Page 177 - 《软件学报》2026年第3期

1140 软件学报 2026 年第 37 卷第 3 期

6 总结与展望

本文提出了一种基于大语言模型的空间数据库自然语言查询转换方法 NALSpatial, 支持基础空间查询、范围
查询、最近邻居查询、空间 Join 查询和聚合查询. NALSpatial 的架构主要分为两个核心模块: 自然语言理解和可
执行语言生成. 首先, 通过应用知识库和基于大语言模型构建的语料库, 提取出关键实体和查询类型. 然后, 根据查
询类型选择结构化语言模型, 将实体映射到模型中构造数据库可执行语言. 实验结果表明, NALSpatial 能够有效地
将空间数据自然语言查询转换为可执行的数据库查询语句. 本文所提方法主要聚焦于文本形式的自然语言查询,
未来可以探索多模态数据的自然语言查询, 如结合语音或图像的查询解析.

References
[1] Liu ZD, Lin WX, Wu KS. A spatial structure matching algorithm for large spatial-textual datasets. Chinese Journal of Computers, 2022,
45(6): 1261–1275 (in Chinese with English abstract). [doi: 10.11897/SP.J.1016.2022.01261]
[2] Yu J, Sarwat M. GEOSPARKVIZ: A cluster computing system for visualizing massive-scale geospatial data. The VLDB Journal, 2021,
30(2): 237–258. [doi: 10.1007/S00778-020-00645-2]
[3] Xie J, Chen Z, Liu JW, Wang F, Li FF, Chen ZD, Liu YP, Cai SL, Fan ZH, Xiao F, Chen Y. Ganos: A multidimensional, dynamic, and
scene-oriented cloud-native spatial database engine. Proc. of the VLDB Endowment, 2022, 15(12): 3483–3495. [doi: 10.14778/3554821.
3554838]
[4] Güting RH, Behr T, Düntgen C. SECONDO: A platform for moving objects database research and for publishing and integrating research
implementations. IEEE Data Engineering Bulletin, 2010, 33(2): 56–63.
[5] Hori K, Sasaki Y, Amagata D, Murosaki Y, Onizuka M. Learned spatial data partitioning. In: Proc. of the 6th Int’l Workshop on
Exploiting Artificial Intelligence Techniques for Data Management. Seattle: ACM, 2023. 3. [doi: 10.1145/3593078.3593932]
[6] Zardbani F, Mamoulis N, Idreos S, Karras P. Adaptive indexing of objects with spatial extent. Proc. of the VLDB Endowment, 2023,
16(9): 2248–2260. [doi: 10.14778/3598581.3598596]
[7] Lin XC, Wei KM, Li ZT, Chen JP, Pei TR. Aggregation-based dual heterogeneous task allocation in spatial crowdsourcing. Frontiers of
Computer Science, 2024, 18(6): 186605. [doi: 10.1007/S11704-023-3133-6]
[8] Manning CD, Surdeanu M, Bauer J, Finkel JR, Bethard S, Mcclosky D. The Stanford CoreNLP natural language processing toolkit. In:
Proc. of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Baltimore: ACL, 2014.
55–60. [doi: 10.3115/V1/P14-5010]
[9] Algamdi S, Albanyan A, Shah SK, Tariq Z. Twitter accounts suggestion: Pipeline technique spaCy entity recognition. In: Proc. of the
2022 IEEE Int’l Conf. on Big Data. Osaka: IEEE, 2022. 5121–5125. [doi: 10.1109/BIGDATA55660.2022.10020570]
[10] Potočár M, Kvet M. Comparison of unigram, HMM, CRF and Brill’s part-of-speech taggers available in NLTK library. In: Proc. of the
33rd Conf. of Open Innovations Association. Zilina: IEEE, 2023. 226–235. [doi: 10.23919/FRUCT58615.2023.10143061]
[11] Qi P, Zhang YH, Zhang YH, Bolton J, Manning CD. Stanza: A Python natural language processing toolkit for many human languages. In:
Proc. of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. ACL, 2020. 101–108.
[doi: 10.18653/V1/2020.ACL-DEMOS.14]
[12] Li SC, Wang ZQ, Zhou GD. LLM enhanced cross domain aspect-based sentiment analysis. Ruan Jian Xue Bao/Journal of Software,
2025, 36(2): 644–659 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/7156.htm [doi: 10.13328/j.cnki.jos.007156]
[13] Kim H, So BH, Han WS, Lee H. Natural language to SQL: Where are we today? Proc. of the VLDB Endowment, 2020, 13(10):
1737–1750. [doi: 10.14778/3401960.3401970]
[14] Popescu AM, Etzioni O, Kautz H. Towards a theory of natural language interfaces to databases. In: Proc. of the 8th Int’l Conf. on
Intelligent User Interfaces. Miami: ACM, 2003. 149–157. [doi: 10.1145/604045.604070]
[15] Li F, Jagadish HV. Understanding natural language queries over relational databases. ACM SIGMOD Record, 2016, 45(1): 6–13. [doi: 10.
1145/2949741.2949744]
[16] Pan X, Xu SH, Cai XR, Wen YL, Yuan XJ. Survey on deep learning based natural language interface to database. Journal of Computer
Research and Development, 2021, 58(9): 1925–1950 (in Chinese with English abstract). [doi: 10.7544/issn1000-1239.2021.20200209]
[17] Guo JQ, Zhan ZC, Gao Y, Xiao Y, Lou JG, Liu T, Zhang DM. Towards complex text-to-SQL in cross-domain database with intermediate
representation. In: Proc. of the 57th Conf. of the Association for Computational Linguistics. Florence: ACL, 2019. 4524–4535. [doi: 10.
18653/V1/P19-1444]
[18] Brunner U, Stockinger K. ValueNet: A natural language-to-SQL system that learns from database information. In: Proc. of the 37th IEEE
Int’l Conf. on Data Engineering. Chania: IEEE, 2021. 2177–2182. [doi: 10.1109/ICDE51399.2021.00220]
[19] Kordjamshidi P. Spatial and temporal reasoning with LLMs for natural language comprehension and grounding. In: Proc. of the 2nd Int’l