AI Narrative Generation Using Composable Ontologies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional natural language generation (NLG) systems face limitations in communicating data-driven ideas per sentence, variability in word choice, and analyzing data sets to determine content for narrative stories, leading to constrained narrative generation capabilities.
Innovation Solution
The development of AI technology that uses composable communication goal statements and ontologies to facilitate the generation of narrative stories from data sets, allowing users to structure story outlines without coding, with the ontology being reusable and adaptable, and employing a conditional outcome framework for intelligent content adaptation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional template approaches are used for NLG, then the system structure is simple and easy to implement, but the narrative generation capabilities are constrained with limited data-driven ideas per sentence and restricted word choice variability
Solution Approach 1:
The patent segments the NLG system into distinct modular components: a data analysis module that identifies data-driven ideas, a template selection module that chooses appropriate sentence structures, and a word substitution module that introduces variability. This segmentation allows each component to specialize in one function, improving overall narrative generation capabilities while keeping individual modules manageable in complexity
Solution Approach 2:
The patent implements universal templates that can handle multiple types of data-driven ideas through parameterization. Instead of creating separate templates for each specific narrative pattern, the system uses a set of core templates with configurable parameters that adapt to different data types and contexts, thereby expanding narrative versatility without proportionally increasing system complexity
2Measurement precision
If the system analyzes data sets to determine content for narrative stories, then the narrative content becomes more accurate and relevant, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary data analysis by pre-identifying and categorizing data-driven ideas before the actual narrative generation process. The system pre-processes the data set to extract key insights, relationships, and patterns, storing them in a structured format that can be quickly retrieved and applied during story generation, thus reducing real-time processing requirements while maintaining high content accuracy
Solution Approach 2:
The patent applies different levels of analysis depth to different portions of the data set based on their importance to the narrative. Critical data points that directly impact story accuracy receive thorough analysis, while less critical information undergoes lighter processing. This localized quality approach ensures high content accuracy where needed while minimizing overall processing time
3Adaptability or versatility
If conventional NLG systems are used, then the system is easy to operate, but the user accessibility is limited and coding requirements constrain user base
Solution Approach 1:
The patent implements a system where the NLG engine automatically performs data analysis, template selection, and narrative generation without requiring user coding or complex configuration. Users simply provide the data set and desired story type, and the system self-manages the entire generation process, making advanced narrative generation accessible to non-technical users while maintaining operational simplicity
Data Source
AI summary
Artificial intelligence (AI) technology can be used in combination with composable communication goal statements to facilitate a user's ability to quickly structure story outlines in a manner usable by an NLG narrative generation system without any need for the user to directly author computer code. This AI technology permits attribute structures within an ontology can include an explicit model for the subject attribute, regardless of whether that model is used to compute the value of the subject attribute itself. This explicit model can then be leveraged to support an investigation of drivers of the value for the subject attribute. Narrative analytics that perform driver analysis can then be used to support narrative generation for communication goals relating to explanations, predictions, recommendations, and the like.