Volume 4,Issue 6
基于预训练模型适配的烟草营销领域智能查询增强技术研究
针对XX 烟草企业营销数据孤岛严重、业务人员数据分析能力不强、需求响应迟缓等问题，本文结合业务需求及现有技术，提出融合湖仓一体架构与改进型NL2SQL 技术的查询增强方案，以满足企业技术需求。
[1] Gartner. Hype Cycle for Data Management, 2022[R]. Stamford: Gartner, 2022.
[2] Zaharia M, Ghodsi A, Xin R, et al. Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics[C]// Proceedings of the 11th Conference on Innovative Data Systems Research (CIDR). Online: www.cidrdb.org, 2021.
[3] Elizabeth M. Pierce, Song I Y. Dimensional modeling: Identification, classification, and evaluation of patterns[J]. Decision Support Systems, 2008, 45(1): 59-76.
[4] Wang B, Shin R, Liu X, et al. RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). Online: ACL, 2020: 7567-7578.
[5] Sun Z, Deng Z H, Nie J Y, Tang J. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space[C]// Proceedings of the 7th International Conference on Learning Representations (ICLR). New Orleans: OpenReview.net, 2019.
[6] Hu E J, Shen Y, Wallis P, et al. LoRA: Low-Rank Adaptation of Large Language Models[C]// Proceedings of the 10th International Conference on Learning Representations (ICLR). Online: OpenReview.net, 2022.