| CPC G06F 16/243 (2019.01) [G06F 16/212 (2019.01); G06F 16/248 (2019.01)] | 20 Claims |
|
1. A data query system configured to intelligently generate structured data queries from natural language questions using large language models (LLMs), the data query system comprising:
a processor and a non-transitory computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform query generation operations which comprise:
receiving a first natural language question for a response to be provided based on structured data in a structured database system;
converting one or more words in the first natural language question to one or more first embeddings;
matching the one or more first embeddings to one or more pre-generated embeddings for pre-generated questions from a user questions repository (UQR), wherein the matching includes computing similarity scores between the one or more first embeddings and the one or more pre-generated embeddings using a similarity scoring operation that assess an accuracy of the matching;
determining that one or more of the similarity scores associated with the accuracy of the matching meets or exceeds a first threshold similarity;
determining, using an LLM and metadata corresponding to the pre-generated questions from the UQR, a structured data query for querying the structured database system for the structured data based on the similarity score;
querying the structured database system for the response to the first natural language question, wherein the response includes at least a portion of the structured data; and
outputting, in a user interface of an application associated with the UQR, the response to the first natural language question from the LLM.
|