Back to results
US 12,754,907 B2Granted
System and method for enhanced schema discovery and query generation
AssigneeIntuit Inc.
InventorsRachit Sengupta, Sivashanker Thiruchittampalam, Daniel Moise, Hui Chen, Daniel Li, Tharathorn Rimchala, Horace Chan, John Patrick Symborski
Life of this patent
Estimating the term…
Abstract
A system and method are provided for enhanced schema discovery and query generation.
Claims20
A computing system comprising:
- a processor;
- and
- a non-transitory computer-readable storage device storing computer-executable instructions, the instructions operable to cause the processor to perform operations comprising:
- chunking a supergraph into a plurality of chunks, each chunk comprising an attribute name, an attribute description, and a canonical attribute name;
- embedding the plurality of chunks into a vector database;
- receiving a natural language user query from a user device for generating a data query related to the supergraph;
- executing, based on the user query, a semantic search within the vector database to identify one or more attributes for generating the data query;
- extracting a canonical attribute name for each of the identified one or more attributes;
- generating a large language model (LLM) schema based on the extracted canonical attribute name;
- feeding the user query and the LLM schema to an LLM;
- generating a response to the user query via the LLM, the response comprising the data query or one or more attributes related to the data query;
- and
- causing the response to be displayed on the user device.
10 more elements
A computer-implemented method, performed by at least one processor, comprising:
- chunking a supergraph into a plurality of chunks, each chunk comprising an attribute name, an attribute description, and a canonical attribute name;
- embedding the plurality of chunks into a vector database;
- receiving a natural language user query from a user device for generating a data query related to the supergraph;
- executing, based on the user query, a semantic search within the vector database to identify one or more attributes for generating the data query;
- extracting a canonical attribute name for each of the identified one or more attributes;
- generating a large language model (LLM) schema based on the extracted canonical attribute name;
- feeding the user query and the LLM schema to an LLM;
- generating a response to the user query via the LLM, the response comprising the data query or one or more attributes related to the data query;
- and
- causing the response to be displayed on the user device.
7 more elements
Dependencies are inferred from the claim text.