FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model
With the rapid development of prominent models, NL2SQL has made many breakthroughs, but customers still hope that the accuracy of NL2SQL can be continuously improved through optimization. The method based on large models has brought revolutionary changes to NL2SQL. This paper innovatively proposes a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/1/12 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588399411724288 |
|---|---|
| author | Xiaozheng Du Shijing Hu Feng Zhou Cheng Wang Binh Minh Nguyen |
| author_facet | Xiaozheng Du Shijing Hu Feng Zhou Cheng Wang Binh Minh Nguyen |
| author_sort | Xiaozheng Du |
| collection | DOAJ |
| description | With the rapid development of prominent models, NL2SQL has made many breakthroughs, but customers still hope that the accuracy of NL2SQL can be continuously improved through optimization. The method based on large models has brought revolutionary changes to NL2SQL. This paper innovatively proposes a new NL2SQL method based on a large language model (LLM), which could be adapted to an edge-cloud computing platform. First, natural language is converted into Python language, and then SQL is generated through Python. At the same time, considering the traceability characteristics of financial industry regulatory requirements, this paper uses the open-source big model DeepSeek. After testing on the BIRD dataset, compared with most NL2SQL models based on large language models, EX is at least 2.73% higher than the original method, F1 is at least 3.72 higher than the original method, and VES is 6.34% higher than the original method. Through this innovative algorithm, the accuracy of NL2SQL in the financial industry is greatly improved, which can provide business personnel with a robust database access mode. |
| format | Article |
| id | doaj-art-291e3337dd1b4a28b3a10fe0cabc7c38 |
| institution | Kabale University |
| issn | 1999-5903 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-291e3337dd1b4a28b3a10fe0cabc7c382025-01-24T13:33:33ZengMDPI AGFuture Internet1999-59032025-01-011711210.3390/fi17010012FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language ModelXiaozheng Du0Shijing Hu1Feng Zhou2Cheng Wang3Binh Minh Nguyen4School of Computer Science, Fudan University, Shanghai 200438, ChinaSchool of Computer Science, Fudan University, Shanghai 200438, ChinaSchool of Artificial Intelligence, Shanghai Normal University Tianhua College, No. 1661 Shengxin North Road, Shanghai 201815, ChinaBusiness Analysis BU, GienTech Technology Co., Ltd., Shanghai 200232, ChinaSchool of Information and Communication Technology, Hanoi University of Science and Technology, No. 1 Dai Co Viet, Hai Ba Trung, Hanoi 100000, VietnamWith the rapid development of prominent models, NL2SQL has made many breakthroughs, but customers still hope that the accuracy of NL2SQL can be continuously improved through optimization. The method based on large models has brought revolutionary changes to NL2SQL. This paper innovatively proposes a new NL2SQL method based on a large language model (LLM), which could be adapted to an edge-cloud computing platform. First, natural language is converted into Python language, and then SQL is generated through Python. At the same time, considering the traceability characteristics of financial industry regulatory requirements, this paper uses the open-source big model DeepSeek. After testing on the BIRD dataset, compared with most NL2SQL models based on large language models, EX is at least 2.73% higher than the original method, F1 is at least 3.72 higher than the original method, and VES is 6.34% higher than the original method. Through this innovative algorithm, the accuracy of NL2SQL in the financial industry is greatly improved, which can provide business personnel with a robust database access mode.https://www.mdpi.com/1999-5903/17/1/12LLMNL2SQLpre-trainingpromptPython |
| spellingShingle | Xiaozheng Du Shijing Hu Feng Zhou Cheng Wang Binh Minh Nguyen FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model Future Internet LLM NL2SQL pre-training prompt Python |
| title | FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model |
| title_full | FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model |
| title_fullStr | FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model |
| title_full_unstemmed | FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model |
| title_short | FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model |
| title_sort | fi nl2py2sql financial industry nl2sql innovation model based on python and large language model |
| topic | LLM NL2SQL pre-training prompt Python |
| url | https://www.mdpi.com/1999-5903/17/1/12 |
| work_keys_str_mv | AT xiaozhengdu finl2py2sqlfinancialindustrynl2sqlinnovationmodelbasedonpythonandlargelanguagemodel AT shijinghu finl2py2sqlfinancialindustrynl2sqlinnovationmodelbasedonpythonandlargelanguagemodel AT fengzhou finl2py2sqlfinancialindustrynl2sqlinnovationmodelbasedonpythonandlargelanguagemodel AT chengwang finl2py2sqlfinancialindustrynl2sqlinnovationmodelbasedonpythonandlargelanguagemodel AT binhminhnguyen finl2py2sqlfinancialindustrynl2sqlinnovationmodelbasedonpythonandlargelanguagemodel |