Animation engine resource asset management system and method based on artificial intelligence
By integrating multimodal data processing, AI technology, etc. into the animation engine resource asset management system, and building a distributed platform, it solves the problem that traditional management methods are difficult to cope with massive animation assets, and realizes efficient and low-cost animation asset management and utilization .
Patent Information
- Application Number
- CN202410994868.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-24
AI Technical Summary
Traditional manual management methods are difficult to cope with the effective management and reuse of massive animation assets, resulting in high cost and low efficiency of animation production.
Adopt an animation engine resource asset management system based on artificial intelligence, and build distribution through multimodal data processing, knowledge base construction, natural language processing, meta-learning, small sample learning, fine-tuning technology, etc., combining the Internet of Things, edge computing and cloud computing, A kind of asset management platform, optimizes asset distribution and version control, integrates deep learning and interpretable AI technology, and provides an end-to-end one-stop service.
It realizes intelligent and automated management of animation assets, improves asset utilization efficiency, reduces production costs, provides a highly interpretable and controllable experience, and ensures the efficiency and scalability of the system.
Smart Images

Figure CN118964010A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an animation engine resource asset management system and method based on artificial intelligence. Background Art
[0002] Animation production is a complex and huge process that requires a large number of asset materials such as 3D models, texture maps, animation clips, sound effects, etc. These assets are usually stored in animation engines or specialized asset management systems to provide support for subsequent animation creation.
[0003] As the demand for high-quality animations in the fields of film, television, and games increases, the number of animation assets is growing exponentially. Traditional manual management methods are no longer able to effectively manage and reuse massive assets. Therefore, it is urgent to establish an intelligent animation asset management system to improve asset utilization efficiency and reduce production costs. Summary of the invention
[0004] Based on the above problems, the present invention proposes an animation engine resource asset management system and method based on artificial intelligence. The solution of the present invention will be more intelligent and automated, providing end-to-end one-stop service; at the same time, it will also be more humane, deeply collaborate with users, and provide a highly explainable and controllable experience; the distributed architecture ensures the efficiency and scalability of the system.
[0005] In view of this, one aspect of the present invention proposes an animation engine resource asset management system based on artificial intelligence, comprising: a management server and a content server; The management server is configured to: Build a unified AI-driven first-class asset management framework by leveraging multimodal data processing technology, knowledge base construction technology, and natural language processing technology; Acquire existing animation engine resource asset data, and use the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; Generate 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data, and add them to the animation asset library; Combining meta-learning technology, small sample learning technology and fine-tuning technology, adjusting the first model to improve the AI model's ability to understand, generate and process the 3D animation assets, thereby obtaining a second model; Using explainable artificial intelligence technology to give the second model explainability; According to the first asset management framework and the second model, the Internet of Things technology, edge computing technology and cloud computing technology are integrated to build a distributed asset management platform; Optimize asset distribution and version control processes; Using deep learning technology, new animation assets are generated based on the animation engine resource asset data, and the animation asset library is automatically expanded; Formulate unified data standards, interface standards and development specifications for the asset management platform; Design human-computer interaction interfaces and integrate artificial intelligence technology into animation production tools and the asset management platform.
[0006] Another aspect of the present invention provides an animation engine resource asset management method based on artificial intelligence, comprising: Build a unified AI-driven first-class asset management framework by leveraging multimodal data processing technology, knowledge base construction technology, and natural language processing technology; Acquire existing animation engine resource asset data, and use the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; Generate 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data, and add them to the animation asset library; Combining meta-learning technology, small sample learning technology and fine-tuning technology, adjusting the first model to improve the AI model's ability to understand, generate and process the 3D animation assets, thereby obtaining a second model; Using explainable artificial intelligence technology to give the second model explainability; According to the first asset management framework and the second model, the Internet of Things technology, edge computing technology and cloud computing technology are integrated to build a distributed asset management platform; Optimize asset distribution and version control processes; Using deep learning technology, new animation assets are generated based on the animation engine resource asset data, and the animation asset library is automatically expanded; Formulate unified data standards, interface standards and development specifications for the asset management platform; Design human-computer interaction interfaces and integrate artificial intelligence technology into animation production tools and the asset management platform.
[0007] Optionally, the step of constructing a unified artificial intelligence-driven first asset management framework by utilizing multimodal data processing technology, knowledge base construction technology, and natural language processing technology includes: defining a unified data format standard for different types of first animation asset data; Preprocessing and standardizing the first animation asset data using computer vision technology and natural language processing technology to obtain basic asset data; Establish metadata standards for animation assets to describe various attributes and semantic information of animation assets; Automatically construct a knowledge graph of animation assets based on the basic asset data and metadata standards; Use graph embedding technology to represent structured knowledge graphs as low-dimensional knowledge graph vectors; Inputting the basic asset data of different modalities (such as images, text, 3D, etc.) into a deep neural network for feature extraction; Merge the extracted features with the knowledge graph vector to obtain a multimodal fusion encoding vector; Developing an AI enhanced function module based on the multimodal fusion coding vector; Integrate and deploy each functional module into the asset management platform; Collect feedback information through active learning and human-computer interaction, and continuously optimize the performance of the asset management platform based on the feedback information; Introduce explainable AI and interactive learning mechanisms to enhance the explainability and controllability of the asset management platform.
[0008] Optionally, the step of obtaining existing animation engine resource asset data, and using the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model includes: Collect various resource asset data from existing animation engines and animation projects; After the asset data is classified, labeled and reviewed, it is cleaned, formatted and standardized; Using data enhancement technology to expand the data volume of the asset data to obtain first asset data; Convert the first asset data in different formats into a unified tensor representation format to obtain the animation engine resource asset data; Design the corresponding network architecture of the first neural network for different types of asset data; A multi-head attention mechanism is used to fuse data of different modes in the animation engine resource asset data; Using the animation engine resource asset data to train the first neural network, and using a self-supervised learning method to learn a multimodal representation of the asset data, to obtain a general animation asset representation basic model; For a specific task, fine-tune and transfer learn the animation asset representation basic model on corresponding annotated data to generate a dedicated first model; Evaluation indicators and test sets are designed to measure model performance. Based on evaluation feedback, continuous optimization is carried out through parameter fine-tuning and data increment to achieve closed-loop model improvement to improve the quality of the first model.
