Textual Relationship Identification via Word Vector Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for mapping textual requirements to process models in enterprise software implementations face challenges such as linguistic complexity, high-frequency terms, and implicit details, which can lead to inefficiencies and inaccuracies in identifying relationships between requirements and capabilities.
Innovation Solution
A computer-implemented method that identifies textual statement relationships by parsing word groups, calculating scores, and using word vectors to match requirements with process model capabilities, leveraging natural language processing, information retrieval techniques, and semantic reasoning to automate the mapping process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional text matching methods are used to map requirements to process models, then the system is simple to implement, but the accuracy and precision of identifying textual relationships deteriorates due to linguistic complexity and high-frequency terms
Solution Approach 1:
The system segments the text matching process into multiple independent components: parsing word groups to extract meaningful units, creating word vectors to represent semantic meaning, calculating parsed word scores for structural similarity, calculating word vector scores for semantic similarity, and combining these into an overall match score. This segmentation allows each component to specialize in handling specific aspects of linguistic complexity.
Solution Approach 2:
Word vectors serve as an intermediary representation between the raw textual requirements and the process model capabilities. By transforming text into vector space representations, the system mediates the matching process, enabling semantic comparison while filtering out high-frequency terms and linguistic noise that would otherwise interfere with accurate matching.
2Productivity
If manual mapping of requirements to process models is performed, then the system is simple and interpretable, but the productivity and efficiency of the software implementation process deteriorates
Solution Approach 1:
The system enables automated self-service matching of requirements to process model capabilities without requiring manual intervention. The automated system parses requirements, creates word vectors, calculates match scores, and identifies corresponding capabilities autonomously, dramatically improving productivity while the modular architecture keeps the system manageable through clear separation of concerns.
Solution Approach 2:
The system replaces the mechanical manual process of requirement mapping with an automated computational system. Instead of manually comparing text to process models, the system uses natural language processing, vector space models, and automated scoring mechanisms to perform the mapping, eliminating manual labor while maintaining accuracy through multiple computational layers.
3Adaptability or versatility
If simple text comparison is used, then the system is fast to execute, but the ability to handle poorly formed requirements and identify implicit relationships deteriorates
Solution Approach 1:
The system performs preliminary actions by parsing word groups and creating word vectors before the actual matching process. This preprocessing step standardizes diverse requirement formats into uniform representations, enabling the system to handle poorly formed requirements and implicit relationships effectively. By preparing the data structure in advance, the system gains adaptability without incurring time penalties during the matching phase.
Data Source
AI summary
A computer-implemented method identifies textual statement relationships. Textual statement pairs including a first and second textual statement are identified, and parsed word group pairs are extracted from first and second textual statements. The parsed word groups are compared, and a parsed word score for each statement pair is calculated. Word vectors for the first and second textual statements are created and compared. A word vector score is calculated based on the comparison of the word vectors for the first and second textual statements. A match score is determined for the textual statement pair, with the match score being representative of at least one of the parsed word score and the word vector score.