Requirement Behavior Tree Construction from Assembly Drawings

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing requirement description tools in requirements engineering face challenges in converting text-based work instructions into structured data formats like tree structures due to variations in text formats across different suppliers, hindering the automation and efficiency of converting requirements into executable production systems.

Innovation Solution

A method and device for constructing a requirement behavior tree by pre-establishing regular pairings of mechanical drawings with assembly relationships, matching candidate pairings, and adding assembly process information to create a requirement behavior tree using behavior tree syntax, leveraging historical assembly data and mechanical drawings to automate the construction process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If text-based work instructions from different suppliers are used to describe requirements, then flexibility in requirement description is improved, but the difficulty of converting requirements into structured data formats increases

Engineering Contradiction:

Improveflexibility in requirement descriptionVSAvoiddifficulty of converting to structured data

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary system that includes a material bill parser, mechanical drawing extractor, and behavior tree constructor. This intermediary layer translates various text-based work instruction formats into a standardized structured format (behavior tree), resolving the contradiction between maintaining description flexibility and enabling systematic conversion to structured data.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual conversion of work instructions into structured data formats is performed, then accuracy of requirement representation is improved, but the time and labor required increases

Engineering Contradiction:

Improveaccuracy of requirement representationVSAvoidtime and labor for conversion

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-defining standard behavior tree structures, common assembly patterns, and standardized extraction rules for mechanical drawings. These pre-prepared templates and rules enable automatic conversion while maintaining accuracy, eliminating the need for manual conversion for each new requirement set.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the manual mechanical conversion process with an automated computer-based system that uses pattern recognition and rule-based extraction to convert work instructions into behavior trees automatically, significantly reducing time and labor while maintaining or improving accuracy through consistent application of conversion rules.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated conversion systems are implemented, then productivity in converting requirements is improved, but the complexity of the conversion system increases

Engineering Contradiction:

Improveconversion speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the automated conversion system into distinct modular components: a material bill parsing module, a mechanical drawing extraction module, a pattern matching module, and a behavior tree construction module. Each module handles a specific aspect of the conversion process, improving productivity through automation while managing system complexity through modular design that allows independent development and maintenance of each component.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12561649B2Method, device and storage medium for constructing requirement behavior tree

Publication Date: 2026.02.24 SIEMENS AG

AI summary

Various embodiments of the teachings herein include methods for constructing a requirement behavior tree. An example includes: receiving a material bill including names of parts involved in a current assembly; obtaining a mechanical drawing of each part in the material bill; establishing multiple candidate pairings based on obtained mechanical drawings, wherein each of the multiple candidate pairings is composed of mechanical drawings of two parts; matching each of the multiple candidate pairings with each of pre-established regular pairings and regarding candidate pairings each of which matches a regular paring as target candidate pairings; for each target candidate pairing, adding assembly process information of a regular pairing matching the target candidate pairing to the target candidate pairing; and based on the assembly process information of all target candidate pairings, constructing a requirement behavior tree corresponding to a whole assembly process of the current assembly according to behavior tree syntax.