Method and system for displaying a response to a natural language query

Patent metadata

Field	Value
Publication number	US-12443632-B2
Application number	US-202318140873-A
Country	US
Kind code	B2
Filing date	Apr 28, 2023
Priority date	Jan 24, 2023
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

A method and a system for displaying a response to at least one natural language query are disclosed. The method includes receiving the at least one natural language query. The method further includes analyzing, using a trained model, the at least one natural language query to identify an intent and entities associated with the at least one natural language query. The method further includes composing a database-specific query using the identified intent and entities associated with the at least one natural language query. The method includes executing the database-specific query to retrieve the response to the at least one natural language query from at least one database. The method further includes displaying, via a display, the response that is retrieved from the at least one database.

First claim

What is claimed is:

1. A method for displaying a response to at least one natural language query, the method being implemented by at least one processor, the method comprising:
receiving, by the at least one processor via a communication interface, at least one first natural language query from a user;
identifying, by the at least one processor via a query analyzer, an intent of the user regarding intended search results of the at least one first natural language query, wherein the query analyzer uses an artificial-intelligence-based model and a machine-learning-based, natural-language processing model that is trained on past queries for identifying intents and entities of past natural language queries;
identifying, by the at least one processor via the query analyzer, an entity associated with the at least one first natural language query, wherein the entity includes at least one keyword associated with a context of the at least one first natural language query;
automatically correcting, by the at least one processor using the artificial-intelligence-based model and the machine-learning-based, natural-language processing model, the at least one first natural language query to generate at least one second natural language query;
classifying, by the at least one processor, the entity into predetermined categories based on data stored in at least one database;
transmitting, by the at least one processor, the identified intent and entities associated with the at least one natural language query to a query composer;
automatically generating, by the at least one processor via the query composer, a database-specific query, based on the intent, the entities, and the at least one second natural language query;
transmitting, by the at least one processor, the database-specific query to an executive module;
automatically executing, by the at least one processor via the executive module, the database-specific query, wherein the executive module connects to the at least one database and runs the database-specific query in the at least one database to generate a plurality of results;
ranking, by the at least one processor and based on the identified intent, the plurality of results;
retrieving, by the at least one processor and based on the ranking of the plurality of results, a response to the database-specific query from the at least one database;
converting, by the at least one processor, the response to the database-specific query into a natural language response; and
displaying, by the at least one processor via a display, the natural language response.

2. The method as claimed in claim 1 , wherein the at least one first natural language query comprises at least one query received in a natural language using at least one querying command type that comprises an audio-based command, and wherein the audio-based command is converted to a text format via a speech-to-text converter.

3. The method as claimed in claim 1 , wherein the response that is retrieved from the at least one database is displayed in a form of a visual representation.

4. The method as claimed in claim 1 , wherein the at least one database comprises a plurality of responses associated with a plurality of queries stored in a language associated with the at least one database.

5. The method as claimed in claim 1 , further comprising automatically predicting, by the at least one processor using the trained model, the at least one second natural language query using an auto-correction feature.

6. A computing device configured to implement an execution of a method for displaying a response to at least one natural language query, the computing device comprising:
a processor;
a memory; and
a communication interface coupled to each of the processor and the memory,
wherein the processor is configured to:
receive, via the communication interface, at least one first natural language query from a user;
identify, via a query analyzer, an intent of the user regarding intended search results of the at least one first natural language query, wherein the query analyzer uses an artificial-intelligence-based model and a machine-learning-based, natural-language processing model that is trained on past queries for identifying intents and entities of past natural language queries;
identify, via the query analyzer, an entity associated with the at least one first natural language query, wherein the entity includes at least one keyword associated with a context of the at least one first natural language query;
automatically correct, via the artificial-intelligence-based model and the machine-learning-based, natural-language processing model, the at least one first natural language query to generate at least one second natural language query;
classify the entity into predetermined categories based on data stored in at least one database;
transmit the identified intent and entities associated with the at least one natural language query to a query composer;
automatically generate, via the query composer, a database-specific query, based on the intent, the entities, and the at least one second natural language query;
transmit the database-specific query to an executive module;
automatically execute, via the executive module, the database-specific query, wherein the executive module connects to the at least one database and runs the database-specific query in the at least one database to generate a plurality of results;
rank, based on the identified intent, the plurality of results;
retrieve, based on the ranking of the plurality of results, a response to the database-specific query from the at least one database;
convert the response to the database-specific query into a natural language response; and
display the natural language response.

7. The computing device as claimed in claim 6 , wherein the at least one first natural language query comprises at least one query received in a natural language using at least one querying command type that comprises an audio-based command, and wherein the audio-based command is converted to a text format via a speech-to-text converter.

8. The computing device as claimed in claim 6 , wherein the processor is further configured to display the response that is retrieved from the at least one database in a form of a visual representation.

9. The computing device as claimed in claim 6 , wherein the at least one database comprises a plurality of responses associated with a plurality of queries stored in a language associated with the at least one database.

10. The computing device as claimed in claim 6 , wherein the processor is further configured to automatically predict, using the trained model, the at least one second natural language query using an auto-correction feature.

11. A non-transitory computer readable storage medium storing instructions for displaying a response to at least one natural language query, the instructions comprising executable code which, when executed by a processor, causes the processor to:
receive the at least one first natural language query from a user;
identify, via a query analyzer, an intent of the user regarding intended search results of the at least one first natural language query, wherein the query analyzer uses an artificial-intelligence-based model and a machine-learning-based, natural-language processing model that is trained on past queries for identifying intents and entities of past natural language queries;
identify, via the query analyzer, an entity associated with the at least one first natural language query, wherein the entity includes at least one keyword associated with a context of the at least one first natural language query;
automatically correc

Assignees

• Jpmorgan Chase Bank Na

Inventors

• Kumar Sachin

Classifications

• G06F16/3344 Primary

  using natural language analysis · CPC title

• G06F16/338

  Presentation of query results · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G06F16/243

  Natural language query formulation · CPC title

• G06F16/3329 Primary

  Natural language query formulation · CPC title