Automated Narrative Story Generation System Using Angle Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack the ability to automatically generate narrative stories from domain-specific data in a comprehensible and compelling manner, failing to customize stories for specific audiences effectively.
Innovation Solution
A system and method that processes domain-related data to derive features, identify angles, filter and prioritize narrative elements, select and assemble relevant facts, and render stories in a customized format, using a network of processing devices to create engaging narratives across various domains.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated story generation is implemented, then productivity is improved, but the quality and engagement of narratives deteriorates
Solution Approach 1:
The patent introduces multiple intermediary components between raw data and final narrative output, including angle identification modules, fact selection filters, and template-based generation systems. These intermediaries process and refine information at each stage, ensuring that automated generation maintains high narrative quality while achieving productivity gains through systematic automation.
Solution Approach 2:
The system incorporates feedback mechanisms where generated stories are evaluated against multiple criteria including factual accuracy, narrative coherence, and audience appropriateness. This feedback loop allows the system to iteratively refine story generation, maintaining reliability while automating the process across multiple stories.
2Measurement precision
If comprehensive data processing is performed to ensure accurate story generation, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the complex data processing task into distinct segmented modules: data ingestion, feature extraction, angle identification, fact selection, and narrative generation. Each module handles a specific aspect of processing with defined inputs and outputs, maintaining measurement precision through specialized processing while reducing overall system complexity through modular architecture.
Solution Approach 2:
The system employs universal data structures and processing frameworks that can handle multiple types of domain-specific data (sports, business, finance, etc.) through the same core architecture. This multi-functionality allows comprehensive data processing for accurate story generation without proportionally increasing complexity, as the same modules serve multiple data types and story genres.
3Adaptability or versatility
If multiple angles and perspectives are considered for story generation, then adaptability is improved, but loss of information increases
Solution Approach 1:
The system performs preliminary actions by pre-identifying multiple relevant angles and perspectives from the available data before story generation begins. All potential facts supporting different angles are extracted and stored with their contextual metadata, ensuring that information is preserved in advance and can be selectively assembled based on the chosen narrative angle without loss of underlying data.
Solution Approach 2:
The patent implements a nested structure where multiple levels of information are organized hierarchically: raw data contains facts, facts contain supporting evidence, and each angle is nested within the broader context of the domain. This nesting allows the system to adapt to different audience perspectives by selecting at which level to focus while preserving all underlying information in the nested structure.
Data Source
AI summary
A system and method for automatically generating a narrative story receives data and information pertaining to a domain event. The received data and information and/or one or more derived features are then used to identify a plurality of angles for the narrative story. The plurality of angles is then filtered, for example through use of parameters that specify a focus for the narrative story, length of the narrative story, etc. Points associated with the filtered plurality of angles are then assembled and the narrative story is rendered using the filtered plurality of angles and the assembled points.