[0009] Optionally, the step of generating 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data and adding the 3D animation assets to the animation asset library includes: Analyze specific asset requirements for 3D assets in historical animation projects; Determine the type, quantity, and level of detail of the required 3D assets based on the specific asset requirements; Conduct creative design based on the requirements and output conceptual design drafts and sketches; Based on the concept design and the sketch, create an initial 3D model; Generate a 3D rendering asset using a real-time or offline rendering tool based on the initial 3D model; Input the 3D rendering assets into animation software and perform keyframe animation according to the storyboard and action design; According to the key frames produced, render and output the animation sequence frames to form a complete 3D animation clip; Categorize and organize 3D static and dynamic assets, annotate metadata information, and integrate with other 2D and audio assets to build a complete animation asset library; The animation asset library is deployed to the asset management platform for creation and retrieval.
[0010] Optionally, the step of combining meta-learning technology, small sample learning technology and fine-tuning technology to adjust the first model to improve the AI model's ability to understand, generate and process the 3D animation assets to obtain the second model includes: Dividing the 3D animation asset into a plurality of first tasks, each of the first tasks corresponding to a 3D asset type; Based on the first model, a meta-model capable of understanding, generating and processing 3D animation assets is trained using an optimization-based meta-learning algorithm or a metric-based meta-learning algorithm; Collecting annotated new type 3D animation asset data, using the new type 3D animation asset data as input for small sample learning, and fine-tuning the meta-model to adapt to the new type 3D animation asset; For a preset specific application scenario, collect corresponding first 3D animation asset data; The fine-tuning technology is adopted, and on the basis of retaining the aforementioned learned knowledge, the first 3D animation asset data is used to optimize and train the meta-model to obtain the second model.
[0011] Optionally, the step of using explainable artificial intelligence technology to give the second model explainability includes: Selecting explainable artificial intelligence technology to be embedded into the architecture of the second model so that the second model can generate a decision process that can be understood by users and explain its internal reasoning logic; An active learning strategy is introduced, where the second model actively asks users for key information to reduce the uncertainty of the model; The second model learns the user's preferences and feedback through the human-computer interaction process and adjusts its own behavior and decision-making accordingly; An interactive learning interface is designed to allow users to modify and adjust the knowledge base and parameters of the second model in real time.
[0012] Optionally, the step of building a distributed asset management platform based on the first asset management framework and the second model by integrating Internet of Things technology, edge computing technology and cloud computing technology includes: Use distributed file systems and distributed databases to store asset data; Build an asset management platform based on microservice architecture and containerization technology to achieve service orchestration and elastic scaling; Introduce service grid technology to manage cross-platform service calls and data interactions; Deploy edge nodes integrating the second model at the collaboration site to support edge-side asset processing and local caching; Based on the second model, an edge AI model with local rendering and retrieval functions is generated; Introducing content distribution network technology to distribute and cache animation assets; Deploy AI-based intelligent asset management engine and analysis modules in the cloud; Deploy identity authentication and access control systems to manage asset access rights for multiple users; Encryption and digital signatures protect important assets and prevent leakage and data tampering.
[0013] Optionally, the step of optimizing the asset distribution and version control process includes: Deploy multiple CDN nodes to achieve edge caching and distribution of assets; Generate multiple distribution paths according to the location and router address of the CDN node, combined with a preset router intelligent control strategy and a dynamic routing allocation scheme; Utilize file system snapshot technology and data deduplication technology to calculate the first difference data between asset versions; distributing the first difference data through the distribution path; Connecting the CDN node to a preset first blockchain network; Uploading all the version management data, propagation path data and equity transaction data of the animation assets involved in each CDN node to the chain; Utilize smart contracts on the First Blockchain network to automate copyright protection, usage authorization, and revenue distribution; Introducing a version control system to support distributed collaborative editing of animation assets.
[0014] Optionally, the step of using deep learning technology to generate new animation assets based on the animation engine resource asset data and automatically expanding the animation asset library includes: Expanding the data volume of the first animation asset data according to a preset data compression and enhancement strategy to obtain first training data; Designing generative model architectures suitable for different asset types; Using the first training data to train the generation model architecture to obtain a first asset generation model; For a specific asset production task, fine-tune the first asset generation model to obtain a second asset generation model; Generate a new animation asset according to the animation engine resource asset data and the second asset generation model; Perform quality assessment on the newly generated animation assets and filter out unqualified results.
[0015] The method for managing animation engine resources and assets based on artificial intelligence includes building a unified artificial intelligence-driven first asset management framework by using multimodal data processing technology, knowledge base construction technology and natural language processing technology; acquiring existing animation engine resource asset data, and using the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; generating 3D animation assets based on the animation engine resource asset data by using 3D animation modeling technology, and adding the assets to the animation asset library; combining meta-learning technology, small sample learning technology and fine-tuning technology to adjust the first model to improve the AI model's control over the 3D animation assets; and D animation assets to understand, generate and process, and obtain the second model; use explainable artificial intelligence technology to give the second model explainability; according to the first asset management framework and the second model, integrate the Internet of Things technology, edge computing technology and cloud computing technology to build a distributed asset management platform; optimize the asset distribution and version control process; use deep learning technology to generate new animation assets based on the animation engine resource asset data, and automatically expand the animation asset library; formulate unified data standards, interface standards and development specifications for the asset management platform; design a human-computer interaction interface, and integrate artificial intelligence technology into the animation production tool and the asset management platform. The solution of the present invention will be more intelligent and automated, providing end-to-end one-stop service; at the same time, it will be more humane, deeply collaborate with users, and provide a highly explainable and controllable experience; the distributed architecture ensures the efficiency and scalability of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is a schematic block diagram of an animation engine resource asset management system based on artificial intelligence provided by one embodiment of the present invention; Figure 2 It is a flow chart of an animation engine resource asset management method based on artificial intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0017] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0019] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0021] Refer to the following Figure 1 to Figure 2 To describe an artificial intelligence-based animation engine resource asset management system and method provided according to some embodiments of the present invention.
