Process Graph Generation from Multi-Media Narratives
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems fail to efficiently capture and characterize narrative information from subject matter experts, often missing important details and treating various types of data equally, which leads to poor replication of complex business processes.
Innovation Solution
A computer-implemented system that collects and processes narrative information from content generators, using processors to analyze and score data based on factors like emotion, truthfulness, and posture analysis, generating a process graph with weighted nodes and edges to derive actionable steps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional interview methods are used to capture expert knowledge, then some narrative information can be obtained, but important details are missed and data is treated equally without proper weighting
Solution Approach 1:
The patent segments narrative information into multiple types (factual, procedural, contextual, emotional) and processes each type separately with appropriate weighting. This segmentation allows the system to capture diverse information types without treating them all equally, thereby reducing information loss while maintaining characterization precision.
Solution Approach 2:
The patent applies different processing qualities to different types of narrative information. Factual information receives different weighting than procedural or emotional information. This local quality approach ensures that each information type is characterized with the appropriate level of detail and importance, preventing both information loss and over-emphasis on less critical data.
2Measurement precision
If domain expertise is required to identify relevant information, then accurate process characterization can be achieved, but the process becomes inefficient and inaccessible to less experienced practitioners
Solution Approach 1:
The patent creates a structured digital copy of expert knowledge in the form of a process graph with weighted nodes and edges. This copy captures the nuanced decision-making processes of experts without requiring the original experts to be present. Less experienced practitioners can access and follow this copied knowledge, improving productivity while maintaining the precision of expert-level process characterization.
Solution Approach 2:
The patent introduces an intermediary system (the narrative analysis system) that translates unstructured expert narratives into structured process graphs. This intermediary bridges the gap between expert knowledge and practitioner application, making expert-level process characterization accessible without requiring direct expert involvement in each case.
3Device complexity
If all narrative information is treated equally, then processing is simplified, but important data is underemphasized and critical process details are lost
Solution Approach 1:
The patent applies different processing qualities and weighting factors to different types of narrative information. Critical factual information receives higher weight than less important contextual details. This approach prevents information loss of critical data while avoiding the complexity of manual prioritization, as the weighting is automatically applied based on information type classification.
Data Source
AI summary
A system for characterizing content relating to a desired outcome is disclosed. The disclosed system can be configured to identify context included in content collected from various content sources, map the identified context into graph nodes and graph edges connecting the graph nodes, identify one or more features of the identified context and adjust at least one of: a graph node and a graph edge based on the identified one or more features, identify a graph incorporating the graph nodes, the graph edges, and at least one of an adjusted graph node and an adjusted graph edge, and provide a recommendation for at least one action for achieving the desired outcome based on the identified graph.