View in EDS

自然语言生成多表SQL.查询语句技术研究.

Saved in:
Bibliographic Details
Title: 自然语言生成多表SQL.查询语句技术研究. (Chinese)
Alternate Title: Research on Technology of Generating Multi-table SQL Query Statement by Natural Language. (English)
Authors: 曹金超, 黄滔, 陈刚, 吴晓凡, 陈珂
Source: Journal of Frontiers of Computer Science & Technology; Jul2020, Vol. 14 Issue 7, p1133-1141, 9p
Abstract (English): Natural language generation of SQL queries is not only an important part of the construction of intelligent: energy database query system, but also a new type of power rail transit One of the difficulties in the personalized operation and maintenance of mixed-temporal big data for communication systems. Current use: The deep learning method of learning templates focuses on single-east SQL query in the database Query generation, unable to solve the multi-table SQL query generation in the database. Aiming at this body, a special method based on SQL statement template Column generation R Gu is transformed into multiple classification problems, and the dependence between different prediction components of SQL clauses is fully utilized in the process of training the deep learning model. relationship. In the generation of multi-table JOIN path of FROM clause, model it as Swana tree asking Zhao, and use a global optimal algorithm to perform Solve... The model and algorithm are verified on an open text-generated SQL data set Spider. The results show that the method can be taught. Improve the accuracy of query matching generated by multi-table SQL queries. [ABSTRACT FROM AUTHOR]
Abstract (Chinese): 自然语言生成SQL查询不仅是构建•智:能数据库查询系统的一个重要组成部分，亦是新型供电轨道交 通系统混合时态大数据个性化运维的难点之一。目前利用:深裒学习模盤的方法专注于数据库中单東SQL查 询生成，无法解决數据库中多表SQL查询生成。针对这个阿身，采用一特基于SQL语句模板填充的方法，将序 列生成R顧转化为多个分类问题, 在训练深處學习模型的过程中充分利用SQL子句不同预測成分之间的依赖 关系。在FROM子句的多表JOIN路径生成方面，将其建模为斯垣纳树问趙，采用一种全局最优的算法来进行 求解.。在一个开放的文本生成SQL数据集Spider上对模型和算法进行实蠢脸证/实蠢结果表明••该方法能有教 地提升多表SQL查询生成的查询匹配准确率. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:Natural language generation of SQL queries is not only an important part of the construction of intelligent: energy database query system, but also a new type of power rail transit One of the difficulties in the personalized operation and maintenance of mixed-temporal big data for communication systems. Current use: The deep learning method of learning templates focuses on single-east SQL query in the database Query generation, unable to solve the multi-table SQL query generation in the database. Aiming at this body, a special method based on SQL statement template Column generation R Gu is transformed into multiple classification problems, and the dependence between different prediction components of SQL clauses is fully utilized in the process of training the deep learning model. relationship. In the generation of multi-table JOIN path of FROM clause, model it as Swana tree asking Zhao, and use a global optimal algorithm to perform Solve... The model and algorithm are verified on an open text-generated SQL data set Spider. The results show that the method can be taught. Improve the accuracy of query matching generated by multi-table SQL queries. [ABSTRACT FROM AUTHOR]
ISSN:16739418
DOI:10.3778/j.issn.1673-9418.1908025