[0022] like Figure 1 As shown, one embodiment of the present invention provides an animation engine resource asset management system based on artificial intelligence, including: a management server and a content server; The management server is configured to: Build a unified AI-driven first-class asset management framework by leveraging multimodal data processing technology, knowledge base construction technology, and natural language processing technology; Acquire existing animation engine resource asset data, and use the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; Generate 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data, and add them to the animation asset library; Combining meta-learning technology, small sample learning technology and fine-tuning technology, adjusting the first model to improve the AI model's ability to understand, generate and process the 3D animation assets, thereby obtaining a second model; Using explainable artificial intelligence technology to give the second model explainability; According to the first asset management framework and the second model, the Internet of Things technology, edge computing technology and cloud computing technology are integrated to build a distributed asset management platform; Optimize asset distribution and version control processes; Using deep learning technology, new animation assets are generated based on the animation engine resource asset data, and the animation asset library is automatically expanded; Formulate unified data standards, interface standards and development specifications for the asset management platform; Design human-computer interaction interfaces and integrate artificial intelligence technology into animation production tools and the asset management platform.
[0023] It should be known that Figure 1 The block diagram of the animation engine resource asset management system based on artificial intelligence is for illustration only, and the number of modules shown therein does not limit the protection scope of the present invention.
[0024] See also Figure 2 Another embodiment of the present invention provides an animation engine resource asset management method based on artificial intelligence, comprising: By leveraging multimodal data processing technology, knowledge base construction technology, and natural language processing technology, a unified AI-driven first-class asset management framework is built (to cover the entire asset life cycle and achieve data standardization, knowledge fusion, and closed-loop optimization); Acquire existing animation engine resource asset data, and use the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; Generate 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data, and add them to the animation asset library; Combining meta-learning technology, small sample learning technology and fine-tuning technology, adjusting the first model to improve the AI model's ability to understand, generate and process the 3D animation assets, thereby obtaining a second model; Use explainable artificial intelligence technology to make the second model explainable (allow users to understand the system decision-making process; improve the controllability and personalization of the system through active learning, interactive learning and other technologies); Based on the first asset management framework and the second model, the Internet of Things technology, edge computing technology and cloud computing technology are integrated to build a distributed asset management platform (to achieve cross-platform and multi-scenario asset management and support real-time collaboration); Optimize the asset distribution and version control process (communication technology can support efficient asset distribution and version control; new distributed technologies such as blockchain can provide reliable asset traceability and permission management mechanisms); Using deep learning technology (such as generative adversarial networks, etc.), new animation assets are generated based on the animation engine resource asset data to automatically expand the animation asset library; Formulate unified data standards, interface standards and development specifications for the asset management platform (to achieve standardization of animation asset management); In this step, you can sort out the common asset types in the animation industry (such as models, textures, actions, etc.), define the data structure and properties of each asset; formulate unified file format standards (such as FBX, Alembic, USD, etc.) to ensure the interoperability of assets between different software; establish asset metadata standards, including asset descriptions, version information, creators, etc., to facilitate asset management and retrieval; define API interface standards between asset management systems / platforms and animation production software, asset libraries and other systems; standardize interface specifications for common operations such as asset upload, download, and version control; ensure seamless integration and data interaction between systems from different manufacturers; formulate standardized specifications for development processes such as asset creation, modification, and submission, and unify development practice standards such as asset naming, organizational structure, and metadata filling; establish code specifications, test specifications, document specifications, etc. to improve development efficiency and maintainability. Through this step, unified data standards ensure seamless import and export of assets between different software; standardized asset attribute information facilitates retrieval and cross-project reuse; standardized development processes and specifications reduce the operational complexity of asset management; standardized metadata information facilitates asset classification, search and version tracing; standardized interface specifications achieve seamless docking between different systems; asset management systems can be seamlessly integrated with animation production software, asset libraries, etc. In short, by formulating unified data standards, interface standards and development specifications for the asset management platform, the standardization level of animation asset management can be greatly improved.
[0025] Design a human-computer interaction interface and integrate artificial intelligence technology into the animation production tools and the asset management platform (using technologies such as natural language processing to achieve human-computer semantic interaction and improve the intelligence level of the asset management platform).
[0026] By adopting the technical solution of this embodiment, a unified artificial intelligence-driven first asset management framework is constructed by utilizing multimodal data processing technology, knowledge base construction technology and natural language processing technology; the existing animation engine resource asset data is obtained, and the first model is obtained by training the AI model using the animation engine resource asset data and a preset first neural network; according to the animation engine resource asset data, 3D animation assets are generated using 3D animation modeling technology, and added to the animation asset library; the first model is adjusted by combining meta-learning technology, small sample learning technology and fine-tuning technology to improve the AI model's understanding, generation and processing capabilities of the 3D animation assets to obtain a second model; interpretable artificial intelligence technology is used to give the second model interpretability; according to the first asset management framework and the second model, a distributed asset management platform is constructed by integrating Internet of Things technology, edge computing technology and cloud computing technology; the asset distribution and version control process is optimized; new animation assets are generated based on the animation engine resource asset data using deep learning technology, and the animation asset library is automatically expanded; unified data standards, interface standards and development specifications are formulated for the asset management platform; a human-computer interaction interface is designed to integrate artificial intelligence technology into animation production tools and the asset management platform. The AI-based animation resource asset management solution will be more intelligent and automated, providing end-to-end one-stop service; it will also be more humane, deeply collaborating with users to provide a highly explainable and controllable experience; the distributed architecture ensures the efficiency and scalability of the system.
