A three-dimensional part retrieval method and system based on graph similarity search

By constructing an edge-face connectivity graph and training a ranking model using a graph attention network, the problem of insufficient utilization of geometric and topological relationships in CAD models in existing technologies is solved, achieving efficient and accurate 3D part retrieval, suitable for rapid querying of large-scale CAD libraries.

CN121542482BActive Publication Date: 2026-06-23HEFEI ARTIFICIAL INTELLIGENCE & BIG DATA RES INST CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HEFEI ARTIFICIAL INTELLIGENCE & BIG DATA RES INST CO LTD
Filing Date
2025-11-28
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Existing technologies cannot fully utilize the geometric and design semantic information of computer-aided design (CAD) models and struggle to capture explicit topological relationships, resulting in low efficiency in 3D part retrieval.

Method used

A graph similarity-based search method is adopted. By constructing an edge-face connectivity graph, calculating the graph editing distance matrix, and training a ranking model using a graph attention network, the method directly processes the 3D data of CAD models, avoiding information loss caused by data conversion and achieving self-supervised learning.

Benefits of technology

It achieves efficient and accurate 3D part retrieval, avoids information loss caused by data conversion, improves retrieval efficiency and accuracy, and is suitable for rapid querying of large-scale CAD libraries.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121542482B_ABST
    Figure CN121542482B_ABST
Patent Text Reader

Abstract

The application provides a three-dimensional part retrieval method based on graph similarity search, relates to the field of computer graphics, and solves the technical problem that the prior art cannot fully utilize the geometry and design semantic information of CAD, and it is difficult to capture and display the topological relationship, resulting in low retrieval efficiency. The method comprises the following steps: obtaining part three-dimensional data of a computer-aided design (CAD) model, and constructing a training data set; constructing an edge-face connection graph based on the part three-dimensional data; calculating a graph edit distance (GED) matrix of all edge-face connection graphs in the training data set as a supervision signal; training a ranking model based on the GED matrix, mapping the edge-face connection graph to a hidden space, and constructing a part vector database according to the output graph-level embedding vector; the ranking model is constructed based on a graph attention network; inputting a CAD part to be queried into the trained ranking model to obtain a feature vector, performing nearest neighbor search in the part vector database, and returning a similar part result.
Need to check novelty before this filing date? Find Prior Art