Story Generator for Coherent Narrative from Thought Sequences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Natural Language Processing (NLP) and Natural Language Understanding (NLU) systems are limited in understanding the relationships between sentences and fail to create coherent stories from human thought representations, as they process well-formed sentences one-by-one without considering time sense, possibility, or reasoning, leading to incomplete and isolated meaning representations.
Innovation Solution
A system comprising an entity dereferencing and enrichment module, an anomaly detecting unit, and an inter thought representation reasoning and transformation unit, which uses entity and thought representation knowledge bases to perform entity dereferencing, anomaly detection, and reasoning to create coherent stories by analyzing sequences of thought representations and facilitating data flow between modules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If NLP/NLU systems process sentences one-by-one in isolation, then processing simplicity is maintained, but understanding of relationships between sentences deteriorates
Solution Approach 1:
The system segments the processing into two distinct phases: (1) individual sentence processing through NLP/NLU to extract intent and entities, and (2) sequential processing of intent sequences through the story generator. This segmentation allows simple individual processing while enabling relationship understanding through the dedicated sequence analysis phase.
Solution Approach 2:
The patent introduces an intermediary component - the story generator with its intent sequence processor and knowledge base - that acts as a mediator between individual sentence processing and coherent story creation. This intermediary analyzes the sequence of intents, detects anomalies, and generates the narrative structure, thereby preserving relationship understanding without complicating the core NLP processing.
2Productivity
If statistical methods are used for context representation, then processing efficiency is improved, but reasoning capability deteriorates
Solution Approach 1:
The system segments reasoning functions into dedicated modules: the anomaly detector identifies context violations, the story generator structures narratives, and the knowledge base provides logical frameworks. This segmentation enables efficient statistical processing of individual sentences while maintaining reliable reasoning through specialized components that handle sequential logic.
Solution Approach 2:
The story generator serves as an intermediary between statistical sentence processing and reasoning requirements. It receives intent sequences, uses the knowledge base for logical validation, detects anomalies that violate contextual rules, and generates coherent stories. This intermediary layer preserves processing efficiency while introducing reliable reasoning capabilities.
3Device complexity
If sentence-by-sentence processing is used, then system complexity is reduced, but story coherence deteriorates
Solution Approach 1:
The system segments story coherence generation into distinct functional modules: the intent sequence processor maintains contextual state, the anomaly detector ensures logical consistency, and the story generator assembles coherent narratives. This segmentation achieves story coherence without requiring a monolithic complex system, as each module handles a specific aspect of coherence.
Solution Approach 2:
The story generator acts as an intermediary that transforms discrete sentence-level intents into coherent story structures. It uses the knowledge base to ensure logical consistency, processes intent sequences to maintain contextual flow, and generates narratives with proper temporal and causal relationships. This intermediary enables coherence without proportionally increasing overall system complexity.
Data Source
AI summary
A system to convert sequences of human thought representations into coherent stories, in association with a language understanding system is disclosed. Said system comprises: an entity dereferencing and enrichment module, an anomaly detecting unit that comprises: a context anomaly module, and a meaning anomaly and reinforcement module; an inter thought representation reasoning and transformation unit; an entity knowledge base; a thought representation knowledge base; and an output thought representation cloud. The system takes sequences of thought representations as input and tries to make sense out of them. The system is used in association with any type of language understanding system for creating meaning out of the sequence of thoughts.