[0027] In some possible implementations of the present invention, the step of constructing a unified artificial intelligence-driven first asset management framework by utilizing multimodal data processing technology, knowledge base construction technology, and natural language processing technology includes: Define unified data format standards for different types of first animation asset data (such as 2D images, videos, 3D models, etc.); Preprocessing and standardizing the first animation asset data using computer vision technology and natural language processing technology to obtain basic asset data; Establish metadata standards for animation assets to describe various attributes and semantic information of animation assets; In this step, we should deeply understand the animation production process and sort out the needs of asset metadata in each link; collect the expectations of users with different roles (such as animators, artists, producers, etc.) for asset metadata; refer to the mature metadata standards in the industry (such as ACES, MDEC, etc.) and learn best practices; establish a metadata model for animation assets based on the needs and expectations for asset metadata and the mature metadata standards in the industry collected above, including general attributes and specific attributes; general attributes such as basic information such as asset ID, name, version, creation time; specific attributes such as professional attributes such as model geometry information, texture material, action data; determine the relationship between metadata, such as the relationship between assets and materials, and assets and projects; formulate detailed definitions, data types, value ranges and other standards for each metadata attribute; establish an asset classification system and customize appropriate metadata attributes for different types of assets; formulate metadata filling specifications, clarify mandatory and optional items, and unify naming, format and other constraints; based on the metadata model, develop a software system for asset metadata management to provide a user-friendly metadata editing interface and support batch import and export; realize metadata version control, permission management, search query and other functions. Through the above steps, detailed metadata information can be obtained, which is convenient for asset classification, retrieval and tracing; users can quickly locate the required assets and improve asset reuse rate; standardized metadata ensures the interoperability of asset information between different systems and platforms; assets can be efficiently shared and circulated across projects and teams; the metadata management system provides a visual asset management interface to simplify operations; metadata version control and permission management are implemented to support multi-person collaborative development; standardized metadata descriptions ensure the integrity and accuracy of asset information; and the accumulated rich metadata form a knowledge base for reference. In short, by establishing metadata standards for animation assets, not only can the manageability and discoverability of assets be greatly improved, but also the efficient circulation of assets and team collaboration can be promoted, bringing significant technical benefits to the animation production industry.
[0028] Based on the basic asset data and metadata standards, automatically construct a knowledge graph of animation assets (graph nodes represent different types of asset entities, and edges represent semantic relationships between entities); In this step, natural language processing technology is applied to identify various entities contained in the metadata standard. Correspondingly, key entity information, such as asset type, name, attributes, etc., is extracted from the basic asset data; machine learning models are used to analyze the semantic relationships between entities, such as inclusion, use, association, etc.; entity-relationship triples are constructed to form a preliminary knowledge graph structure; the extracted entities and relationships are organized and stored according to the standard knowledge graph data model, and each entity node is given rich attribute information, such as asset ID, name, type, etc.; the types and attributes of semantic relationships between entities are defined, such as "has_texture", "part_of", etc.; graph algorithms are applied to analyze the structural characteristics of the knowledge graph and discover potential errors and conflicts; domain expert knowledge is used to manually correct erroneous information in the knowledge graph; the coverage and accuracy of the knowledge graph are continuously optimized to improve its overall quality; a graph visualization interface is developed to intuitively display the knowledge graph of animation assets; functions such as asset search, recommendation, and association analysis based on the knowledge graph are provided; and knowledge graphs are used to support intelligent management and innovative applications of animation assets. Through the above steps, the knowledge graph can capture asset entities and their complex semantic relationships to form a more detailed knowledge representation; compared with traditional metadata, the knowledge graph can better reflect the intrinsic connection between animation assets; the algorithm based on the graph structure can realize more intelligent asset search and recommendation functions; users can quickly discover related asset information according to specific needs; the knowledge graph provides semantic relationships between assets, which can support more advanced asset classification, organization and management; using knowledge graph analysis, it can also explore novel combinations between assets and promote the generation of innovative applications; the knowledge graph provides a basis for the systematic accumulation and effective use of animation asset knowledge; cross-team and cross-project asset knowledge sharing has also become more convenient and intelligent. In short, building a knowledge graph based on animation asset metadata can not only achieve richer asset knowledge expression, but also greatly improve the ability of asset management and innovative application, bringing significant technical advantages to the animation industry.
[0029] Use graph embedding technology to represent structured knowledge graphs as low-dimensional knowledge graph vectors; In this step, first, clean and normalize the entities and relationships in the knowledge graph to ensure data quality; selectively retain or delete some entities and relationships based on needs to focus on specific areas; According to the characteristics and application scenarios of the knowledge graph, select a suitable graph embedding algorithm, such as Node2Vec, DeepWalk, TransE, etc. (consider the algorithm's computational complexity, embedding dimension, whether to consider relationships, etc.); input the preprocessed knowledge graph into the selected graph embedding algorithm for training, and adjust the algorithm hyperparameters, such as random walk length, embedding dimension, etc., to optimize model performance; ensure that the training process converges to obtain a stable knowledge graph vector representation; design suitable evaluation indicators, such as similarity, link prediction, etc., to evaluate the quality of the graph embedding vector; based on the evaluation results, further adjust the parameters and settings of the graph embedding technology; apply the trained knowledge graph vector to downstream tasks, such as asset association analysis, asset recommendation, etc.; explore how to best use the graph embedding vector according to specific application requirements. Through the above steps, the original complex knowledge graph can be compressed into a low-dimensional vector form, greatly improving the storage and computing efficiency; knowledge representation in vector form is more convenient for subsequent machine learning and data analysis applications; graph embedding technology can capture the semantic information contained in the knowledge graph and reflect it in the topological structure of the vector space; similar entities and relationships are close in the vector space, preserving the semantic association of the original graph; based on the graph embedding vector, the knowledge graph can be seamlessly integrated with other data modalities (such as text, images, etc.); cross-modal semantic association analysis and application become more efficient and accurate; graph embedding vectors can be used as a general feature representation to provide strong support for downstream asset analysis, recommendation and other tasks; compared with the original graph, vector-based computing is usually more efficient. In short, representing the structured knowledge graph as a low-dimensional graph embedding vector can effectively compress the knowledge representation, retain semantic information, provide strong support for cross-modal fusion and downstream applications, and play an important role in animation asset management.
[0030] Inputting the basic asset data of different modalities (such as images, text, 3D, etc.) into a deep neural network for feature extraction; In this step, relevant visual, semantic and other multimodal features are extracted according to the specific application scenario; mature feature extraction models such as CNN and BERT are used to ensure feature quality.
