Metadata-Based Anomaly Detection Using Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer systems face challenges in effectively detecting anomalies in user activities, as existing methods often require processing vast volumes of data, leading to inefficiencies in resource usage and detection accuracy.
Innovation Solution
The proposed solution involves generating metadata from electronic documents stored on a management platform, using machine learning models to identify anomalies by transforming features into feature vectors and training anomaly-detection models, which automatically trigger actions in response to detected anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vast volumes of data are processed for anomaly detection, then detection comprehensiveness is improved, but resource usage efficiency deteriorates
Solution Approach 1:
The patent extracts and processes only metadata from electronic documents rather than analyzing the complete document content. The system generates metadata items for each document, transforms them into feature vectors, and feeds only these condensed representations to the machine learning model, thereby reducing data volume while preserving anomaly detection capability
Solution Approach 2:
The patent segments the document analysis process into two distinct stages: first generating metadata items that capture essential document characteristics, then transforming these metadata into feature vectors for model input. This segmentation allows the system to process only the most relevant extracted features rather than raw document content
2Use of energy by moving object
If metadata-based anomaly detection is implemented, then resource usage efficiency is improved, but detection precision may deteriorate
Solution Approach 1:
The patent transforms metadata items into feature vectors through a parameter transformation process. The system determines a set of features based on metadata items and transforms them into a standardized feature vector format that is optimized for machine learning model input, thereby enhancing detection precision while maintaining resource efficiency
Solution Approach 2:
The patent introduces feature vectors as an intermediary representation between raw metadata and the machine learning model. These feature vectors serve as a bridge that condenses metadata information into a format that preserves anomaly-related patterns while reducing computational complexity
Data Source
AI summary
Systems and methods for providing metadata-based anomaly detection, comprising: storing a plurality of sets of electronic documents associated with a plurality of users; generating a set of metadata items for each document in each set of the plurality of sets of documents; determining a set of features based on the set of metadata items for each document in each set of the plurality of sets of documents; transforming the set of features into a set of feature vectors, each feature vector tagged to indicate a correspondence to a particular anomaly or not; and training, based at least in part on the set of features vectors, a data anomaly-detection machine learning model to obtain a trained data anomaly-detection machine learning model, the data anomaly-detection machine learning model comprising a set of triggering rules that are configured to determine a plurality of anomalies within a particular set of metadata items.