ML Traceability System for Work Item Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current software development techniques face challenges in correlating work items from various tools, leading to inefficient tracking of project progress, unsatisfied requirements, and the release of defective software products, which wastes computing resources and results in handling complaints and modifications.
Innovation Solution
A traceability system utilizing machine learning and natural language processing to cleanse and process work item data, identify synonyms, replace abbreviations, and determine mappings between work items from different tools, providing a confidence score for similarity, thus aiding in achieving traceability across the project lifecycle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual correlation of work items from various tools is performed, then traceability can be achieved, but it consumes excessive computing resources and time
Solution Approach 1:
The patent replaces manual mechanical correlation processes with automated machine learning models and natural language processing systems. The ML model automatically analyzes work item data, identifies relationships, and generates correlations without human intervention, thereby maintaining traceability accuracy while dramatically improving processing efficiency and reducing resource consumption.
Solution Approach 2:
The system enables self-service automation where the machine learning model independently processes work item data, performs cleansing, generates mappings, and produces traceability results without requiring manual intervention. The system serves itself by automatically improving its mappings through feedback mechanisms, reducing the need for external computational resources and human effort.
2Loss of information
If work item data from multiple tools is correlated without processing, then data completeness is maintained, but data quality and mapping accuracy deteriorate
Solution Approach 1:
The patent applies preliminary data cleansing and processing actions before the main correlation task. The system performs data validation, standardization, and preprocessing steps that prepare the data for accurate mapping. This preliminary action ensures that while data completeness is maintained, the quality and mapping accuracy are significantly improved through systematic preprocessing.
Solution Approach 2:
The patent introduces an intermediary machine learning model that acts as a mediator between raw work item data and final correlations. This intermediary layer processes the data through learned patterns and relationships, transforming raw data into accurate mappings while preserving information. The intermediary model bridges the gap between maintaining data completeness and achieving high mapping precision.
3Object-generated harmful factors
If traditional defect tracking methods are used, then defect identification is possible, but computing resources are wasted and defects are not efficiently reduced
Solution Approach 1:
The patent applies partial action by focusing computational resources only on the most critical analysis tasks rather than processing all data uniformly. The machine learning model identifies and focuses on key patterns and relationships that are most indicative of defects, performing excessive analysis only where needed. This approach efficiently reduces defects while minimizing unnecessary computing resource consumption.
Data Source
AI summary
A device may receive work item data identifying work items associated with requirements from different tools of a project and may perform data cleansing to remove and/or modify particular words from the work item data and to generate cleansed work item data. The device may perform natural language processing on the cleansed work item data to identify synonyms for words in the cleansed work item data and may replace abbreviations in the cleansed work item data with full form text to generate final work item data. The device may identify keywords in the final work item data and may process the final work item data, the synonyms, and the keywords, with a machine learning model, to identify mappings between work items of the final work item data and to determine a confidence score for the mappings. The device may perform actions based on the mappings and the confidence score.