Machine Learning WBS Creation for Consistent Project Customization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for creating a Work Breakdown Structure (WBS) in software development are hindered by the increasing complexity of work packages and varying quality characteristics, making it difficult to consistently incorporate customer requirements into the WBS within a limited time frame.

Innovation Solution

A machine learning apparatus that acquires and processes first, second, and third information to create associated information, using supervised and reinforcement learning to generate a general-purpose WBS, including ID management, terminology management, and WBS link tables.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If experts manually analyze requirements and create WBS from past project results, then the WBS can be customized to customer requirements, but the process takes too much time and lacks consistency in standard compliance

Engineering Contradiction:

Improvecustomization to customer requirementsVSAvoidtime for WBS creation

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system pre-processes and stores compliance standards, quality characteristics, and past project WBS data in structured formats before actual WBS creation. This preliminary organization of information allows the machine learning model to quickly retrieve and apply relevant standards during WBS generation, significantly reducing creation time while maintaining consistency.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the manual expert analysis process with an automated machine learning system. The ML model automatically analyzes customer requirements, retrieves relevant compliance standards, and generates WBS structures without human intervention, eliminating the time-consuming manual process while preserving the ability to customize to customer needs.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If the number of WBS work packages increases to cover all operations, then the WBS becomes more comprehensive, but the complexity of connection between work packages increases

Engineering Contradiction:

Improvecompleteness of WBS coverageVSAvoidcomplexity of WBS connections

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing the WBS creation process into distinct modules: requirement analysis, standard retrieval, work package generation, and connection establishment. Each module handles specific aspects independently, making the overall complex process more manageable and maintainable while ensuring comprehensive coverage of all operations.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The machine learning model serves as an intermediary that automatically establishes connections between work packages based on learned patterns from past projects and compliance standards. This intermediary intelligence reduces the manual effort required to manage complex connections while ensuring comprehensive and accurate inter-package relationships.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Stability of the object's composition

If learning is performed based only on standard information, then compliance consistency is improved, but appropriate WBS cannot be created without project-specific context

Engineering Contradiction:

Improveconsistency of standard complianceVSAvoidappropriateness of WBS for specific projects

Core Design Contradiction:

Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The patent merges multiple information sources including compliance standards, quality characteristics, past project WBS data, and current project requirements into a unified machine learning training dataset. This combination allows the model to learn both standard compliance patterns and project-specific contextual nuances, producing WBS that satisfy both consistency and appropriateness requirements.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The machine learning model is designed with multi-functionality to handle diverse input types (standards, requirements, past projects) and produce versatile output applicable to different project types. The model learns universal patterns from varied data sources while adapting to specific project contexts, enabling it to create appropriate WBS for different scenarios while maintaining standard compliance.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250225483A1Machine learning apparatus, WBS creation apparatus, and machine learning method

Publication Date: 2025.07.10 MITSUBISHI ELECTRIC CORP

AI summary

An object is to provide a technique capable of creating an appropriate general-purpose WBS. A machine learning apparatus includes an acquisition part and a learning control part. The acquisition part acquires first information regarding a WBS work package of standard, second information regarding a WBS work package of a project corresponding to the standard, and third information regarding a process diagnosis result of a project corresponding to the standard. The learning control part performs learning regarding a WBS work package based on the first information, the second information, and the third information, thereby creating associated information associating the first information, the second information, and the third information.