User-dominated personal image subjective narrative authoring system

Abstract

The invention discloses a user-guided personal image subjective narrative creation system, and belongs to the technical field of digital art and mobile images. The system comprises an image management module, a theme definition module, a culture fusion module, a creation execution module, an AR extension module and the like. A user actively selects a plurality of images and defines a theme; selecting styles from a built-in classic art library; manually adjusting the area intensity through a creation panel, hand-drawing a fusion area and a composition, and performing AI execution to generate a work; storing the works into a creation set and generating an operation log; the works and user dynamic behaviors are fused in real time through AR, and immersive experience is achieved; and the user completely has the work copyright. According to the method, a cooperative normal form of'manual user adjustment + AI accurate execution 'is constructed, three-dimensional fusion of entity art, digital materials and user behaviors is realized, and the defect of an image creation function of a mobile terminal is overcome.

Description

Technical Field

[0001] This invention belongs to the field of digital art and mobile imaging technology, specifically involving a user-led creation system based on the theory of personal image subjectivity narrative, which is particularly suitable for subjective artistic creation and cultural output in mobile terminal photo albums. Background Technology

[0002] Current mobile photo albums generally only offer image storage, categorization, and basic editing functions, lacking the ability for in-depth narrative creation based on user choices. Existing AI image processing tools mostly employ template-based, fully automated generation modes, allowing users to only select preset effects and lacking the ability to manually control different areas of an image in a differentiated and refined manner. This results in highly homogenized works, an uncontrollable creative process, and an untraceable creative trajectory. Furthermore, existing creation tools are independent of photo albums, requiring users to switch between multiple applications, disrupting the continuity of the creative context. In addition, current image creation is largely confined to a two-dimensional plane, failing to achieve real-time integration and interaction between physical space, digital materials, and user behavior, resulting in a single creative dimension and insufficient immersion and interactivity. More importantly, existing tools generally adopt an AI-driven, user-passive human-computer collaboration paradigm, weakening user agency and making it difficult to achieve subjective narrative expression based on personal life experiences. Therefore, there is an urgent need in this field for a personal image narrative creation system that can guarantee user narrative sovereignty, achieve deep AI collaboration, support multi-dimensional manual control, and extend creation to physical space. Summary of the Invention

[0003] This invention aims to address the technical problems in existing technologies, such as low creative autonomy, lack of refined regional adjustment, untraceable creative process, fragmented context, insufficient spatial interactivity, and weakened user subjectivity under AI dominance. It provides a user-driven personal video narrative creation system. This invention is the first to construct a human-computer collaboration paradigm combining multi-dimensional manual adjustment by the user with precise AI execution. Through multi-regional differentiated intensity adjustment, hand-drawn region selection, physical space anchoring, and creation log recording, it achieves highly autonomous, highly controllable, traceable, and spatially interactive personal video narrative creation. The system includes an image material management module for on-device intelligent classification and sentiment analysis of images in the user's album, ensuring privacy and security; a theme definition module for receiving user-selected images, constructing narrative groups, and customizing creative themes, strengthening user narrative sovereignty; a cultural material fusion module with a built-in library of classic artworks for users to choose from, combining personal narratives with cultural heritage; a creative narrative creation module with an AIGC creation panel, including a style transfer intensity slider, a hand-drawn area selection tool, and a composition proportion adjustment tool, supporting differentiated adjustment intensities for different areas of the image. After manual adjustment by the user, AI generates the final image, ensuring user-led creation; a work saving module for storing created works and recording a creation log containing operation trajectories and adjustment parameters, making the creation process traceable and reproducible; and an AR extension module that scans physical space to identify physical frames, anchoring digital works in real-world space, achieving real-time fusion rendering of physical frames, digital materials, and user dynamic behavior, and supporting the recording of AR interactive short films and the generation of shareable QR codes, breaking through the limitations of two-dimensional creation.

