Electronic Asset Ownership via Feature Space Tokens
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively assert and manage ownership of electronic assets and their variants, such as images, videos, and 3D models, by not facilitating identification of copying, licensed use, or ownership control.
Innovation Solution
The method involves using a machine learning model to identify points in a feature space for electronic assets and their variants, creating a representation of ownership by training a fixed function classifier to minimize distances for similar assets and maximize distances for dissimilar ones, and generating a token that asserts ownership, which can be used to check if an asset falls within an already-claimed portion of the feature space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional ownership assertion methods are used for electronic assets, then ownership of the original asset can be established, but ownership of variants and derivatives cannot be effectively protected
Solution Approach 1:
The patent transitions from protecting individual electronic assets to protecting a multidimensional feature space. By mapping assets into an n-dimensional feature space and defining ownership over regions in this space, the system extends protection from discrete points (individual assets) to continuous volumes (regions containing variants and derivatives). This dimensional expansion allows single ownership assertions to cover multiple asset variations.
Solution Approach 2:
The patent creates a digital representation (token) that copies and encapsulates the ownership information for an entire region of feature space. This token serves as a portable, verifiable copy of ownership rights that can be transferred or licensed without transferring the actual electronic assets, enabling efficient ownership management across distributed systems.
2Measurement precision
If manual identification of asset variants is performed, then precise ownership boundaries can be defined, but the process becomes time-consuming and impractical for large-scale assets
Solution Approach 1:
The system implements self-service by automatically computing feature space mappings and identifying variant relationships without requiring manual input from asset owners. The automated pipeline extracts features, computes embeddings, and determines ownership regions algorithmically, enabling rapid processing of large asset collections while maintaining precise boundary definitions through mathematical optimization.
Solution Approach 2:
The patent transforms the ownership definition problem from a manual boundary-drawing task to an automated parameter optimization problem. By changing parameters such as feature extraction methods, embedding dimensions, and region clustering algorithms, the system adapts to different asset types and scales while maintaining precision through configurable hyperparameters that control the granularity of ownership regions.
3Reliability
If comprehensive variant identification is implemented, then complete ownership coverage is achieved, but system complexity and computational requirements increase significantly
Solution Approach 1:
The patent segments the complex task of comprehensive ownership protection into distinct modular components: feature extraction module, embedding computation module, region clustering module, and token generation module. Each component handles a specific aspect of the pipeline independently, allowing parallel processing and reducing overall system complexity while achieving complete variant coverage through coordinated operation of these segmented functions.
4Reliability
If feature space mapping is used to cover all variants, then ownership protection is comprehensive, but the computational resources required increase
Solution Approach 1:
The patent applies partial action by computing feature space mappings only for the essential dimensions needed to distinguish variants, rather than exhaustively processing all possible feature combinations. By selecting a subset of discriminative features and using dimensionality reduction techniques, the system achieves sufficient ownership coverage with reduced computational energy consumption, avoiding the excessive computation that would result from analyzing every possible asset variation.
Data Source
AI summary
Various implementations manage an electronic asset by creating a representation of an electronic asset and its variants. This may be accomplished by identifying variants of an electronic asset, identifying a portion of a feature space associated with the asset and variants, and providing a representation corresponding to that portion of feature space. A fixed function classifier may be used to determine the points in the feature space for the electronic asset and its variants. The set of points produced for an asset and its variants using such a fixed function classifier will be near one another in feature space. Moreover, the area around such points will also represent points for other similar variations of the asset and thus, the portion of the feature space around the points can be considered the area of ownership for the electronic asset, e.g., it defines a boundary of what the creator is asserting is his or her creation.