Project Requirement Routing Using ML Department Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack an efficient method to identify and assign responsible departments for project requirements, making it difficult to create effective implementation plans.
Innovation Solution
A project support system utilizing a machine learning model, specifically a deep learning model, to identify responsible departments based on requirement data, leveraging pre-trained models and updated through human correction and department database information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of responsible departments is used, then accuracy of department assignment can be maintained through human judgment, but time consumption and human effort increase significantly
Solution Approach 1:
The patent replaces the manual mechanical process of department identification with an automated machine learning system. The processing unit automatically analyzes requirement data and identifies responsible departments using trained models, eliminating the need for manual human judgment while maintaining high accuracy through sophisticated algorithms.
Solution Approach 2:
The system enables self-service automation where the machine learning model independently performs the department identification task without requiring human intervention. The model processes requirement data autonomously and generates department assignments, making the system self-sufficient for this specific function.
2Productivity
If automated department identification is implemented, then time consumption is reduced and productivity increases, but accuracy may deteriorate without human judgment
Solution Approach 1:
The system performs preliminary action by pre-training machine learning models using historical data and domain knowledge before actual deployment. This pre-training phase establishes the foundation for accurate automated department identification, ensuring the model is prepared and calibrated before processing real project requirements.
Solution Approach 2:
The system implements feedback mechanisms where the machine learning model continuously learns from its predictions and corrections. By incorporating feedback from actual project outcomes and manual corrections when provided, the model improves its accuracy over time while maintaining high productivity through automated processing.
3Ease of operation
If simple matching algorithms are used, then system complexity is reduced and ease of operation improves, but measurement precision of department identification deteriorates
Solution Approach 1:
The patent employs a universal machine learning framework that can handle multiple types of requirement data and identify different departments across various project domains. This multi-functional approach maintains system simplicity while achieving high precision through the adaptability of the trained models to different scenarios.
4Measurement precision
If comprehensive analysis of requirement data is performed, then accuracy of department identification improves, but device complexity and computational resources increase
Solution Approach 1:
The system utilizes parameter changes by adjusting the complexity and depth of data analysis based on the specific requirements and context of each project. The machine learning model can dynamically modify its analysis parameters to achieve optimal accuracy while managing computational resources efficiently.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A project support system (10) includes at least one processor configured to execute a first process (s1) of acquiring requirement data (100) recording information on a requirement content required in a project, and a second process (s2) of identifying a responsible department that is highly relevant to the requirement content recorded in the requirement data (100).