Landscape garden path design method based on artificial intelligence

Through the landscape park road design method based on artificial intelligence, the graph convolution neural network and the pix2pix model framework are used to dynamically adjust the weight, which solves the problems of insufficient data quantitative research and cumbersome design in landscape park road design, and improves the efficiency and accuracy of the design Improve the quality of garden road design.

CN119167558AInactive Publication Date: 2024-12-20SHANDONG YOUTH UNIV OF POLITICAL SCI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411233821.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-12-20
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The lack of quantitative research based on data in landscape garden road design leads to low reusability, cumbersome design process and waste of human resources. Traditional design ignores people's dynamic behavior and psychological feelings.

Method used

Using an artificial intelligence-based design method, by collecting and processing 400 landscape garden design map data, using graph convolution neural network for data enhancement, and building an improved pix2pix model framework, dynamically adjusting the weights to generate a garden design scheme, combined with Global wandering, label correlation and local subgraphs are used for data processing.

Benefits of technology

It improves the reliability and accuracy of the design, improves the generalization ability of the model, solves the problems of blurred boundaries and unclear regional segmentation, and achieves a more efficient design process and a better park design.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119167558A_ABST
    Figure CN119167558A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of landscape garden path design and application, and particularly relates to a landscape garden path design method based on artificial intelligence, which comprises the steps of envelope data collection, data processing, training set data enhancement, landscape garden path generation model establishment and landscape garden path design completion. According to the method, training set data is enhanced, a fusion type data enhancement strategy is built through a graph convolutional neural network, global migration, label correlation and local sub-graphs are respectively used for data enhancement, a weight calculation module is built and fusion is carried out, the learnability and diversity of samples are improved, and the generalization ability of the model is improved. According to the landscape garden path generation model, a framework based on an improved pix2pix model is built, and in a garden path output design scheme of a generator, dynamic weight adjustment is used to solve the problems of fuzzy boundary and unclear region segmentation.
Need to check novelty before this filing date? Find Prior Art