[0004] Beneficial Effects: The beneficial effects of this invention are as follows: First, by adjusting the intensity of different regions and using precise hand-drawn selection, the user gains refined control over the creative process. AI only performs low-level calculations, avoiding the homogenization problem caused by fully automatic generation and improving the controllability and personalization of creation. Second, the creation entry is directly triggered within the album, eliminating the need to switch between applications, achieving contextualized connection between materials and tools, and improving operational convenience and creative continuity. Third, by recognizing physical frames, anchoring digital twins, and integrating user dynamics in real time, the limitations of two-dimensional creation are broken, enabling three-dimensional spatial interaction and enhancing the immersiveness and narrative expressiveness of the work. Fourth, the creation log fully records the operation trajectory and adjustment parameters, making the creative process traceable and reproducible, overcoming the deficiency of existing tools that lack process recording. Fifth, all processing is completed on the device side without uploading to the cloud, ensuring user privacy and security, and can be widely integrated into various mobile terminal album systems, demonstrating strong industrial applicability.

[0005] Attached image description: Figure 1This is a schematic diagram of the overall architecture of the user-led personal image-based narrative creation system described in this invention, used to illustrate the hierarchical relationship and data flow of each functional module. 1. Image Material Management Module: Used for on-device intelligent classification and sentiment analysis of images in the terminal's album. All processing is completed on the device side, without uploading to the cloud, ensuring user privacy and security. 2. Theme Definition Module: Used to receive users' active selection of multiple images, construct narrative groups, and define custom creative themes. Simultaneously, AI dialogue guides users to input narrative elements such as time span and related stories, strengthening user narrative sovereignty. 3. Cultural Material Fusion Module: Includes a built-in library of classic artworks for users to choose fusion objects, achieving a combination of personal narrative and cultural heritage. 4. Creative Narrative and Creation Module: Features an AIGC creation panel, including a style transfer intensity slider, a hand-drawn area selection tool, and a composition proportion adjustment tool. It supports setting differentiated adjustment intensities for different areas of the image. After the user completes manual adjustments, AI generates the final image, ensuring user-led creation. 5. Work Saving and Display Module: Used to store created works and record a creation log containing operation trajectories and adjustment parameters, enabling traceability and reproducibility of the creation process. 6. AR Extension Module: By scanning the physical space to identify physical picture frames, digital works are anchored in the real space, realizing real-time fusion rendering of physical picture frames, digital materials, and user dynamic behavior. It also supports recording AR interactive short films and generating shareable QR codes. AR experience data and newly generated materials can be sent back to the image material management module to form a creative closed loop of material iteration.

[0006] Figure 2This is a schematic diagram of the creation process of the user-led personal image subjectivity narrative creation system described in this invention, clearly demonstrating the complete interactive path from the album entry to the personal digital museum. 1. Album Creation Entry: The initial entry point for the user to trigger the creation process within the terminal's album. This can be accessed by long-pressing to select multiple photos or swiping right on a single photo, achieving a contextualized connection between inspiration and tools. 2. Photo Selection: Users actively select one or more image materials from their personal album to construct a narrative group. Sentiment Analysis: The AI ​​module performs on-device sentiment recognition and scene analysis on the selected materials, generating sentiment tags and preliminary creation suggestions. 3. User Narrative: Users input personal stories, emotional needs, or creative intentions through text, voice, etc., injecting a personal narrative into the work. Questioning and Positioning: The AI ​​module further clarifies the user's creative goals, scene preferences, and core expressions through interactive questioning. 4. User Operations: Users perform basic editing of the materials, such as cropping, color correction, and composition adjustments. Suggestions and Integration: Based on user operations and sentiment analysis, the AI ​​module provides suggestions for cultural material integration and a preview of the automatic integration effect. 5. Multi-dimensional Fusion: Users can fine-tune the fusion effect generated by AI, including area intensity, transparency, and overlay method. Introducing Classics: Users can select classic artworks or cultural materials built into the system for deep fusion with their personal materials. 6. User Operation: Users make final adjustments and confirmations to the fused work. Storage and Recording: The system automatically records user operation paths, adjusts parameters, generates a traceable creation log, and stores the work in the creation collection. 7. User Operation: Users select to enter AR mode and initiate the spatial extension process. Real-time Rendering: The AR module anchors the digital work to physical space, achieving real-time rendering of the virtual-real fusion. 8. Personal Digital Museum: All digital works and creation logs generated by the user are permanently saved, forming a unique digital cultural heritage.