[0031] Merge the extracted features with the knowledge graph vector to obtain a multimodal fusion encoding vector; In this step, the extracted multimodal features (such as vision, semantics, etc.) are spliced with the knowledge graph vector to form a multimodal fusion coding vector (different splicing methods can be tried, such as simple splicing, weighted average, etc., and the appropriate method can be selected according to needs); the attention mechanism is introduced to dynamically assign weights to different modalities, highlight important information, and suppress secondary information; through the attention mechanism, multimodal features are adaptively aggregated to improve the fusion effect; the multimodal fusion coding vector is applied to downstream tasks, such as classification, retrieval, etc.; through end-to-end training, the performance of the multimodal fusion coding vector is optimized; the model structure and hyperparameters are adjusted to improve the fusion effect. Through the above steps, multimodal information such as vision, semantics, and knowledge are integrated, and the feature representation is more comprehensive and semantic. Compared with single-modal features, multimodal fusion features can better capture the various attributes of assets. Multimodal fusion encoding vectors provide more effective feature representations for downstream classification, retrieval and other tasks. The integration of knowledge graph information can significantly improve task performance, such as more accurate asset association analysis. Multimodal feature fusion can improve the generalization ability of the model and cope with more complex scenarios and data distributions. Especially in the case of insufficient data, knowledge graph information can play an effective supplementary role. Multimodal fusion features contain rich semantic information, which enhances the interpretability of the model. It helps to understand the decision-making process of the model and provide a basis for subsequent manual intervention and optimization. In short, by multimodally fusing the extracted visual, semantic and other features with the knowledge graph vector, and using the attention mechanism to dynamically aggregate the information of each modality, we can obtain feature representations with rich information, excellent performance and strong generalization ability, which plays an important role in animation asset management.
[0032] Based on the multimodal fusion coding vector, develop AI enhanced functional modules (e.g., intelligent retrieval: multimodal retrieval based on semantic similarity; asset generation: generating new assets through generative adversarial networks; asset archiving: automated asset archiving and organization based on clustering); Integrate and deploy each functional module into the asset management platform; Collect feedback information through active learning and human-computer interaction, and continuously optimize the performance of the asset management platform based on the feedback information; Introduce explainable AI and interactive learning mechanisms to enhance the explainability and controllability of the asset management platform.
[0033] In this embodiment, intelligent management of the entire life cycle of assets is achieved, covering all aspects such as asset creation, use, retrieval, and distribution; through multimodal fusion coding, basic asset data of different modalities are fully integrated, deep semantic associations are mined, and data utilization efficiency is improved; AI enhancement functions greatly improve the automation capabilities of asset management, reduce manual labor intensity, and improve production efficiency; semantic understanding and reasoning based on knowledge graphs support more intelligent and accurate asset retrieval and decision-making; continuous model optimization and human-computer collaboration mechanisms continuously improve system performance and user experience.
[0034] In some possible implementations of the present invention, the step of obtaining existing animation engine resource asset data, and using the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model includes: Collect various resource asset data (including 2D image materials, 3D models, animation clips, material maps, etc.) from existing animation engines and animation projects; After the asset data is classified, labeled and reviewed, it is cleaned, formatted and standardized; Expand the data volume of the asset data using data enhancement technology (such as rotation, scaling, noise addition, etc.) to obtain first asset data; Convert the first asset data in different formats into a unified tensor representation format to obtain the animation engine resource asset data; Design the corresponding first neural network architecture for different types of asset data (such as using 3D convolutional networks to process 3D models and using Transformers to process sequence data); A multi-head attention mechanism is used to fuse data of different modes in the animation engine resource asset data; Using the animation engine resource asset data to train the first neural network, and using a self-supervised learning method to learn a multimodal representation of the asset data, to obtain a general animation asset representation basic model; In this step, multimodal features are extracted from the animation engine resource asset data, including different types of features such as vision and semantics; self-supervised learning tasks are designed to allow the first neural network to autonomously learn the potential representation of asset data; common self-supervised tasks include: asset attribute prediction, asset relationship inference, cross-modal reconstruction, etc.; through these self-supervised learning tasks, the first neural network can learn a general and semantically rich asset representation; through large-scale asset data training, a general and robust asset representation basic model is learned; the trained basic model is applied to specific downstream tasks, such as asset classification, retrieval, etc.; according to task requirements, the basic model is appropriately fine-tuned to improve the performance of the model on specific tasks. Through the above steps, the model learns the general representation of animation asset data, covering multiple aspects such as vision and semantics; the basic model can be widely used in different animation asset management tasks and has strong migration capabilities; based on the general representation model, key tasks such as asset classification and retrieval can be quickly completed; the efficiency and accuracy of animation asset management are greatly improved; the self-supervised learning method enables the model to learn the inherent laws and general characteristics of asset data; self-supervised learning does not require a large amount of manually labeled data, which greatly reduces the cost of model training. In short, using self-supervised learning methods to train a general basic model for animation asset representation can effectively enhance the ability of animation asset management and provide strong support for animation production.
[0035] For a specific task (such as asset identification, retrieval, generation, etc.), fine-tuning and transfer learning the animation asset representation basic model on the corresponding annotated data to generate a dedicated first model (with improved performance on the task); Evaluation indicators and test sets are designed to measure model performance. Based on evaluation feedback, continuous optimization is carried out through parameter fine-tuning and data increment to achieve closed-loop model improvement to improve the quality of the first model.
[0036] Through the steps of this embodiment, it is possible to build a powerful asset representation capability and efficiently encode multimodal asset data; through the pre-training + fine-tuning paradigm, the first model is suitable for a variety of downstream tasks; the limited annotated data in the industry is used to the maximum extent to achieve the best performance; continuous optimization enables the model to continuously adapt to new needs and has good generalization capabilities, laying a solid foundation for subsequent intelligent asset management, generation and other tasks. In short, the paradigm of large-scale data pre-training + transfer learning can efficiently build an AI model with excellent performance, opening up new possibilities for artificial intelligence enhancement for animation asset management.
[0037] In some possible implementations of the present invention, the step of generating 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data and adding the assets to the animation asset library includes: Analyze the specific asset requirements for 3D assets in historical animation projects (such as character models, scene models, props, etc.); Determine the type, quantity, and level of detail of the required 3D assets based on the specific asset requirements; Conduct creative design based on the requirements, and output concept design drafts and sketches (including character settings, modeling design, action line drafts, etc.); Based on the concept design and sketches, create an initial 3D model (such as rigging characters, creatures and other assets to prepare for animation; importing reference images and videos to refine model details; applying physically based rendering (PBR) principles to design materials; giving the model reasonable physical properties such as light, shadow, and reflection; etc.); Generate a 3D rendering asset using a real-time or offline rendering tool based on the initial 3D model; Input the 3D rendering assets into animation software and perform keyframe animation according to the storyboard and action design; According to the key frames produced, render and output the animation sequence frames to form a complete 3D animation clip; Categorize and organize 3D static and dynamic assets, annotate metadata information, and integrate with other 2D and audio assets to build a complete animation asset library; The animation asset library is deployed to the asset management platform for creation and retrieval.
