Insight Creation Filtering via K-Partite Metadata Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital organization strategies lack transparency and flexibility in leveraging insights from vast datasets for predicting future trends, as they do not effectively filter or adjust unstructured/structured data to derive impactful insights.
Innovation Solution
A method for insight creation filtering that involves receiving a transparent query, extracting keywords, generating a k-partite metadata graph, creating interactive query results, detecting user interactions, and updating results based on user adjustments to provide transparent and impactful insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a complete metadata graph is used for insight generation, then comprehensive data coverage is achieved, but processing complexity and time increase
Solution Approach 1:
The patent divides the complete metadata graph into multiple k-partite subgraphs based on different metadata types (e.g., financial data, operational data, market data). Each partite graph processes a specific subset of data, enabling parallel processing and reducing overall computational complexity while maintaining comprehensive data coverage.
Solution Approach 2:
The system generates insights from multiple perspectives by creating k different insight sets from k-partite graphs, where each insight set focuses on specific metadata types. This partial action approach allows the system to process data in manageable segments rather than attempting to analyze the entire graph simultaneously.
2Productivity
If keyword-based filtering is applied to the metadata graph, then processing efficiency improves, but information completeness may be reduced
Solution Approach 1:
The patent applies different filtering strategies to different parts of the metadata graph based on local requirements. Keyword-based filtering is applied selectively to specific partite graphs based on their metadata types, while other parts use different filtering approaches. This ensures that each data subset is processed with the most appropriate method, maintaining both efficiency and completeness.
Solution Approach 2:
The system performs partial filtering on subsets of the metadata graph rather than applying uniform filtering to the entire graph. This allows keyword-based filtering to improve efficiency for relevant data while preserving information completeness by leaving other data subsets unfiltered or differently filtered.
3Adaptability or versatility
If multiple insight perspectives are generated, then analytical depth increases, but result complexity increases
Solution Approach 1:
The patent segments insights into multiple distinct perspectives (k insight sets), where each insight set corresponds to a specific partite graph and metadata type. This segmentation allows users to analyze different aspects of the data separately while maintaining the ability to integrate findings, thereby increasing analytical depth without overwhelming complexity.
Solution Approach 2:
The system adds a dimensional aspect to insight generation by creating insights across k different partite graphs simultaneously. Each graph provides insights from a different dimensional perspective (e.g., financial dimension, operational dimension, market dimension), enabling multi-dimensional analysis while organizing results in a structured manner that manages complexity.
Data Source
AI summary
A method and system for insight creation filtering. Explainable artificial intelligence, in recent years, has become synonymous with a framework through which users, relying on machine learning models for various applications, may come to trust the result(s) outputted by said models through better comprehension of the mechanisms leading to said result(s). Leveraging a vast database of metadata for a plethora of unstructured and structured data/information, embodiments disclosed herein derive, or infer, insights therefrom that best address any user-submitted queries. Embodiments disclosed herein, further, provide transparency information detailing, for example, which input(s) and which technique(s) and/or algorithm(s) were employed to arrive at the derived/inferred insights. Moreover, embodiments disclosed herein enable users to make adjustments to (e.g., through the filtering/pruning of) the unstructured/structured data/information determined to be most impactful in the derivation, or inference, of any insights in order to ascertain suppositional insights resulting from said adjustments.