into three categories based on the assessment results: qualified, automatically optimized, and manually optimized. Qualified videos can be automatically output, while automatically optimized videos are transmitted to three corresponding modules—the composition optimization calculation module, the dynamic focus adjustment module, and the multi-lens collaborative adjustment module—for optimization as needed.

[0041] The quality assessment decision module transmits videos deemed to require manual optimization to the user feedback learning module for adjustment using a manual adjustment mode.

[0042] Working Principle: In use, this invention first receives the user-inputted storyboard script through a storyboard input semantic parsing module and converts it into structured data. This module comprises multiple subsystems, including an input interface design module providing a user-friendly interface; a natural language parsing module converting text descriptions into structured data; a scene semantic recognition module extracting and classifying scene elements; and a data management and storage module for storing storyboard data and parsing results. These steps ensure the system can understand user input and provide accurate structured information for subsequent shot analysis and optimization. Subsequently, the system passes the parsed data to the shot analysis and optimization module. This module analyzes shot language and composition, identifies potential errors, and provides optimization suggestions, thereby improving the accuracy of shot design.

[0043] Next, the intelligent adjustment video generation module automatically adjusts the storyboard parameters based on the suggestions from the shot analysis and optimization module, and generates a preliminary demo video. During this process, users can view the automatically generated suggestions and make fine-tuning adjustments through the user feedback integration module to further optimize the storyboard design. Subsequently, the rendering and video generation module transforms the adjusted storyboard data into a preliminary demo video, providing it to users for detailed editing and final optimization, ultimately ensuring the video's quality and effect. Simultaneously, the feedback iterative system learning module continuously optimizes and adjusts the algorithm by analyzing the comparison between user feedback and the generated video, improving the system's intelligence level, and provides diverse creative suggestions through the creative generation and recommendation module, enhancing the flexibility and innovation of storyboard adjustments.

[0044] In the implementation of the automated storyboard adjustment module, the shot grammar analysis module utilizes image processing and grammar analysis techniques to analyze shot language and scene structure, providing necessary visual information for subsequent composition optimization. Next, the composition optimization calculation module calculates the optimal composition scheme based on principles such as the golden ratio and the rule of thirds, providing a shot framework for the dynamic focus adjustment module. When the scene changes or characters move, the dynamic focus adjustment module automatically adjusts the focus position to ensure shot clarity and visual focus. The scene element scheduling module optimizes the position and path of characters and props based on the focus adjustment results, thereby improving the rationality of the scene layout. Finally, the multi-shot collaborative adjustment module coordinates the switching and visual transitions between multiple shots, ensuring visual consistency between shots. Through these functions, the system automatically optimizes shot design, reduces manual intervention, improves the efficiency and accuracy of storyboard adjustments, and provides users with more creative and adjustment space.

[0045] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A storyboard adjustment demonstration system based on artificial intelligence, characterized in that, It includes a storyboard input semantic parsing module for parsing user input text and preliminary visual materials and converting them into structured data for subsequent processing; a shot analysis and optimization module for performing comprehensive shot language and composition analysis on storyboards; an intelligent adjustment video generation module for automatically applying optimization adjustments and generating demonstration videos; and a feedback iterative system learning module for collecting user feedback and continuously learning and optimizing algorithms. The storyboard input semantic parsing module includes an input interface design module for providing a user-friendly interface for inputting storyboard scripts, a natural language parsing module for analyzing and parsing the input text descriptions and converting them into operable structured data, a scene semantic recognition module for identifying and classifying scene categories in the input descriptions and extracting scene elements, and a data management and storage module for storing and managing the input storyboard data and parsing results. The shot analysis and optimization module includes a shot language evaluation module for analyzing shot language and identifying potential shot errors based on input shot data, a composition and visual optimization module for providing suggestions for composition improvement, a scene scheduling evaluation module for analyzing the scheduling of characters and props to ensure reasonable configuration in the scene, and a creative generation and recommendation module for calling the built-in creative library to provide diverse creative suggestions. The input interface design module provides a user-friendly interface for inputting storyboard scripts and provides input data to the natural language parsing module, ensuring that the text descriptions input by users can be received and parsed by the system. The natural language parsing module analyzes and converts the user's input text into structured data, providing parsed text descriptions for the scene semantic recognition module, which helps to identify and classify scene elements; The scene semantic recognition module extracts scene category and element information based on the structured data output by the natural language parsing module, providing necessary data storage and management for the data management and storage module; the data management and storage module stores and manages storyboard data and parsing results, providing structured input data for the subsequent shot analysis and optimization module.

