Method and system for generating intent responses through virtual agents
A method and system for generating a response through a virtual agent is provided herein. The method comprises receiving information associated with a plurality of themes and topics. The method further comprises creating a knowledgebase based on the information received. The method further comprises analyzing the knowledgebase based on an intent identified, using an Artificial Intelligence (AI) model. Further, the method comprises generating a response corresponding to the intent through the virtual agent based on analyzation.
1 . A computer-implemented method for generating a response through a virtual agent, the computer-implemented method comprising:
receiving information associated with a plurality of themes and topics;
creating a knowledgebase based on the information received;
identifying an intent from a user input using an Artificial Intelligence (AI) model;
analyzing, by the AI model, the knowledgebase based on the intent identified from the user input, wherein analyzing the knowledgebase comprises:
retrieving, via an integrated application programming interface (API), supplemental information from one or more external sources, the external sources comprising at least one of real-time data feeds, supplementary articles, or domain-specific knowledge repositories;
combining the supplemental information retrieved from the external sources with the knowledgebase information;
determining a plurality of responses corresponding to the intent based on the combined information; and
providing one or more optimal responses selected from the plurality of responses, as recommendations to the virtual agent; and
generating the response corresponding to the intent through the virtual agent based on the recommendations of the one or more optimal responses.
2 . The computer-implemented method of claim 1 , further comprising:
receiving, by the virtual agent, a query from a user;
determining, by the virtual agent, the intent associated with the query; and
generating, by the virtual agent, the response based on the intent for the query.
3 . The computer-implemented method of claim 1 , wherein the knowledgebase corresponds to a knowledge bank of documents.
4 . The computer-implemented method of claim 1 , wherein the plurality of themes and topics are modeled in a graph-based structure in the knowledgebase.
5 . The computer-implemented method of claim 1 , wherein the plurality of topics and themes are extracted from conversation history between at least one of two or more human agents, two or more users, or at least one human agent and at least one user.
6 . The computer-implemented method of claim 1 , wherein the AI model is a Large Language Model (LLM).
7 . The computer-implemented method of claim 6 , further comprising:
preprocessing training datasets comprising textual data; and
generating a plurality of tokens from the training datasets, wherein the plurality of tokens comprises words and sub-words.
8 . The computer-implemented method of claim 7 , further comprising training the LLM based on the plurality of tokens to learn patterns, relationships, and representations of language, and wherein the LLM generates the response based on the learned patterns, relationships, and representations of language.
9 . The computer-implemented method of claim 1 , wherein the intent corresponds to at least one of a new intent or an existing intent, and wherein the new intent is associated with a new query, and the existing intent is associated with a repeated query.
10 . A computer system for generating a response through a virtual agent comprising, the computer system comprising: one or more computer processors, one or more computer readable memories, one or more computer readable storage devices, and program instructions stored on the one or more computer readable storage devices for execution by the one or more computer processors via the one or more computer readable memories, the program instructions comprising:
receiving information associated with a plurality of themes and topics;
creating a knowledgebase based on the information received;
identifying an intent from a user input using an Artificial Intelligence (AI) model;
analyzing, by the AI model, the knowledgebase based on the intent identified from the user input, wherein analyzing the knowledgebase comprises:
retrieving, via an integrated application programming interface (API), supplemental information from one or more external sources, the external sources comprising at least one of real-time data feeds, supplementary articles, or domain-specific knowledge repositories;
combining the supplemental information retrieved from the external sources with the knowledgebase information;
determining a plurality of responses corresponding to the intent based on the combined information; and
providing one or more optimal responses selected from the plurality of responses, as recommendations to the virtual agent; and
generating the response corresponding to the intent through the virtual agent based on the recommendations of the one or more optimal responses.
11 . The computer system of claim 10 , further comprising:
receiving, by the virtual agent, a query from a user;
determining, by the virtual agent, the intent associated with the query; and
generating, by the virtual agent, the response based on the intent for the query.
12 . The computer system of claim 10 , wherein the knowledgebase corresponds to a knowledge bank of documents.
13 . The computer system of claim 10 , wherein the plurality of themes and topics are modeled in a graph-based structure in the knowledgebase.
14 . The computer system of claim 10 , wherein the plurality of topics and themes are extracted from conversation history between at least one of two or more human agents, two or more users, or at least one human agent and at least one user.
15 . The computer system of claim 10 , wherein the AI model is a Large Language Model (LLM).
16 . The computer system of claim 15 , further comprising:
preprocessing training datasets comprising textual data; and
generating a plurality of tokens from the training datasets, wherein the plurality of tokens comprises words and sub-words.
17 . The computer system of claim 16 , further comprising training the LLM based on the plurality of tokens to learn patterns, relationships, and representations of language, and wherein the LLM generates the response based on the learned patterns, relationships, and representations of language.
18 . The computer system of claim 10 , wherein the intent corresponds to at least one of a new intent or an existing intent, and wherein the new intent is associated with a new query, and the existing intent is associated with a repeated query.
19 . A non-transitory computer-readable storage medium having stored thereon computer executable instructions which, when executed by one or more processors, cause the one or more processors to carry out operations for generating a response through a virtual agent, the operations comprising:
receiving information associated with a plurality of themes and topics;
creating a knowledgebase based on the information received;
identifying an intent from a user input using an Artificial Intelligence (AI) model;
analyzing, by the AI model, the knowledgebase based on the intent identified from the user input, wherein analyzing the knowledgebase comprises:
retrieving, via an integrated application programming interface (API), supplemental information from one or more external sources, the external sources comprising at least one of real-time data feeds, supplementary articles, or domain-specific knowledge repositories;
combining the supplemental information retrieved from the external sources with the knowledgebase information;
determining a plurality of responses corresponding to the intent based on the combined information; and
providing one or more optimal responses selected from the plurality of responses, as recommendations to the virtual agent; and
generating the response corresponding to the intent through the virtual agent based on the recommendations of the one or more optimal responses.