Automated Narrative Generation with Story Angle Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for automatically generating narrative stories from data lack effective criteria to determine when and how to generate stories, leading to inefficiencies and irrelevant content.
Innovation Solution
A method and apparatus that evaluate data against a set of story angles and applicability conditions to determine whether a narrative story should be generated, using a processor to access an angle set data structure and compute interestingness data, comparing it with thresholds to decide on story generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated narrative generation is performed without evaluation criteria, then story generation can occur freely, but the relevance and quality of generated stories deteriorates
Solution Approach 1:
The system performs preliminary evaluation of data against multiple story angles and applicability conditions before generating narratives. The story evaluator assesses whether data satisfies specific conditions (e.g., significance thresholds, recency requirements) and generates evaluation indicators that determine if a story should be produced, ensuring only relevant stories are generated
Solution Approach 2:
The system changes parameters by computing derived features from raw data (e.g., transforming box score data into meaningful metrics) and comparing these derived features against thresholds. This parameter transformation enables the system to assess story applicability and generate only when conditions are met, balancing automation with quality
2Manufacturing precision
If multiple story angles are evaluated with multiple conditions, then story relevance improves, but system complexity increases
Solution Approach 1:
The evaluation system is segmented into distinct story angles (e.g., comeback victory, record breaking, upset), each with its own applicability conditions. The story evaluator independently assesses data against each angle's conditions, allowing modular evaluation that improves comprehensiveness while managing complexity through structured organization
Solution Approach 2:
The story evaluator performs multiple functions: it accesses angle set data structures, processes data against multiple applicability conditions, computes derived features, and generates evaluation indicators. This multi-functional component handles diverse evaluation tasks through a unified mechanism, reducing overall system complexity
Data Source
AI summary
Artificial intelligence methods and systems for triggering the generation of narratives are disclosed. Specific embodiments relate to real-time evaluation and automated generation of narrative stories based on received data. For example, data can be tested against data representative of a plurality of story angles to determine whether a narrative story incorporating one or more such story angles is to be automatically generated.