[0038] Through the above process of this embodiment, the following significant technical effects can be obtained: using professional 3D modeling tools to generate high-quality, high-fidelity 3D assets; applying physical rendering, 3D assets have realistic materials and lighting effects; integrating 3D modeling and animation production, and efficiently outputting dynamic 3D animation assets; standardized processes to ensure the consistency and traceability of 3D assets; integrating with other asset types to build a rich and complete asset library; by integrating 3D animation modeling technology into the entire workflow, not only can the asset library capacity be enriched, but more importantly, the quality and immersive experience of the entire animation assets can be improved; moreover, high-quality 3D assets have laid a solid foundation for subsequent innovative applications such as intelligent management, retrieval, and generation, which will help the entire animation industry to innovate and develop to a higher dimension.
[0039] In some possible implementations of the present invention, the step of combining meta-learning technology, small sample learning technology and fine-tuning technology to adjust the first model to improve the AI model's ability to understand, generate and process the 3D animation assets to obtain the second model includes: Dividing the 3D animation asset into a plurality of first tasks, each of the first tasks corresponding to a 3D asset type; Based on the first model, an optimization-based meta-learning algorithm (such as MAML) or a metric-based meta-learning algorithm (such as Prototypical Networks) is used to train a meta-model that can understand, generate, and process 3D animation assets; Collect annotated new type 3D animation asset data, use the new type 3D animation asset data as input for small sample learning, and fine-tune the meta-model to adapt to the new type 3D animation asset (i.e., be able to understand, generate and process the new type 3D animation asset); For a preset specific application scenario, collect corresponding first 3D animation asset data; The fine-tuning technology is adopted, and on the basis of retaining the aforementioned learned knowledge, the first 3D animation asset data is used to optimize and train the meta-model to obtain the second model.
[0040] The model obtained through this embodiment has stronger generalization ability and can quickly adapt to new types of 3D assets; it has higher data efficiency and can be optimized in a targeted manner with only a small amount of labeled data; it can better understand, generate and process 3D assets, and meet the needs of intelligent management of animation engines. This method makes full use of the advantages of meta-learning, small sample learning and fine-tuning, and can effectively improve the performance of AI models in 3D animation asset management. The scheme of this embodiment can greatly improve the applicability and robustness of AI models in the field of complex animation assets, support multi-modal animation asset generation, and reduce the creative difficulty and workload of artists; it can realize intelligent asset creation, editing and processing, and improve the automation level of animation production; the ability of 3D asset creation and physical simulation lays the foundation for new animation creation methods and immersive experiences; with the help of technologies such as transfer learning and meta-learning, it constantly adapts to emerging animation creation needs.
[0041] In some possible implementations of the present invention, the step of using explainable artificial intelligence technology to give explainability to the second model includes: Select explainable artificial intelligence technology (such as attention mechanism, visual explanation, causal reasoning, etc.) and embed it into the architecture of the second model, so that the second model can generate a decision process that can be understood by users and explain its internal reasoning logic; An active learning strategy is introduced, where the second model actively asks users for key information to reduce the uncertainty of the model; The second model learns the user's preferences and feedback through the human-computer interaction process and adjusts its own behavior and decision-making accordingly; An interactive learning interface is designed to allow users to modify and adjust the knowledge base and parameters of the second model in real time.
[0042] In this embodiment, the interpretable, controllable, and personalized second model obtained through the above steps will greatly enhance the intelligence level and user experience of the 3D animation asset management system; users are no longer passively accepting the decisions of the system, but can actively participate in and guide the system to obtain better customized services. This human-computer collaborative approach helps to enhance users' trust and dependence on the system, significantly improves the interpretability of the AI system in the field of animation asset management, and wins users' trust in the system; human-computer interactive interpretation enables users to better understand the system, and provide feedback on wrong decisions, promoting continuous improvement of the system. In short, through a series of innovative technical means, the future AI-based animation asset management system will be more reliable, interpretable, and controllable, form deep collaboration with users, maximize the potential of artificial intelligence, and achieve true intelligent assistance.
[0043] In some possible implementations of the present invention, the step of building a distributed asset management platform based on the first asset management framework and the second model by integrating Internet of Things technology, edge computing technology and cloud computing technology includes: Use distributed file systems and distributed databases to store asset data; Build an asset management platform based on microservice architecture and containerization technology to achieve service orchestration and elastic scaling; Introduce service grid technology to manage cross-platform service calls and data interactions; Deploy edge nodes integrating the second model at the collaboration site to support edge-side asset processing and local caching; Based on the second model, an edge AI model with local rendering and retrieval functions is generated; Introducing content distribution network technology to distribute and cache animation assets; Deploy AI-based intelligent asset management engine and analysis modules in the cloud; Deploy identity authentication and access control systems to manage asset access rights for multiple users; Encryption and digital signatures protect important assets and prevent leakage and data tampering.
[0044] In this embodiment, through the above-mentioned distributed architecture, unified management and high-availability storage of asset data can be achieved, eliminating data islands; supporting remote distributed collaboration to get rid of the limitations of the traditional single-machine production model; using the powerful computing power of the cloud to support high-performance asset processing and analysis; local processing and caching at the edge to reduce data transmission delays and improve response speed; the Internet of Things and augmented reality technology give animation creation a new immersiveness. By innovatively integrating emerging technologies such as cloud, edge, and end, this distributed asset management platform can significantly improve the intelligence level, collaboration efficiency, and security of animation asset management, injecting new impetus into the industry's digital and intelligent transformation.
