Enhancing Policy Generation with GraphRAG and YouTube Data: A Logistics Case Study
Збережено в:
| Опубліковано в:: | Electronics vol. 14, no. 7 (2025), p. 1241 |
|---|---|
| Автор: | |
| Інші автори: | |
| Опубліковано: |
MDPI AG
|
| Предмети: | |
| Онлайн доступ: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Теги: |
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3188813064 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2079-9292 | ||
| 024 | 7 | |a 10.3390/electronics14071241 |2 doi | |
| 035 | |a 3188813064 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231458 |2 nlm | ||
| 100 | 1 | |a Naganawa, Hisatoshi |u Faculty of Ocean Science and Technology, Kobe University, Kobe 658-0022, Japan | |
| 245 | 1 | |a Enhancing Policy Generation with GraphRAG and YouTube Data: A Logistics Case Study | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Graph-based retrieval-augmented generation (GraphRAG) represents an innovative advancement in natural language processing, leveraging the power of large language models (LLMs) for complex tasks such as policy generation. This research presents a GraphRAG model trained on YouTube data containing keywords related to logistics issues to generate policy proposals addressing these challenges. The collected data include both video subtitles and user comments, which are used to fine-tune the GraphRAG model. To evaluate the effectiveness of this approach, the performance of the proposed model is compared to a standard generative pre-trained transformer (GPT) model. The results show that the GraphRAG model outperforms the GPT model in most prompts, highlighting its potential to generate more accurate and contextually relevant policy recommendations. This study not only contributes to the evolving field of LLM-based natural language processing (NLP) applications but also explores new methods for improving model efficiency and scalability in real-world domains like logistics policy making. | |
| 651 | 4 | |a Japan | |
| 653 | |a Working hours | ||
| 653 | |a Shortages | ||
| 653 | |a Large language models | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Truck drivers | ||
| 653 | |a Structural equation modeling | ||
| 653 | |a Task complexity | ||
| 653 | |a Questionnaires | ||
| 653 | |a Well being | ||
| 653 | |a Supply & demand | ||
| 653 | |a Logistics | ||
| 653 | |a Natural language processing | ||
| 653 | |a Data collection | ||
| 653 | |a Trucking industry | ||
| 653 | |a Case studies | ||
| 653 | |a Statistical analysis | ||
| 700 | 1 | |a Hirata, Enna |u Graduate School of Maritime Sciences, Kobe University, Kobe 658-0022, Japan | |
| 773 | 0 | |t Electronics |g vol. 14, no. 7 (2025), p. 1241 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3188813064/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3188813064/fulltextwithgraphics/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3188813064/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch |