Home / Current Issue / Paper 1716197
Smart Doc: AI-Powered Contextual Knowledge Assistant
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: https://doi.org/10.64388/IREV9I10-1716197
Abstract
The increasing amount of unstructured data has posed problems with respect to their proper processing and retrieving information from them. Various attempts have been made by researchers to find answers through AI and NLP approaches such as document summarization, speech-to-text conversion, and semantic search techniques. Yet, the existing approaches are limited to single-source approaches, meaning that none of them is capable of dealing with multiple sources. In this paper, we will use Smart Doc: AI-Powered Contextual Knowledge Assistant, which can be considered as an integrated approach for the processing of multiple sources of data, such as documents, video transcripts of YouTube videos, and comments. We leverage the potential of semantic embedding and the RAG technique to process multiple sources of data. Smart Doc demonstrates high accuracy and effectiveness compared to traditional methods based on keyword matching.
Keywords
Retrieval augmented generation (RAG), Natural Language Processing, YouTube transcript analysis, Semantic search
References
[1] A. K. Maiya, G. S., A. R. V., and N. S. C., "YouTube Transcript Summarization Using Abstractive and Extractive Approaches," Proceedings of the 2024 2nd International Conference on Advances in Information Technology (ICAIT), 2024.
[2] “Paper presented at ICISS 2025”, Proc. 2025 Int. conf. on intelligent systems and smart systems, 2025.doi:10.1109/ICISS63372.2025.11076484
[3] S.A.A Rizvi, S.R. Javed, and M. A. Hashmani, “Document AI: Benchmarks, models and applications,” arXiv preprint arXiv:2111.08609, 2021
[4] S. Tay., M. Dehghani, D. Bahri, and D. Metzler, “Efficient transformers: A survey,” arXiv preprint arXiv:2009.06732,2020
How to cite this paper
@article{1716197,
author = {Shilpa K S, Pratibha H G , Sadhana S R , Sahana D M, Soniya Komal V},
title = {Smart Doc: AI-Powered Contextual Knowledge Assistant},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {1191-1198},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1716197.pdf},
abstract = {The increasing amount of unstructured data has posed problems with respect to their proper processing and retrieving information from them. Various attempts have been made by researchers to find answers through AI and NLP approaches such as document summarization, speech-to-text conversion, and semantic search techniques. Yet, the existing approaches are limited to single-source approaches, meaning that none of them is capable of dealing with multiple sources. In this paper, we will use Smart Doc: AI-Powered Contextual Knowledge Assistant, which can be considered as an integrated approach for the processing of multiple sources of data, such as documents, video transcripts of YouTube videos, and comments. We leverage the potential of semantic embedding and the RAG technique to process multiple sources of data. Smart Doc demonstrates high accuracy and effectiveness compared to traditional methods based on keyword matching.},
keywords = {Retrieval augmented generation (RAG), Natural Language Processing, YouTube transcript analysis, Semantic search},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1716197}
}