Original Idea Extraction via Knowledge Graph Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current approaches fail to automatically and systematically identify original ideas and link them to existing concepts, preventing effective networking and collaboration among individuals expressing similar ideas.
Innovation Solution
A computer-implemented method captures written text data, constructs a knowledge graph to represent concepts and relationships, and determines original ideas by correlating thought units to the graph, enabling the detection of novelty and commonalities among ideas and facilitating networking of individuals with similar ideas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current approaches use large tables to find co-occurrences of terms in social media posts, then search results can be improved, but there is no cognitive component to find and link new ideas and the individuals expressing them
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary data structure that bridges the gap between term co-occurrence analysis and cognitive understanding. The knowledge graph stores predefined concepts and relationships, serving as a mediator that enables systematic identification of original ideas by comparing expressed thoughts against existing knowledge structures, thereby adding cognitive capability without directly increasing system complexity
Solution Approach 2:
The patent segments the idea detection process into distinct components: extracting thought units from text, mapping them to knowledge graph concepts, and evaluating originality based on relationship distances. This segmentation allows each component to be processed independently and efficiently, improving measurement precision while managing system complexity through modular design
2Loss of information
If the system maps thought units to knowledge graph by correlating concepts, then it can detect novelty and commonalities among ideas, but this requires substantial processing power and time
Solution Approach 1:
The knowledge graph is pre-computed and stored before the idea detection process begins. All concept relationships and distances are established in advance, allowing the system to quickly map thought units to existing concepts without performing complex calculations during the actual detection phase. This preliminary action preserves idea originality information while significantly reducing processing time
Solution Approach 2:
The patent creates a structured representation (copy) of knowledge in the form of a knowledge graph that mirrors the relationships in the source corpus. This copied structure enables efficient querying and comparison operations, allowing the system to detect novelty by comparing thought units against the pre-established knowledge copy rather than re-analyzing the entire corpus each time
3Adaptability or versatility
If the system stores representations of original ideas in an idea repository, then networking of individuals with similar ideas can be facilitated, but the quantity of data to be processed and stored increases
Solution Approach 1:
The patent extracts only the essential elements needed for networking - the original idea representations and their associated metadata - and stores them in a dedicated idea repository. By taking out only the relevant information (original ideas rather than all processed data), the system enables networking capability while minimizing the volume of stored data through selective extraction of valuable information
Data Source
AI summary
Original idea extraction from written data is provided by capturing expression as written text data, obtaining a knowledge graph representing concepts and relationships between the concepts, automatically topic modeling the written text data to ascertain thought units and identify respective concepts of the thought unit, mapping a thought unit to the knowledge graph, determining that the thought unit is an original idea, and based on determining that the thought unit is an original idea, storing a representation of the original idea to an idea repository and invoking processing of at least one computer.