[0007] Figure 3This is a schematic diagram of an AR application scenario for the user-driven personal image-based narrative creation system described in this invention, used to demonstrate the interactive method of real-time fusion of physical frames, digital materials, and user behavior. 1. Physical Frame: Located on a wall in a physical space, used to display classic cultural materials, serving as a spatial anchor point for creation, clearly marked on the mobile phone screen with a solid outline. 2. Digital Material Library: Contains digital materials imported by the user or built into the system, labeled with the source time of the materials, reflecting the time dimension of the personal narrative, clearly marked on the mobile phone screen with a dotted outline. 3. Real User: Located within the physical space, their body movements are captured in real-time by the device's sensors, serving as the subject of AR interaction, clearly marked on the mobile phone screen with an outline. 4. AR Virtual Avatar: A digital twin avatar generated through AR technology, corresponding in real-time to the real user's actions, realizing an artistic mapping from real-world behavior to digital expression. 5. Real-time Rendering Area: Seamlessly integrates the AR virtual avatar, digital materials, and physical frames to form an immersive narrative scene. 6. Mobile Terminal Preview: Users can preview the AR fusion effect in real-time via their mobile phones, making adjustments, recording short videos, or generating a shareable QR code. Others can scan the code to view the fused scene in the same space.

[0008] Detailed Implementation: Example 1: User-Driven Deep Narrative Fusion Creation Process. Users trigger the creation entry by long-pressing multiple photos in their device's photo album, actively selecting multiple images to construct a narrative group. The system's on-device intelligent recognition module classifies and analyzes the images for sentiment. AI guides users to input the time span, story content, and creative theme in a dialogue format. After entering the creation interface, users select areas to retain details using a hand-drawn area selection tool and adjust the intensity of different areas using a style transfer intensity slider. AI only performs low-level calculations to generate the fused work. The system automatically saves the work and generates a creation log, fully recording the operation trajectory, parameter settings, and adjustment process, ensuring traceability and reproducibility of the creation.

[0009] Example 2: AR Spatial Extension. Users enter AR mode, scan physical frames in the physical space to complete spatial anchoring, and project the merged artwork as a digital twin into the real space. The system captures the user's body movements in real time, aligning and rendering the digital materials, physical frames, and virtual elements in real time. The phone screen distinguishes between real and virtual elements using solid lines, dashed lines, and outlines. Users can adjust the position, size, and spacing of the digital artwork, record interactive videos, and automatically edit them to generate AR narrative short films. A QR code is generated for others to scan and view the fusion effect in the same scene.

[0010] Example 3: Comparison with Existing Technologies. Existing technologies employ a model of importing photos into an independent application, selecting a template, and then automatically generating output using AI. This results in weak user autonomy, high homogeneity of works, and a lack of spatial interaction capabilities. This invention utilizes a complete process that includes direct triggering within the photo album, user-initiated image selection, customized themes, manual fine-tuning, AI-assisted execution, and AR spatial extension. This enables user-led, highly controllable, traceable, and highly immersive personal image-based narrative creation.

[0011] Industrial Applicability: This invention can be integrated into the photo albums of iOS, Android, HarmonyOS, and other systems. All processing is completed on the device side, ensuring user privacy. It has extremely high market promotion value and industrial applicability, and can effectively make up for the functional shortcomings of mainstream mobile terminals in personal image art creation and subjective expression.

