Correspondence Relationship Determination for CAD Line Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining correspondence relationships between line segments in CAD drawings require a large amount of training data, which is often not available, especially when designing similar products, leading to inaccurate automatic dimensioning and increased workload due to manual corrections.
Innovation Solution
A computer-readable medium storing a correspondence relationship determination program that uses two machine learning models to infer individual figure information and relative relationships between line segments, reducing the need for extensive training data by determining correspondence relationships between line segments in past and newly created figure data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods for determining correspondence relationships between line segments are used, then accurate dimensioning can be achieved, but a large amount of training data is required which is often not available
Solution Approach 1:
The patent segments the correspondence relationship determination into two distinct machine learning models: one for inferring individual line segment features and another for inferring relative relationships between line segments. This segmentation allows each model to be trained on smaller, more focused datasets, reducing the overall training data requirement while maintaining determination accuracy.
Solution Approach 2:
The patent transitions from a single-model approach to a multi-model architecture, adding a dimensional aspect to the system design. By introducing separate models for individual features and relative relationships, the system can leverage different training data dimensions, reducing dependency on large amounts of comprehensive training data.
2Productivity
If existing methods are used without sufficient training data, then the dimensioning accuracy deteriorates, but this leads to increased manual corrections and workload
Solution Approach 1:
The patent performs preliminary inference of individual line segment features before determining relative relationships. This preliminary action allows the system to prepare processed information that reduces the complexity of subsequent relationship determination, improving overall accuracy even with limited training data and reducing manual correction needs.
Solution Approach 2:
The first machine learning model acts as an intermediary between the input figure data and the second machine learning model. It processes individual line segment features and passes them to the second model, which then determines relative relationships. This intermediary structure enables accurate dimensioning with reduced training data requirements.
Data Source
AI summary
A computer-readable recording medium stores a correspondence relationship determination program for causing a computer to execute a process. The process includes: acquiring, using a first machine learning model that infers individual figure information regarding one line segment in a first plurality of line segments included in first figure data and a second machine learning model that infers information regarding a relative relationship between the one line segment in the first plurality of line segments and another line segment in the first figure data, an inference result of each of a plurality of items that includes the individual figure information and the information regarding the relative relationship; and determining correspondence relationships between the first plurality of line segments and a second plurality of line segments included in second figure data different from the first figure data based on the inference result of each of the plurality of items.