Methods, systems, and devices for adjusting a user query in requesting information from a knowledge graph database

1 . A device, comprising:

a processing system including a processor; and

a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:

obtaining a first user query and a second user query to access information from a group of knowledge graph databases, wherein the first user query corresponds to first user-generated input, wherein the second user query corresponds to second user-generated input;

identifying a first group of terms within the first user query and identifying a second group of terms within the second user query that reduces a likelihood of identifying a match within the group of knowledge graph databases, wherein the first group of terms comprises a first group of ambiguities and the second group of terms comprises a second group of ambiguities;

adjusting the first user query by removing the first group of ambiguities resulting in a first adjusted user query that enables identifying a first knowledge graph database from the group of knowledge graph databases;

adjusting the second user query by removing the second group of ambiguities resulting in a second adjusted user query that enables identifying a second knowledge graph database from the group of knowledge graph databases;

determining that the second adjusted user query matches a cached user query stored in a cache resulting in a first determination;

based on the first determination, accessing a cached user query response associated with the cached user query;

providing the cached user query response to a communication device associated with a user;

determining a group of named entities within the first adjusted user query resulting in a second determination;

based on the second determination, identifying the first knowledge graph database from the group of knowledge graph databases based on the first adjusted user query resulting in an identified knowledge graph database; and

generating a first database query utilizing a large language model based on the first adjusted user query and the first knowledge graph database, the first database query having a computer-readable syntax compatible with the identified knowledge graph database.

2 . The device of claim 1 , wherein the operations comprise:

requesting a first database query response from the identified knowledge graph database according to the first database query; and

obtaining the first database query response from the identified knowledge graph database based on the first database query.

3 . The device of claim 2 , wherein the operations comprise:

determining the first database query response satisfies a response criteria resulting in a third determination; and

generating a first user query response based on the first database query response and the third determination.

4 . The device of claim 3 , wherein the operations comprise providing the first user query response to the communication device associated with the user.

5 . The device of claim 2 , wherein the operations comprise determining that the first database query response does not satisfy a response criteria resulting in a fourth determination.

6 . The device of claim 5 , wherein the operations comprise:

adjusting the first adjusted user query utilizing the large language model based on the fourth determination resulting in a third adjusted user query; and

generating a second database query from based on the third adjusted user query and the identified knowledge graph database.

7 . The device of claim 6 , wherein the adjusting of the first adjusted user query comprises performing error-correcting on the first adjusted user query based on the fourth determination.

8 . The device of claim 6 , wherein the operations comprise:

requesting a second database query response from the identified knowledge graph database according to the second database query; and

obtaining the second database query response from the identified knowledge graph database based on the second database query.

9 . The device of claim 8 , wherein the operations comprise:

determining the second database query response satisfies the response criteria resulting in a third determination; and

generating a second user query response based on the second database query response and the third determination.

10 . The device of claim 9 , wherein the operations comprise providing the second user query response to the communication device associated with the user.

11 . The device of claim 1 , wherein the computer-readable syntax is associated with a Cypher database query language.

12 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:

obtaining a first user query and a second user query to access information from a group of knowledge graph databases;

identifying a first group of terms within the first user query and identifying a second group of terms within the second user query that reduces a likelihood of identifying a match within the group of knowledge graph databases, wherein the first group of terms comprises a first group of ambiguities and the second group of terms comprises a second group of ambiguities;

adjusting the first user query by removing the first group of ambiguities resulting in a first adjusted user query that enables identifying a first knowledge graph database from the group of knowledge graph databases;

adjusting the second user query by removing the second group of ambiguities resulting in a second adjusted user query that enables identifying a second knowledge graph database from the group of knowledge graph databases;

determining that the second adjusted user query matches a cached user query stored in a cache resulting in a first determination;

based on the first determination, accessing a cached user query response associated with the cached user query;

providing the cached user query response to a communication device associated with a user;

determining a group of named entities within the first adjusted user query resulting in a second determination;

based on the second determination, identifying the first knowledge graph database from the group of knowledge databases based on the first adjusted user query resulting in an identified knowledge graph database; and

converting the first adjusted user query to a database query utilizing a large language model based on the identified knowledge graph database.

13 . The non-transitory machine-readable medium of claim 12 , wherein the operations comprise:

requesting a database query response from the identified knowledge graph database according to the database query; and

obtaining the database query response from the identified knowledge graph database based on the database query.

14 . The non-transitory machine-readable medium of claim 13 , wherein the operations comprise:

determining the database query response satisfies a response criteria resulting in a determination; and

generating a user query response based on the database query response and the determination.

15 . The non-transitory machine-readable medium of claim 14 , wherein the operations comprise providing the user query response to the communication device associated with the user.

16 . The non-transitory machine-readable medium of claim 12 , wherein the first user query corresponds to user-generated input.

17 . The non-transitory machine-readable medium of claim 12 , wherein the database query comprises computer-readable syntax compatible with the identified knowledge graph database.

18 . The non-transitory machine-readable medium of claim 17 , wherein the computer-readable syntax is associated with a Cypher database query language.

19 . A method comprising:

obtaining, by a processing system including a processor, a first user query and a second user query to access information from a group of knowledge graph databases;

identifying, by the processing system, a first group of terms within the first user query and identifying, by the processing system, a second group of terms within the second user query that reduces a likelihood of identifying a match with the group of knowledge graph databases, wherein the first group of terms comprises a first group of ambiguities and the second group of terms comprises a second group of ambiguities;

adjusting, by the processing system, the first user query by removing the first group of ambiguities resulting in first adjusted user query that enables identifying a first knowledge graph database from the group of knowledge graph databases;

adjusting, by the processing system, the second user query by removing the second group of ambiguities resulting in a second adjusted user query that enables identifying a second knowledge graph database from the group of knowledge graph databases;

determining, by the processing system, that the second adjusted user query matches a cached user query stored in a cache resulting in a first determination;

based on the first determination, accessing, by the processing system, a cached user query response associated with the cached user query;

providing, by the processing system, the cached user query response to a communication device associated with a user;

determining, by the processing system, a group of named entities within the first adjusted user query resulting in a second determination;

based on the second determination, identifying, by the processing system, the first knowledge graph database from the group of knowledge databases based on the first adjusted user query resulting in an identified knowledge graph database; and

generating, by the processing system, a database query utilizing a large language model based on the first adjusted user query and the identified knowledge graph database.

20 . The method of claim 19 , wherein the generating of the database query comprises converting the first adjusted user query to the database query having a computer-readable syntax compatible with the identified knowledge graph database.