Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68849
Volume:
10 |
11 |
Nov 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Science(Data Science)
SJB Institute of Technology

Department of Computer Science(Data Science)
SJB Institute of technology

Department of Computer Science(Data Science)
SJB Institute of technology
Associate Professor,Department of Computer Science(Data Science)
SJB Institute of Technology
Residents of Karnataka have access to various welfare programs, but many are unaware of which ones they qualify for.The requirements and necessary documents for each scheme vary and are distributed across different departments and online portals.The platforms we examined depend on information provided directly by citizens.This paper introduces a recommendation system for Karnataka Government welfare schemes and outlines the methods it uses: image enhancement and OCR, field extraction, LLM-assisted drafting of scheme guidelines, rule-based eligibility verification, and privacy-focused management of personal information.The system is designed to analyze citizen documents locally, let them verify the extracted details, and compare them against rules approved by human experts.It provides only the schemes the citizen is eligible for, along with a list of any missing documents and the official application link.For each step, we evaluate common approaches and highlight their limitations.We also mention the challenges we identified: maintaining up-to-date rules, OCR accuracy for Kannada and handwritten text, legal considerations around Aadhaar data, and the fact that the system is still in development and has not undergone evaluation yet.
KEYWORDS
A Karnataka citizen often has to find the right department, read the conditions and gather the right certificates before any benefit arrives. A document-driven recommender aims to remove much of that effort for Karnataka beneficiaries: it reads the documents they already hold, shows only the schemes they appear to qualify for, names the certificates still missing and links to the official application page. The survey showed that doing this reliably is mostly a data-quality problem, namely turning noisy documents into a correct profile and unstructured scheme text into correct rules. We compared the main options for OCR, extraction, rule drafting, eligibility reasoning and privacy, and described how the proposed system combines them: local open-source processing of citizen documents, citizen confirmation of the extracted profile, human-approved and versioned rules, deterministic and explainable evaluation, and minimal storage of identity data. The system is still under development, so the next step is to build it out and report measured results for every stage, using Karnataka scheme rules and test profiles.
[1]R. Smith, “An overview of the Tesseract OCR engine,” in Proc. 9th Int. Conf. Document Analysis and Recognition (ICDAR), 2007, pp. 629–633. [2]Surya OCR, open-source software for OCR, layout analysis and reading order, GitHub. https://github.com/datalab-to/surya, version 2.0.0 (accessed Oct. 17, 2026). [3]U. Zaratiana et al., “GLiNER: Generalist model for named entity recognition using bidirectional transformer,” in Proc. NAACL, 2024; arXiv:2311.08526. [4]A. Dubey et al., “The Llama 3 herd of models,” arXiv:2407.21783, 2024. [5]J. Verhoeff, Error Detecting Decimal Codes, Mathematical Centre Tract 29, Mathematisch Centrum, Amsterdam, 1969. [6]H. Krawczyk, M. Bellare and R. Canetti, “HMAC: Keyed-hashing for message authentication,” RFC 2104, 1997. [7]N. Provos and D. Mazieres, “A future-adaptable password scheme,” in Proc. USENIX Annual Technical Conf., 1999. [8]A. Biryukov, D. Dinu, D. Khovratovich and S. Josefsson, “Argon2 memory-hard function for password hashing and proof-of-work applications,” RFC 9106, 2021. [9]M. Jones, J. Bradley and N. Sakimura, “JSON Web Token (JWT),” RFC 7519, 2015. [10]Government of India, The Digital Personal Data Protection Act, 2023.
Publication Date
11/9/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...