US 2026/0288713 A1Published application

System and method for hybrid query orchestration for complex queries

AssigneeTata Consultancy Services Limited

InventorsShruti Kunal KUNDE, Mayank MISHRA, Ravi Kumar SINGH, Kuldeep SINGH, Manoj Karunakaran NAMBIAR, Rekha SINGHAL

Life of this patent

Estimating the term…

Loading patent…

Abstract

Existing systems face challenges of efficiently handling complex, multi-source queries in enterprise applications. The present disclosure generates a response to the user's Natural Query Language (NLQ) by decomposing the NLQ into sub-queries. Sub-queries related to database are converted into SQL queries and sub-queries related to policy documents are processed using Graph RAG. The data retrieved from database and policy contexts are combined and sent along with NLQ to LLM, which generates the response. On the other hand, the NLQ is sent to Graph RAG for retrieving context, which is combined with database schema, and passed to LLM to assess whether additional database context is required. If needed, LLM generates SQL query which is executed to fetch data. The retrieved database context, Graph RAG context along with NLQ are sent to LLM to generate the response.

Claims20

Dependent claims

A processor implemented method, comprising:

receiving, via one or more hardware processors, an input comprising (i) one or more natural language queries (NLQ) from a user;
and (ii) one or more database schema contexts associated with the one or more NLQ from one or more structured data sources and one or more unstructured data sources;
generating, via the one or more hardware processors, a prompt using the received input;
decomposing, via the one or more hardware processors, the received one or more NLQ into one or more subqueries by sending the generated prompt to one or more Large Language Models (LLMs);
converting, via the one or more hardware processors, the one or more subqueries into a first set of Structured Query Language (SQL) queries, if the one or more subqueries contain information specific to a database;
converting, via the one or more hardware processors, the one or more subqueries into a first set of subqueries, if the one or more subqueries contain information specific to one or more documents;
retrieving, via the one or more hardware processors, a first set of data pertaining to the first set of SQL queries comprised in the database by executing the first set of SQL queries on the database;
retrieving, via the one or more hardware processors, a context pertaining to the first set of subqueries, by executing the first set of subqueries on a Graph RAG (Retrieval Augmented Generation);
combining, via the one or more hardware processors, (i) the retrieved first set of data pertaining to the first set of SQL queries, (ii) the retrieved context pertaining to the first set of subqueries along with the received one or more NLQ;
and
generating, via the one or more hardware processors, a response for the user by sending the combined data comprising (i) the retrieved first set of data pertaining to the first set of SQL queries, (ii) the retrieved context pertaining to the first set of subqueries along with the received one or more NLQ to the one or more LLMs.

8 more elements

A system, comprising:

a memory storing instructions;
one or more communication interfaces;
and
one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
receive an input comprising (i) one or more natural language queries (NLQ) from a user;
and (ii) one or more database schema contexts associated with the one or more NLQ from one or more structured data sources and one or more unstructured data sources;
generate a prompt using the received input;
decompose the received one or more NLQ into one or more subqueries by sending the generated prompt to one or more Large Language Models (LLMs);
convert the one or more subqueries into a first set of Structured Query Language (SQL) queries, if the one or more subqueries contain information specific to a database;
convert the one or more subqueries into a first set of subqueries, if the one or more subqueries contain information specific to one or more documents;
retrieve a first set of data pertaining to the first set of SQL queries comprised in the database by executing the first set of SQL queries on the database;
retrieve a context pertaining to the first set of subqueries, by executing the first set of subqueries on a Graph RAG (Retrieval Augmented Generation);
combine (i) the retrieved first set of data pertaining to the first set of SQL queries, (ii) the retrieved context pertaining to the first set of subqueries along with the received one or more NLQ;
and
generate a response for the user by sending the combined data comprising (i) the retrieved first set of data pertaining to the first set of SQL queries, (ii) the retrieved context pertaining to the first set of subqueries along with the received one or more NLQ to the one or more LLMs.

12 more elements

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

receiving an input comprising (i) one or more natural language queries (NLQ) from a user;
and (ii) one or more database schema contexts associated with the one or more NLQ from one or more structured data sources and one or more unstructured data sources;
generating a prompt using the received input;
decomposing the received one or more NLQ into one or more subqueries by sending the generated prompt to one or more Large Language Models (LLMs);
converting the one or more subqueries into a first set of Structured Query Language (SQL) queries, if the one or more subqueries contain information specific to a database;
converting the one or more subqueries into a first set of subqueries, if the one or more subqueries contain information specific to one or more documents;
retrieving a first set of data pertaining to the first set of SQL queries comprised in the database by executing the first set of SQL queries on the database;
retrieving a context pertaining to the first set of subqueries, by executing the first set of subqueries on a Graph RAG (Retrieval Augmented Generation);
combining (i) the retrieved first set of data pertaining to the first set of SQL queries, (ii) the retrieved context pertaining to the first set of subqueries along with the received one or more NLQ;
and
generating a response for the user by sending the combined data comprising (i) the retrieved first set of data pertaining to the first set of SQL queries, (ii) the retrieved context pertaining to the first set of subqueries along with the received one or more NLQ to the one or more LLMs.

8 more elements

Dependencies are inferred from the claim text.