Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910918397394944 |
|---|---|
| author | Hou, Shuyang Zhao, Anqi Liang, Jianyuan Shen, Zhangxiao Wu, Huayi |
| author_facet | Hou, Shuyang Zhao, Anqi Liang, Jianyuan Shen, Zhangxiao Wu, Huayi |
| contents | The rise of spatiotemporal data and the need for efficient geospatial modeling have spurred interest in automating these tasks with large language models (LLMs). However, general LLMs often generate errors in geospatial code due to a lack of domain-specific knowledge on functions and operators. To address this, a retrieval-augmented generation (RAG) approach, utilizing an external knowledge base of geospatial functions and operators, is proposed. This study introduces a framework to construct such a knowledge base, leveraging geospatial script semantics. The framework includes: Function Semantic Framework Construction (Geo-FuSE), Frequent Operator Combination Statistics (Geo-FuST), and Semantic Mapping (Geo-FuM). Techniques like Chain-of-Thought, TF-IDF, and the APRIORI algorithm are utilized to derive and align geospatial functions. An example knowledge base, Geo-FuB, built from 154,075 Google Earth Engine scripts, is available on GitHub. Evaluation metrics show a high accuracy, reaching 88.89% overall, with structural and semantic accuracies of 92.03% and 86.79% respectively. Geo-FuB's potential to optimize geospatial code generation through the RAG and fine-tuning paradigms is highlighted. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20975 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models Hou, Shuyang Zhao, Anqi Liang, Jianyuan Shen, Zhangxiao Wu, Huayi Software Engineering Artificial Intelligence Databases The rise of spatiotemporal data and the need for efficient geospatial modeling have spurred interest in automating these tasks with large language models (LLMs). However, general LLMs often generate errors in geospatial code due to a lack of domain-specific knowledge on functions and operators. To address this, a retrieval-augmented generation (RAG) approach, utilizing an external knowledge base of geospatial functions and operators, is proposed. This study introduces a framework to construct such a knowledge base, leveraging geospatial script semantics. The framework includes: Function Semantic Framework Construction (Geo-FuSE), Frequent Operator Combination Statistics (Geo-FuST), and Semantic Mapping (Geo-FuM). Techniques like Chain-of-Thought, TF-IDF, and the APRIORI algorithm are utilized to derive and align geospatial functions. An example knowledge base, Geo-FuB, built from 154,075 Google Earth Engine scripts, is available on GitHub. Evaluation metrics show a high accuracy, reaching 88.89% overall, with structural and semantic accuracies of 92.03% and 86.79% respectively. Geo-FuB's potential to optimize geospatial code generation through the RAG and fine-tuning paradigms is highlighted. |
| title | Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models |
| topic | Software Engineering Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2410.20975 |