Author Identification via Feature Similarity Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack an objective technique to identify the author of a creative work whose authorship information is unknown, often relying on subjective judgments and introducing human bias.
Innovation Solution
A system that extracts features from identified and unidentified creative works, compares them using similarity scores, and associates the unidentified work with the author of the most similar identified work, utilizing machine learning models and a creative work database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If subjective judgment methods are used to identify authorship, then human expertise can be applied, but human bias and lack of objectivity are introduced
Solution Approach 1:
The patent replaces subjective human judgment with an automated machine learning system that uses feature extraction and similarity comparison algorithms. The system extracts numerical features from creative works and compares them using computational methods, eliminating human bias while maintaining expertise through trained models.
Solution Approach 2:
The system performs self-service by automatically extracting features, comparing similarities, and identifying authors without requiring continuous human intervention. The machine learning model autonomously processes creative works and makes authorship determinations based on learned patterns from training data.
2Productivity
If manual analysis of creative works is performed, then detailed examination is possible, but time consumption increases
Solution Approach 1:
The patent segments the creative work into discrete numerical features through feature extraction. By breaking down the creative work into measurable components (such as stylistic characteristics, structural elements, or content features), the system can rapidly process and compare large amounts of data while maintaining precision through comprehensive feature analysis.
Solution Approach 2:
The system performs preliminary feature extraction and transformation of creative works into numerical representations before comparison. This pre-processing step enables rapid similarity calculation and authorship identification by preparing the data in advance in a format suitable for efficient computational comparison.
3Reliability
If a comprehensive database of creative works is maintained, then more accurate authorship identification is possible, but storage and processing requirements increase
Solution Approach 1:
The patent extracts only the essential numerical features from creative works for storage and comparison, rather than storing the complete creative works themselves. This feature extraction approach reduces the volume of data that needs to be stored and processed while maintaining the information necessary for accurate authorship identification through similarity comparison.
Data Source
AI summary
An embodiment establishes a creative work database based in part on data representative of a plurality of identified creative works and authors associated with the plurality of identified creative works. The embodiment extracts a set of a first set of features from an unidentified creative work. The embodiment compares the first set of features corresponding to the unidentified creative work to a second set of features corresponding to an identified creative work to obtain a similarity score between the unidentified creative work and the identified creative work. The embodiment compares the similarity score to a threshold similarity score, and upon a determination that the similarity score meets the threshold similarity score, identifies a particular author to associate with the unidentified creative work. The embodiment authenticates the new identified creative work. The embodiment updates the creative work database to include the new identified creative work.