Multi-data source nl2sql system based on semantic rules and multi-dimensional model

Abstract

The invention discloses a multi-data source NL2SQL system based on semantic rules and multidimensional models, including a business layer for realizing NL2SQL, and the business layer includes: a configuration module for configuring matching rules; a data model building module for Build a data model that can use the table and field information of the database to generate SQL statements; the intention recognition module is used to parse and match the natural sentences according to the matching rules to obtain the table and field information of the database, and use the data model to generate executable The SQL statement. The system does not rely on labeled corpus and models, and can realize intent-based NL2SQL through simple interface configuration; the data model building module supports multi-choice nesting, which can be flexibly configured; the intent recognition module reduces the requirements for data sets and improves SQL Generated success rate. Therefore, by adopting the system provided by the present invention, business scenarios can be quickly constructed according to different projects.

Description

technical field [0001] The invention relates to the technical field of intelligent search, in particular to a multi-data source NL2SQL system based on semantic rules and multi-dimensional models. Background technique [0002] In intelligent search, the process of computers understanding user query intentions has become a research hotspot in the industry. Before understanding user intentions, it is first necessary to convert natural language into an executable program language that computers can understand and generate accurate statement semantics. Natural Language to SQL (NL2SQL) is a method to convert the user's natural language statement into a computer-readable, executable, and semantic representation that conforms to computer rules. [0003] At present, in NL2SQL technology, professional knowledge reserves are needed for dictionary configuration, and there are certain requirements for nlp and model training; in addition, its requirements for data sets are relatively high...

AI Technical Summary

Problems solved by technology

[0003] At present, in NL2SQL technology, professional knowledge reserves are needed for dictionary configuration, and there are certain requirements for nlp and model training; in addition, its requirements for data sets are relatively high, requiring a large number of well-marked training set corpus and test set corpus and rejection The model training process is complex and takes a long time

[0004] Therefore, the existing NL2SQL technology is difficult to promote and apply in actual use

Images