[0045] In some possible implementations of the present invention, the step of optimizing the asset distribution and version control process includes: Deploy multiple CDN nodes to achieve edge caching and distribution of assets; According to the location and router address of the CDN node, combined with the preset router intelligent control strategy and dynamic routing allocation scheme, multiple distribution paths are generated (establishing a P2P distribution network, where each node is both a downloader and an upload source; achieving efficient multi-point transmission based on technologies such as tower distributed coding; dynamic load balancing and fault switching to provide highly available distribution services; combining new transmission protocols such as HTTP / 2 and QUIC to improve distribution efficiency); Utilize file system snapshot technology and data deduplication technology to calculate the first difference data between asset versions; Distributing the first difference data through the distribution path (synchronizing and transmitting only the difference part, greatly saving bandwidth and synchronization time; supporting incremental synchronization and breakpoint resume, improving synchronization reliability); Connecting the CDN node to a preset first blockchain network; Uploading all the version management data, propagation path data and equity transaction data of the animation assets involved in each CDN node to the chain; Utilize smart contracts on the First Blockchain network to automate copyright protection, usage authorization, and revenue distribution; Introducing a version control system to support distributed collaborative editing of animation assets.
[0046] In this embodiment, it also includes: end-to-end encryption and integrity verification during asset transmission; distributed storage to achieve fault-tolerant backup to prevent data loss due to single point failure; external security defense system to prevent various attacks and ensure safe and reliable distribution.
[0047] Through the solution of this embodiment, the efficiency, reliability and bandwidth utilization of asset distribution can be greatly improved; the asset traceability and copyright management mechanism based on blockchain can ensure that asset transactions are credible and traceable; the automated rights and interests distribution based on smart contracts can solve the problems of animation asset transactions and income distribution. In short, by integrating innovative technologies such as new communication networks, distributed storage, and blockchain, the pain points of efficiency, security, and copyright in traditional asset distribution and version control can be fundamentally solved, injecting new impetus into the digital and intelligent transformation of the animation industry.
[0048] In some possible implementations of the present invention, the step of using deep learning technology to generate new animation assets based on the animation engine resource asset data and automatically expanding the animation asset library includes: Expanding the data volume of the first animation asset data according to a preset data compression and enhancement strategy to obtain first training data; Designing generative model architectures suitable for different asset types (such as StyleGAN, etc.); Using the first training data to train the generation model architecture to obtain a first asset generation model (supporting asset generation based on conditions such as text descriptions, sketches, and a small number of examples); For specific asset production tasks (such as generating character cartoons and 3D models), the first asset generation model is fine-tuned to obtain the second asset generation model (which integrates visual, semantic, and other modal conditional information to guide the generation process; the attention mechanism enables the model to selectively focus on and integrate different conditional information); Generate a new animation asset according to the animation engine resource asset data and the second asset generation model; Perform quality assessment on the newly generated animation assets and filter out unqualified results; Through the method of this embodiment, the time and workload of creating animation assets can be greatly reduced; high-quality and diversified animation assets can be generated, and the asset library capacity can be automatically expanded.
[0049] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0050] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0051] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0052] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0053] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0054] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.
[0055] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.
[0056] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0057] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.
Claims
1. An animation engine resource asset management system based on artificial intelligence, It is characterized in that include: Management servers and content servers; The management server is configured to: Build a unified AI-driven first-class asset management framework by leveraging multimodal data processing technology, knowledge base construction technology, and natural language processing technology; Acquire existing animation engine resource asset data, and use the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; Generate 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data, and add them to the animation asset library; Combining meta-learning technology, small sample learning technology and fine-tuning technology, adjusting the first model to improve the AI model's ability to understand, generate and process the 3D animation assets, thereby obtaining a second model; Using explainable artificial intelligence technology to give the second model explainability; According to the first asset management framework and the second model, the Internet of Things technology, edge computing technology and cloud computing technology are integrated to build a distributed asset management platform; Optimize asset distribution and version control processes; Using deep learning technology, new animation assets are generated based on the animation engine resource asset data, and the animation asset library is automatically expanded; Formulate unified data standards, interface standards and development specifications for the asset management platform; Design human-computer interaction interfaces and integrate artificial intelligence technology into animation production tools and the asset management platform.
2. An animation engine resource asset management method based on artificial intelligence, It is characterized in that include: Build a unified AI-driven first-class asset management framework by leveraging multimodal data processing technology, knowledge base construction technology, and natural language processing technology; Acquire existing animation engine resource asset data, and use the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model; Generate 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data, and add them to the animation asset library; Combining meta-learning technology, small sample learning technology and fine-tuning technology, adjusting the first model to improve the AI model's ability to understand, generate and process the 3D animation assets, thereby obtaining a second model; Using explainable artificial intelligence technology to give the second model explainability; According to the first asset management framework and the second model, the Internet of Things technology, edge computing technology and cloud computing technology are integrated to build a distributed asset management platform; Optimize asset distribution and version control processes; Using deep learning technology, new animation assets are generated based on the animation engine resource asset data, and the animation asset library is automatically expanded; Formulate unified data standards, interface standards and development specifications for the asset management platform; Design human-computer interaction interfaces and integrate artificial intelligence technology into animation production tools and the asset management platform.
3. The animation engine resource asset management method based on artificial intelligence according to claim 2, It is characterized in that The steps of constructing a unified artificial intelligence-driven first asset management framework by utilizing multimodal data processing technology, knowledge base construction technology, and natural language processing technology include: defining a unified data format standard for different types of first animation asset data; Preprocessing and standardizing the first animation asset data using computer vision technology and natural language processing technology to obtain basic asset data; Establish metadata standards for animation assets to describe various attributes and semantic information of animation assets; Automatically construct a knowledge graph of animation assets based on the basic asset data and metadata standards; Use graph embedding technology to represent structured knowledge graphs as low-dimensional knowledge graph vectors; Inputting the basic asset data of different modalities (such as images, text, 3D, etc.) into a deep neural network for feature extraction; Merge the extracted features with the knowledge graph vector to obtain a multimodal fusion encoding vector; Developing an AI enhanced function module based on the multimodal fusion coding vector; Integrate and deploy each functional module into the asset management platform; Collect feedback information through active learning and human-computer interaction, and continuously optimize the performance of the asset management platform based on the feedback information; Introduce explainable AI and interactive learning mechanisms to enhance the explainability and controllability of the asset management platform.
