Semantic Network Generation for Text Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In systems requirement documents, missing or misplaced instructions can lead to incorrect system design and costly mistakes due to inconsistent or dependent instructions, which existing technologies fail to effectively address.
Innovation Solution
A device and method that analyze text to identify semantic connections between subject-verb-object (SVO) units, generating a semantic network to detect errors and inconsistencies by performing semantic role labeling, discourse connective analysis, verb relation and entailment analysis, and boundary connector and flow analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If text documents are analyzed manually for semantic connections and inconsistencies, then detection accuracy may be maintained, but time consumption and productivity are significantly reduced
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated computational system that uses natural language processing, semantic role labeling, and dependency parsing to detect inconsistencies and semantic connections in text documents, thereby maintaining detection accuracy while dramatically improving productivity
Solution Approach 2:
The patent introduces an intermediary computational layer that processes text through multiple analysis stages including semantic role labeling, dependency parsing, and contradiction detection algorithms, acting as a mediator between raw text and final inconsistency detection to achieve both accuracy and efficiency
2Ease of manufacture
If existing text analysis technologies are used, then basic text processing is achieved, but detection of missing or misplaced instructions and semantic inconsistencies is insufficient
Solution Approach 1:
The patent segments the text analysis process into distinct functional modules including semantic role labeling, dependency parsing, instruction extraction, and contradiction detection, allowing each component to specialize in specific aspects of analysis and thereby improving overall detection reliability while maintaining ease of implementation
Solution Approach 2:
The patent performs preliminary semantic role labeling and dependency parsing before conducting contradiction detection, preparing structured representations of the text in advance to enable more accurate and reliable detection of missing or misplaced instructions
3Measurement precision
If comprehensive semantic analysis is performed on all text documents, then detection accuracy improves, but computational complexity and resource requirements increase
Solution Approach 1:
The patent divides comprehensive semantic analysis into sequential stages including semantic role labeling, dependency parsing, instruction extraction, and contradiction detection, processing only relevant portions of text at each stage to maintain high detection accuracy while reducing overall computational complexity
Solution Approach 2:
The patent applies different levels of analysis intensity to different parts of the text based on their relevance to instruction detection, focusing computational resources on critical sections containing potential inconsistencies while using lighter processing for routine text portions
Data Source
AI summary
A device may obtain text to be analyzed to determine semantic connections between sections of the text. The device may identify subject-verb-object (SVO) units included in the text, and may determine SVO unit information that describes the SVO units. The device may analyze the SVO unit information to determine semantic connection information that identifies one or more semantic connections between two or more of the SVO units. The one or more semantic connections may identify relationships between verbs associated with the two or more of the SVO units. The device may generate a semantic network based on the SVO unit information and the semantic connection information, and may provide information regarding the semantic network.