System and method for providing personalized explainable response by generating multimedia prompt using contextual information

A system for providing personalized explainable response 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 from a user a multimedia user query, wherein the multimedia user query is received in at least one of a form comprising a text query, an image query, an audio query, a video query, and combination thereof;
• validate the multimedia user query relates to agricultural domain by computing a query relevancy score, wherein the query relevancy score with a low value triggers to terminate the process and receives a new multimedia user query, and the query relevancy score with a high value triggers to extract contextual data;
• extract a contextual data from the multimedia user query using at least one Artificial Intelligence (AI) model, wherein the contextual data includes an agricultural field information, an environmental conditions of the agriculture field, and activities performed by the user in the agricultural field;
• obtain a query insights from the multimedia user query using at least one AI model or Natural Language Processing (NLP) based techniques;
• obtain for the multimedia user query one or more relevant indicators from a knowledge graph based on the contextual data, and the query insights;
• generate a personalized context for the multimedia user query using the contextual data and the one or more relevant indicators;
• query a predefined prompt library comprising a plurality of baseline prompts to retrieve one or more matching prompts for the personalized context, wherein each prompt in the prompt library comprise a tagged category based on the context, topic, keywords, and domain specificity;
• generate using a context and domain aware generative AI model a personalized context aware prompt when no desired prompt is identified in the prompt library for the multimedia user query, wherein the personalized context aware prompt is generated using the plurality of baseline prompts, the query insights, and the personalized context;
• transmit the personalized context aware prompt to a plurality of large language models (LLMs) to obtain one or more responses;
• validate the one or more responses received for the personalized context aware prompt from the plurality of large language models to identify response based on similarity matching and iterative refinement;
• predict a contextually relevant user profile to compose the response suitable to the multimedia user query;
• generate a personalized explainable response for the multimedia user query based on the response, contextually relevant user profile, and storing the multimedia user query with corresponding personalized explainable response in a blockchain platform and the prompt library;
• and
• trigger to receive a feedback form from the user for the personalized explainable response.

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 from a user a multimedia user query, wherein the multimedia user query is received in at least one of a form comprising a text query, an image query, an audio query, a video query, and combination thereof;
• validating the multimedia user query relates to agricultural domain by computing a query relevancy score, wherein the query relevancy score with a low value triggers to terminate the process and receives a new multimedia user query, and the query relevancy score with a high value triggers to extract contextual data;
• extracting a contextual data from the multimedia user query using at least one Artificial Intelligence (AI) model, wherein the contextual data includes an agricultural field information, an environmental conditions of the agriculture field, and activities performed by the user in the agricultural field;
• obtaining a query insights from the multimedia user query using at least one AI model or Natural Language Processing (NLP) based techniques;
• obtaining for the multimedia user query one or more relevant indicators from a knowledge graph based on the contextual data, and the query insights;
• generating a personalized context for the multimedia user query using the contextual data and the one or more relevant indicators;
• querying a predefined prompt library comprising a plurality of baseline prompts to retrieve one or more matching prompts for the personalized context, wherein each prompt in the prompt library comprise a tagged category based on the context, topic, keywords, and domain specificity;
• generating using a context and domain aware generative AI model a personalized context aware prompt when no desired prompt is identified in the prompt library for the multimedia user query, wherein the personalized context aware prompt is generated using the plurality of baseline prompts, the query insights, and the personalized context;
• transmitting the personalized context aware prompt to a plurality of large language models (LLMs) to obtain one or more responses;
• validating the one or more responses received for the personalized context aware prompt from the plurality of large language models to identify response based on similarity matching and iterative refinement;
• predicting a contextually relevant user profile to compose the response suitable to the multimedia user query;
• generating a personalized explainable response for the multimedia user query based on the response, contextually relevant user profile, and storing the multimedia user query with corresponding personalized explainable response in a blockchain platform and the prompt library;
• and
• triggering to receive a feedback form from the user for the personalized explainable response.