Method and system for automatic response to customer requests using artificial intelligence models

1 . A method for generating a response to a query, the method being implemented by at least one processor, the method comprising:

receiving, from a user, a first query;

analyzing the first query to determine a topic that is relevant to the first query;

publishing the first query to a topic queue that corresponds to the determined topic;

identifying a first generative artificial intelligence (AI) model that is configured to handle questions related to a first specific domain and that is trained by using data that corresponds to the determined topic;

submitting the first query to the first generative AI model;

receiving, from the first generative AI model, an answer to the first query;

storing the received answer to the first query in a semantic memory; and

transmitting, to the user, the received answer to the first query,

wherein the first generative AI model is configured to have access to an updatable knowledge base, such that when the first generative AI model is not immediately able to generate an answer to the first query, the method further comprises:

forwarding the first query to a second generative AI model that is configured to handle questions related to a second specific domain and to update the knowledge base and to retrieve newly obtainable data; and

using the first generative AI model to access the updated knowledge base in order to generate the answer to the first query.

2 . The method of claim 1 , wherein the second generative AI model is configured to retrieve the newly obtainable data from at least one from among an internet source, a document repository, and a database.

3 . The method of claim 1 , wherein the topic queue comprises a distributed messaging queue that includes a plurality of topic agents within which each respective topic agent corresponds to a different respective topic of interest.

4 . The method of claim 3 , further comprising: after the knowledge base has been updated, using a third generative AI model to initiate a re-indexing of the semantic memory within the plurality of topic agents based on the updated knowledge base.

5 . The method of claim 1 , further comprising performing a semantic search of the semantic memory to determine whether a query that is similar to the first query has previously been answered.

6 . The method of claim 5 , wherein the semantic memory is structured as a vector space in which each of a plurality of question-answer pairs is embedded using Sentence Transformers and stored.

7 . The method of claim 1 , further comprising tracking at least one from among a request latency metric that relates to an amount of elapsed time between the receiving of the first query and the transmitting of the answer to the first query and a semantic memory hit rate metric that relates to a percentage of received queries that are answerable by using the semantic memory without requiring submission to the first generative AI model.

8 . A computing apparatus for generating a response to a query, the computing apparatus comprising:

a processor;

a semantic memory; and

a communication interface coupled to each of the processor and the memory,

wherein the processor is configured to:

receive, from a user via the communication interface, a first query;

analyze the first query to determine a topic that is relevant to the first query;

publish the first query to a topic queue that corresponds to the determined topic;

identify a first generative artificial intelligence (AI) model that is configured to handle questions related to a first specific domain and that is trained by using data that corresponds to the determined topic;

submit the first query to the first generative AI model;

receive, from the first generative AI model, an answer to the first query;

store the received answer to the first query in the semantic memory; and

transmit, to the user via the communication interface, the received answer to the first query,

wherein the first generative AI model is configured to have access to an updatable knowledge base, such that when the first generative AI model is not immediately able to generate an answer to the first query, the processor is further configured to:

forward the first query to a second generative AI model that is configured to handle questions related to a second specific domain and to update the knowledge base and to retrieve newly obtainable data; and

use the first generative AI model to access the updated knowledge base in order to generate the answer to the first query.

9 . The computing apparatus of claim 8 , wherein the second generative AI model is configured to retrieve the newly obtainable data from at least one from among an internet source, a document repository, and a database.

10 . The computing apparatus of claim 8 , wherein the topic queue comprises a distributed messaging queue that includes a plurality of topic agents within which each respective topic agent corresponds to a different respective topic of interest.

11 . The computing apparatus of claim 10 , wherein the processor is further configured to: after the knowledge base has been updated, use a third generative AI model to initiate a re-indexing of the semantic memory within the plurality of topic agents based on the updated knowledge base.

12 . The computing apparatus of claim 8 , wherein the processor is further configured to perform a semantic search of the semantic memory to determine whether a query that is similar to the first query has previously been answered.

13 . The computing apparatus of claim 12 , wherein the semantic memory is structured as a vector space in which each of a plurality of question-answer pairs is embedded using Sentence Transformers and stored.

14 . The computing apparatus of claim 8 , wherein the processor is further configured to track at least one from among a request latency metric that relates to an amount of elapsed time between the receiving of the first query and the transmitting of the answer to the first query and a semantic memory hit rate metric that relates to a percentage of received queries that are answerable by using the semantic memory without requiring submission to the first generative AI model.

15 . A non-transitory computer readable storage medium storing instructions for generating a response to a query, the storage medium comprising executable code which, when executed by a processor, causes the processor to:

receive, from a user, a first query;

analyze the first query to determine a topic that is relevant to the first query;

publish the first query to a topic queue that corresponds to the determined topic;

identify a first generative artificial intelligence (AI) model that is configured to handle questions related to a first specific domain and that is trained by using data that corresponds to the determined topic;

submit the first query to the first generative AI model;

receive, from the first generative AI model, an answer to the first query;

store the received answer to the first query in a semantic memory; and

transmit, to the user, the received answer to the first query,

wherein the first generative AI model is configured to have access to an updatable knowledge base, such that when the first generative AI model is not immediately able to generate an answer to the first query, the executable code is further configured to cause the processor to:

forward the first query to a second generative AI model that is configured to handle questions related to a second specific domain and to update the knowledge base and to retrieve newly obtainable data; and

use the first generative AI model to access the updated knowledge base in order to generate the answer to the first query.

16 . The storage medium of claim 15 , wherein the topic queue comprises a distributed messaging queue that includes a plurality of topic agents within which each respective topic agent corresponds to a different respective topic of interest.

17 . The storage medium of claim 16 , wherein the executable code is further configured to cause the processor to: after the knowledge base has been updated, use a third generative AI model to initiate a re-indexing of the semantic memory within the plurality of topic agents based on the updated knowledge base.