Shuqin Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shuqin Shi has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Aiguo Zhang
School of Computer and Information Engineering , Xiamen University of Technology , Xiamen 361024 , Fujian , China , xmut.edu.cn
1 shared publication - Chenfei Wang
School of Civil Engineering and Architecture , Xiamen University of Technology , Xiamen 361024 , Fujian , China , xmut.edu.cn
1 shared publication - Jiaqin Shen
Xiamen Chengzhi New Materials Technology Co., Ltd. , Xiamen 361006 , China
1 shared publication - Kai Zhang
Xiamen Jiehang Engineering Testing Technology Co., Ltd. , Xiamen 361006 , China
1 shared publication - Yuehui Chen
Xiamen Hordor Architecture and Engineering Design Group Co., Ltd. , Xiamen 361006 , China
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Wiley in Advances in Civil Engineering
- Vol. 2026 (1) , 8953677
A Knowledge Service System for Foundation Pit Engineering Based on LoRA and RAG
Foundation pit engineering involves a complex system of technical standards. Yet practitioners often struggle to retrieve relevant provisions and interpret them efficiently during construction decision‐making. To address these challenges, this paper presents a knowledge service system that integrates low‐rank adaptation (LoRA) with retrieval‐augmented generation (RAG). Based on 35 national and industry standards, we constructed a dataset of more than 8000 high‐quality question–answer pairs. LoRA was adopted for parameter‐efficient domain fine‐tuning, and RAG was incorporated to support real‐time retrieval and source attribution of regulatory provisions. In a comprehensive evaluation on 487 test items (including both subjective and objective questions), the system achieved an overall accuracy of 82.93%, gaining 16.38 and 11.15 percentage points over the pure fine‐tuned model and the pure RAG model, respectively. The average response time was 1.98 s, compared with 3.65 s for the pure RAG model, thereby satisfying the real‐time response requirements for on‐site decision support. This study developed a prototype system using open‐source frameworks, which supports offline inference and multiformat document processing in an experimental setting, thus demonstrating the feasibility and practical viability of the proposed architecture. This work offers a scalable knowledge service solution for foundation pit engineering and provides a generalizable framework for deploying large language models (LLMs) in other knowledge‐intensive engineering domains.
- 1 January 2026
- Published by Wiley in Advances in Civil Engineering
- Vol. 2026 (1) , 8953677
Open AccessA Knowledge Service System for Foundation Pit Engineering Based on LoRA and RAG
Foundation pit engineering involves a complex system of technical standards. Yet practitioners often struggle to retrieve relevant provisions and interpret them efficiently during construction decision‐making. To address these challenges, this paper presents a knowledge service system that integrates low‐rank adaptation (LoRA) with retrieval‐augmented generation (RAG). Based on 35 national and industry standards, we constructed a dataset of more than 8000 high‐quality question–answer pairs. LoRA was adopted for parameter‐efficient domain fine‐tuning, and RAG was incorporated to support real‐time retrieval and source attribution of regulatory provisions. In a comprehensive evaluation on 487 test items (including both subjective and objective questions), the system achieved an overall accuracy of 82.93%, gaining 16.38 and 11.15 percentage points over the pure fine‐tuned model and the pure RAG model, respectively. The average response time was 1.98 s, compared with 3.65 s for the pure RAG model, thereby satisfying the real‐time response requirements for on‐site decision support. This study developed a prototype system using open‐source frameworks, which supports offline inference and multiformat document processing in an experimental setting, thus demonstrating the feasibility and practical viability of the proposed architecture. This work offers a scalable knowledge service solution for foundation pit engineering and provides a generalizable framework for deploying large language models (LLMs) in other knowledge‐intensive engineering domains.