Claims

1. A user-driven personal image subjectivity narrative creation system, characterized in that, include: ① Image Material Management Module: Configured to classify and perform sentiment analysis on images in the user's album based on on-device intelligent recognition. All processing is completed on the device and not uploaded to the cloud, ensuring user privacy and security. ② Theme Definition Module: Configured to receive users' active selection of at least two images, create narrative groups, and receive custom theme tags. Simultaneously, AI dialogue prompts users to input narrative elements such as time span and related stories, strengthening user narrative sovereignty. ③ Cultural Material Integration Module: Configured with a built-in classic art library, supporting users to select classic materials and perform style transfer, achieving a combination of personal narrative and cultural heritage. ④ Creative Narrative Creation Module: Configured to provide an AIGC creation panel, including a style transfer intensity slider, a blending region selection tool, and a composition ratio adjustment tool. The intensity slider supports setting different intensity values ​​for different areas of the image, and the region selection tool allows for precise hand-drawn selection of areas that retain original image details. After the user manually adjusts the operation, the AI ​​generates the fused work. The AI ​​only provides personalized creative suggestions, and all fusion operations are completed manually by the user. The AI ​​does not replace the user's decision-making. ⑤ The work saving module is configured to store the fused work in the creation set and generate a creation log. The log records the selection process, adjustment parameters, and operation trajectory playback, so as to realize the traceability and reproducibility of the creation process. ⑥ The AR extension module is configured to scan the physical space to identify the physical picture frame, anchor the fused work and the original material in the space in the form of a digital twin, receive the user's adjustment of the position, size, and spacing of the digital twin work, capture the user's dynamic behavior in real time, and merge and render it with the digital work on the mobile phone screen to form a composite picture of the user in the digital content. It records interactive videos and automatically edits them to generate AR narrative short films, and generates QR codes for others to scan and view the fused scene in the same space, so as to realize the spatial alignment and real-time fusion of the physical picture frame, digital materials and user dynamic behavior.

2. The system according to claim 1, characterized in that, The creative narrative creation module also includes an AI suggestion unit, configured to provide personalized creative suggestions, but all integration operations are completed manually by the user, and the AI ​​only executes the underlying technology within the user's decision-making framework.

3. The system according to claim 1, characterized in that, The AR extension module identifies physical and digital anchor points through scanning rays, enabling spatial alignment and real-time fusion of the physical frame, digital materials, and user dynamic behavior; the solid outline of the physical frame, the dashed outline of the digital materials, and the user dynamic outline are displayed on the mobile phone screen.

4. The system according to claim 1, characterized in that, The topic definition module also includes an AI questioning unit, configured to guide users to input topics by asking questions in a dialogue format. The questions include inquiries about the time span of the images and related stories.

5. The system according to claim 1, characterized in that, It also includes an entry trigger module, configured to: receive a "Co-create Story" entry when long-pressing to select multiple photos in the album browsing interface, or receive a "Create with This" floating panel when swiping right in the single photo interface, thus realizing a contextual connection between inspiration and tools.

6. A user-driven, personal video narrative creation method, characterized in that... include: S1: Receive the user's active selection of at least two images, create a narrative group, and receive a custom theme; S2: Receives the user's action of selecting materials from the classic art library; S3: Provides an AIGC creation panel, including an intensity slider, area selection tools, and composition tools, allowing users to manually adjust settings and for AI to generate merged works; S4: Save the merged works into the creation collection and generate a creation log to record the selection process and parameter adjustments; S5: Enter AR mode, scan the physical space to identify the physical picture frame, anchor the artwork in the space, capture user dynamics and merge them with the digital artwork to render on the mobile phone screen, record interactive videos to generate AR narrative short films.

7. The method according to claim 6, characterized in that, In S3, AI provides creative suggestions based on the user's historical style, but all adjustments are made manually by the user; AI does not replace user decisions.

Images