Cognitive Graphs for Dark Data Insight Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in efficiently processing and analyzing large volumes of big data, particularly 'dark data' which is neglected or underutilized, making it difficult to extract actionable insights in a timely manner.
Innovation Solution
A cognitive inference and learning system (CILS) that processes streams of data from multiple sources, generates cognitive graphs, and produces composite cognitive insights by integrating semantic analysis, goal optimization, collaborative filtering, common sense reasoning, natural language processing, and entity resolution to provide actionable insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional data processing approaches are used to handle big data, then data storage and basic processing can be achieved, but the ability to efficiently extract actionable insights from dark data deteriorates due to the complexity and volume of data
Solution Approach 1:
The system segments dark data into structured components using ontologies and cognitive graphs, dividing the undifferentiated data mass into meaningful entities, relationships, and patterns that can be processed independently and efficiently
Solution Approach 2:
The patent introduces cognitive graphs and ontologies as intermediary structures between raw dark data and actionable insights. These intermediaries organize and contextualize data, making it accessible for efficient analysis and insight generation
2Measurement precision
If comprehensive data collection from multiple sources is performed to improve insight quality, then the depth and breadth of analysis improve, but the time required to process and analyze the data increases
Solution Approach 1:
The system performs preliminary organization of data from multiple sources into cognitive graphs and ontological structures before analysis is needed. This pre-structuring of data enables faster retrieval and processing when insights are required, reducing the time penalty of comprehensive data collection
Solution Approach 2:
The patent transforms data from its original heterogeneous formats into a standardized ontological representation with defined parameters and relationships. This parameter transformation enables efficient querying and analysis across diverse data sources without sacrificing accuracy
3Loss of information
If dark data is utilized to generate unique insights, then competitive advantage and decision-making quality improve, but the complexity of processing unstructured and neglected data increases
Solution Approach 1:
The patent creates a universal processing framework using ontologies and cognitive graphs that can handle multiple types of unstructured data (text, sensor data, social media, etc.) through a single system architecture, reducing complexity through standardization rather than requiring separate processing systems for each data type
Data Source
AI summary
A method for providing composite cognitive insights comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching and generating a sub-graph for incorporation into a cognitive graph; processing the cognitive graph, the processing the cognitive graph providing a plurality of individual cognitive insights; and, generating a composite cognitive insight, the composite cognitive insight being composed of the plurality of individual cognitive insights.