2. The storyboard adjustment demonstration system based on artificial intelligence according to claim 1, characterized in that, The intelligent adjustment video generation module includes an automated storyboard adjustment module for automatically adjusting storyboard parameters based on the analysis module's suggestions, a user feedback integration module for allowing users to view adjustment suggestions and selectively apply them or manually fine-tune them, a rendering and video generation module for generating a preliminary demonstration video from the adjusted storyboard data, and an interactive editing and optimization module for providing a user interface that allows users to directly edit the generated video in detail within the system. The feedback iterative system learning module includes a video expectation-actual comparison module for comparing the generated video with the user's expectations to identify differences, an adaptive proposal generation module for generating adjustment suggestions based on comparison analysis to narrow the gap between the expected and actual effects, a learning feedback algorithm optimization module for automatically adjusting the analysis and generation algorithm based on the user's adjustment feedback, and a system update resource management module for regularly updating the system's creative library and analysis model.

3. The storyboard adjustment demonstration system based on artificial intelligence according to claim 2, characterized in that, The automated storyboard adjustment module includes a shot grammar analysis module for detecting and parsing shot language using image processing and grammar analysis techniques; a composition optimization calculation module for calculating the optimal composition based on visual composition principles such as the golden ratio and the rule of thirds; a dynamic focus adjustment module for automatically adjusting the focus position according to scene changes; a scene element scheduling module for optimizing the position and movement path of characters and props in the scene; a multi-shot collaborative adjustment module for coordinating multiple shots to ensure overall visual consistency; a user feedback learning module for optimizing the adjustment algorithm using user feedback data; and a quality assessment decision module for evaluating whether the adjusted storyboard meets the preset quality standards and deciding whether to accept it, further optimize it, or provide feedback to the user for manual adjustment.

4. The storyboard adjustment demonstration system based on artificial intelligence according to claim 3, characterized in that, The shot grammar analysis module is responsible for parsing shot language and scene structure, providing necessary visual information for the composition optimization calculation module; the composition optimization calculation module provides the shot composition framework for the dynamic focus adjustment module by calculating the best composition principle; the dynamic focus adjustment module automatically adjusts the focus position according to scene changes and character / object movement to ensure focused and clear visual effects, while providing the focus position basis for the scene element scheduling module.

5. The storyboard adjustment demonstration system based on artificial intelligence according to claim 4, characterized in that, The scene element scheduling module optimizes the position and movement path of characters and props in the scene based on the focus adjustment results, providing accurate element scheduling information for the multi-camera collaborative adjustment module; the multi-camera collaborative adjustment module coordinates the switching and visual transition between multiple cameras to ensure overall visual consistency, providing adjusted camera data for the user feedback learning module; the user feedback learning module adjusts the algorithm strategy based on user feedback to optimize the camera design and adjustment process, providing optimized camera data for the quality assessment decision module.

6. The storyboard adjustment demonstration system based on artificial intelligence according to claim 1, characterized in that, The shot language evaluation module performs shot language analysis based on the input storyboard data, identifies potential shot errors, and provides shot improvement suggestions to the composition and visual optimization module; after receiving the optimization suggestions from the shot language evaluation module, the composition and visual optimization module improves the composition and provides improved composition information to the scene scheduling evaluation module. The scene scheduling evaluation module analyzes the scheduling of characters and props in the scene based on the composition optimization results, ensuring their reasonable configuration and providing scene scheduling evaluation data for the creative generation and recommendation module; the creative generation and recommendation module calls the built-in creative library and generates diverse creative suggestions based on the information provided by the aforementioned modules, providing more creative directions for subsequent storyboard adjustments.

7. The storyboard adjustment demonstration system based on artificial intelligence according to claim 2, characterized in that, The automated storyboard adjustment module automatically adjusts storyboard parameters based on suggestions from the shot analysis and optimization module, and transmits the adjusted storyboard data to the user feedback integration module, allowing users to view the suggestions and selectively apply or fine-tune them. The user feedback integration module allows users to view the automatic adjustment suggestions and make fine-tuning or selective applications, and transmits the adjusted data to the rendering and video generation module to generate a preliminary demo video. The rendering and video generation module converts the adjusted storyboard data into a preliminary demo video and provides video files to the interactive editing and optimization module, allowing users to further refine the video. The interactive editing and optimization module provides a user interface, allowing users to edit and optimize the generated video within the system, ultimately adjusting the video quality.

8. The storyboard adjustment demonstration system based on artificial intelligence according to claim 2, characterized in that, The video expectation-to-actual comparison module compares the generated video with the user's expectations, identifies differences, and passes the results to the adaptive proposal generation module. Based on the analysis results from the video expectation-to-actual comparison module, the adaptive proposal generation module generates adjustment suggestions to narrow the gap between expectations and actual results, and passes these suggestions to the learning feedback algorithm optimization module for adjusting the analysis and generation algorithms. The learning feedback algorithm optimization module continuously optimizes the analysis and generation algorithms based on user feedback, improving the intelligence of storyboard adjustments and providing updated data and models to the system update resource management module. The system update resource management module regularly updates the system's creative library and analysis models, providing the entire system with the latest creative resources and analysis tools.

Images