4. The animation engine resource asset management method based on artificial intelligence according to claim 3, It is characterized in that The step of obtaining existing animation engine resource asset data, and using the animation engine resource asset data and a preset first neural network to train an AI model to obtain a first model includes: Collect various resource asset data from existing animation engines and animation projects; After the asset data is classified, labeled and reviewed, it is cleaned, formatted and standardized; Using data enhancement technology to expand the data volume of the asset data to obtain first asset data; Convert the first asset data in different formats into a unified tensor representation format to obtain the animation engine resource asset data; Design the corresponding network architecture of the first neural network for different types of asset data; A multi-head attention mechanism is used to fuse data of different modes in the animation engine resource asset data; Using the animation engine resource asset data to train the first neural network, and using a self-supervised learning method to learn a multimodal representation of the asset data, to obtain a general animation asset representation basic model; For a specific task, fine-tune and transfer learn the animation asset representation basic model on corresponding annotated data to generate a dedicated first model; Evaluation indicators and test sets are designed to measure model performance. Based on evaluation feedback, continuous optimization is carried out through parameter fine-tuning and data increment to achieve closed-loop model improvement to improve the quality of the first model.
5. The animation engine resource asset management method based on artificial intelligence according to claim 4, It is characterized in that The step of generating 3D animation assets using 3D animation modeling technology according to the animation engine resource asset data and adding the assets to the animation asset library comprises: Analyze specific asset requirements for 3D assets in historical animation projects; Determine the type, quantity, and level of detail of the required 3D assets based on the specific asset requirements; Conduct creative design based on the requirements and output conceptual design drafts and sketches; Based on the concept design and the sketch, create an initial 3D model; Generate a 3D rendering asset using a real-time or offline rendering tool based on the initial 3D model; Input the 3D rendering assets into animation software and perform keyframe animation according to the storyboard and action design; According to the key frames produced, render and output the animation sequence frames to form a complete 3D animation clip; Categorize and organize 3D static and dynamic assets, annotate metadata information, and integrate with other 2D and audio assets to build a complete animation asset library; The animation asset library is deployed to the asset management platform for creation and retrieval.
6. The animation engine resource asset management method based on artificial intelligence according to claim 5, It is characterized in that The step of combining the meta-learning technology, the small sample learning technology and the fine-tuning technology to adjust the first model to improve the AI model's ability to understand, generate and process the 3D animation assets to obtain the second model includes: Dividing the 3D animation asset into a plurality of first tasks, each of the first tasks corresponding to a 3D asset type; Based on the first model, a meta-model capable of understanding, generating and processing 3D animation assets is trained using an optimization-based meta-learning algorithm or a metric-based meta-learning algorithm; Collecting annotated new type 3D animation asset data, using the new type 3D animation asset data as input for small sample learning, and fine-tuning the meta-model to adapt to the new type 3D animation asset; For a preset specific application scenario, collect corresponding first 3D animation asset data; The fine-tuning technology is adopted, and on the basis of retaining the aforementioned learned knowledge, the first 3D animation asset data is used to optimize and train the meta-model to obtain the second model.
7. The method for managing animation engine resources based on artificial intelligence according to claim 6, It is characterized in that The step of using explainable artificial intelligence technology to give the second model explainability includes: Selecting explainable artificial intelligence technology to be embedded into the architecture of the second model so that the second model can generate a decision process that can be understood by users and explain its internal reasoning logic; An active learning strategy is introduced, where the second model actively asks users for key information to reduce the uncertainty of the model; The second model learns the user's preferences and feedback through the human-computer interaction process and adjusts its own behavior and decision-making accordingly; An interactive learning interface is designed to allow users to modify and adjust the knowledge base and parameters of the second model in real time.
8. The method for managing animation engine resources based on artificial intelligence according to claim 7, It is characterized in that The step of building a distributed asset management platform based on the first asset management framework and the second model by integrating Internet of Things technology, edge computing technology and cloud computing technology includes: Use distributed file systems and distributed databases to store asset data; Build an asset management platform based on microservice architecture and containerization technology to achieve service orchestration and elastic scaling; Introduce service grid technology to manage cross-platform service calls and data interactions; Deploy edge nodes integrating the second model at the collaboration site to support edge-side asset processing and local caching; Based on the second model, an edge AI model with local rendering and retrieval functions is generated; Introducing content distribution network technology to distribute and cache animation assets; Deploy AI-based intelligent asset management engine and analysis modules in the cloud; Deploy identity authentication and access control systems to manage asset access rights for multiple users; Encryption and digital signatures protect important assets and prevent leakage and data tampering.
9. The method for managing animation engine resources based on artificial intelligence according to claim 8, It is characterized in that The steps of optimizing the asset distribution and version control process include: Deploy multiple CDN nodes to achieve edge caching and distribution of assets; Generate multiple distribution paths according to the location and router address of the CDN node, combined with a preset router intelligent control strategy and a dynamic routing allocation scheme; Utilize file system snapshot technology and data deduplication technology to calculate the first difference data between asset versions; distributing the first difference data through the distribution path; Connecting the CDN node to a preset first blockchain network; Uploading all the version management data, propagation path data and equity transaction data of the animation assets involved in each CDN node to the chain; Utilize smart contracts on the First Blockchain network to automate copyright protection, usage authorization, and revenue distribution; Introducing a version control system to support distributed collaborative editing of animation assets.
10. The method for managing animation engine resources based on artificial intelligence according to claim 9, It is characterized in that The step of using deep learning technology to generate new animation assets based on the animation engine resource asset data and automatically expanding the animation asset library includes: Expanding the data volume of the first animation asset data according to a preset data compression and enhancement strategy to obtain first training data; Designing generative model architectures suitable for different asset types; Using the first training data to train the generation model architecture to obtain a first asset generation model; For a specific asset production task, fine-tune the first asset generation model to obtain a second asset generation model; Generate a new animation asset according to the animation engine resource asset data and the second asset generation model; Perform quality assessment on the newly generated animation assets and filter out unqualified results.
Citation Information
Patent Citations
Visual analysis method and device for integrity of pipe network assets
CN114860890A
Sanitation integrated asset management system
CN115689535A
Cloud edge collaborative management system and method based on intelligent Internet of Things system
CN117391645A
Multi-modal data asset management method, system and equipment based on large model and medium
CN117632640A
Data asset identification and risk early warning system and method based on financial knowledge graph and large language model
CN118247057A
Cited By
Commercial credit evaluation and supervision method based on multi-modal coevolution algorithm
CN119250963A
Short video production method and system based on artificial intelligence
CN120547417A
Short video production method and system based on artificial intelligence
CN120547417B
