Thematic Concept Conformance Scoring via Data Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Business analysts face challenges in efficiently managing and analyzing vast amounts of data from various sources to identify relevant information for market or industry research, often relying on personal knowledge due to the overwhelming volume and complexity of available information.
Innovation Solution
A system that utilizes data graphs and scoring models to associate thematic concepts with organizations, generating thematic scores based on relationships between concepts and entities, allowing for the identification of relevant information and conformance to thematic concepts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If analysts review vast amounts of information from multiple sources, then analysis completeness is improved, but time consumption increases
Solution Approach 1:
The system performs automated information gathering, processing, and analysis without requiring manual intervention from analysts. The automated analysis system independently retrieves data from multiple sources, processes information, generates insights, and provides recommendations, thereby eliminating the time-consuming manual review process while maintaining comprehensive analysis coverage.
Solution Approach 2:
The patent replaces manual mechanical processes of information review and analysis with automated computational systems. The automated analysis system uses algorithms, data processing mechanisms, and computational models to perform tasks that would otherwise require human analysts to manually read, interpret, and synthesize information from numerous sources.
2Productivity
If analysts rely on personal knowledge and experience, then analysis speed is improved, but analysis objectivity deteriorates
Solution Approach 1:
The system performs automated information gathering, processing, and analysis without requiring manual intervention from analysts. The automated analysis system independently retrieves data from multiple sources, processes information, generates insights, and provides recommendations, thereby eliminating the time-consuming manual review process while maintaining comprehensive analysis coverage.
Solution Approach 2:
The automated analysis system incorporates feedback mechanisms that continuously monitor and adjust its analysis based on new data and patterns. The system learns from historical data, refines its models, and provides iterative improvements in analysis accuracy and objectivity, ensuring that conclusions are based on evidence rather than subjective judgment.
3Loss of information
If analysts manually process information from multiple sources, then information relevance is improved, but effort requirement increases
Solution Approach 1:
The system divides the complex information processing task into separate functional modules: data collection from multiple sources, data processing and cleaning, information extraction, analysis generation, and insight presentation. Each module handles a specific aspect of the workflow, making the overall complex process manageable and automated without requiring manual effort in any single segment.
Solution Approach 2:
The automated analysis system acts as an intermediary between raw information from multiple sources and the final analysis outputs. This intermediary layer processes, filters, and synthesizes information automatically, transforming raw data into relevant insights without requiring analysts to manually navigate through the complexity of multiple data sources.
Data Source
AI summary
Embodiments are directed to managing data using network computers. A data graph may be provided based on knowledge graphs and information provided by data sources. Concepts and entities may be provided based on the data graph. Scoring models may be determined based on the concepts and the entities. Thematic scores for the entities may be generated based on the scoring models and the data graph such that the thematic scores include values that quantify each relationship between the concepts and the entities and such that an entity with a higher thematic score value for a concept has a relationship strength value that exceeds another relationship strength value for another entity with a lower thematic score value for the concept. A report that includes the thematic scores, the entities, and the concepts may be provided.