The invention belongs to the technical field of large models, and particularly relates to an
SQL (Structured
Query Language)
conversion method,
system and equipment based on a
large model and a storage medium. The technical problem that in the prior art, errors in
SQL query statements are difficult to effectively verify and repair, and consequently the
SQL conversion and generation accuracy of related technologies is low is solved. Comprising the following steps: analyzing a
natural language of a user, identifying and mapping SQL skeleton components to a predefined Python
action function, and generating an initial action sequence; and then, the sequence is verified through a detection tool, if an error is found, error information is fed back to the
large model to correct the sequence, detection is cyclically carried out until the sequence passes or reaches the maximum number of iterations, and a final action sequence is output. And if no error exists, directly outputting. And finally, switching the final sequence to an SQL splicing mode, executing each
action function to obtain SQL clause fragments, and performing character string splicing to generate a complete SQL
query statement.