Construction Pattern Mining Algorithm for Massive Construction Plans

DOI

10.2991/978-94-6463-449-5_64How to use a DOI?

Keywords

Construction plan; construction pattern; data mining; serialization

Abstract

In a plethora of construction plans lie effective construction plans tailored to specific scenarios. When faced with new construction challenges, we often seek inspiration from historical construction plans, hoping to immediately derive effective solutions upon presenting construction problems. In the era of large-scale modeling, there is a growing desire for artificial intelligence models to learn effective problem-solving approaches from a vast array of construction plans. Prior to this, we need to process the massive volume of construction plans, abstracting and refining those that are effective for specific scenarios. We define these as “construction modes” and propose a Construction Plan Mining Algorithm (CPMA) aimed at extracting such modes from the vast collection of construction plans. The algorithm first serializes all documents and then employs a sequence expansion strategy to extend frequent items within the documents, generating new sequences. Utilizing a non-continuous pattern pruning strategy ensures the generation of only continuous sequences, thus maintaining the effectiveness of construction modes. Subsequently, a non-maximal pattern filtering strategy is used to filter the result set into maximal sequences, ensuring the integrity of sequence patterns. Through these three strategies, a continuous and maximal sequence pattern result set is generated. The algorithm was experimented on 1. 53 million words of publicly available construction plans, demonstrating that the construction mode mining process, with CPMA as its core, exhibits better operational efficiency and superior result outputs. This holds groundbreaking significance in the field of construction mode mining, while also providing insights and practical technological means to reduce redundancy in mining.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yu Liu
AU  - Lei Yan
AU  - Miao Li
PY  - 2024
DA  - 2024/06/30
TI  - Construction Pattern Mining Algorithm for Massive Construction Plans
BT  - Proceedings of the 2024 8th International Conference on Civil Architecture and Structural Engineering (ICCASE 2024)
PB  - Atlantis Press
SP  - 659
EP  - 665
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-449-5_64
DO  - 10.2991/978-94-6463-449-5_64
ID  - Liu2024
ER  -