International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | JuriBot: An AI-Powered Legal Document Analysis and Advisory System |
|---|---|
| ABSTRACT | JuriBot is an AI-powered legal document analysis and advisory system designed to reduce the time and effort required in handling complex legal texts. It uses natural language processing and machine learning to interpret, classify, and summarize unstructured documents such as contracts, case records, and judicial reports. The system can identify clauses, extract entities like names, dates, and statutes, and generate context-aware summaries. Its advisory module recommends relevant precedents and similar cases using similarity scoring and retrieval techniques. Built on transformer models such as BERT and LegalBERT, JuriBot offers deep understanding of legal language. Delivered through a secure web interface with search and upload features, it aims to improve research speed, accuracy, and accessibility while supporting, not replacing, human legal expertise for professionals, researchers, and institutions seeking efficient, scalable, intelligent legal assistance daily use. |
| AUTHOR | AYUSH RAUT, MOHIT KHAIRNAR, MITESH SHETYE, TEJAS SHIRSATH, PROF. MONICA SHETTY Students, Dept. of Information Technology, Atharva College of Engineering, Maharashtra, India Project Guide, Dept. of Information Technology, Atharva College of Engineering, Maharashtra, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404022 |
| pdf/22_JuriBot An AI-Powered Legal Document Analysis and Advisory System.pdf | |
| KEYWORDS | |
| References | [1] M. M. Rahman, N. G. Md, and M. M. Rahman, “Natural Language Processing in Legal Document Analysis Software: A Systematic Review of Current Approaches, Challenges, and Opportunities,” International Journal of Innovative Research and Scientific Studies, Vol. 8, No. 3, pp. 5026–5042, 2025. [2] S. Ajay Mukund et al., “Optimizing Legal Text Summarization Through Dynamic Retrieval-Augmented Generation and Domain-Specific Adaptation,” IEEE Conference Publication | Recent Trends in Legal AI, May 2025. [3] J. K. Verma et al., “Context-Aware Legal Summarization Using Reinforcement Learning,” in 2025 2nd International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), IEEE, Ghaziabad, India, 2025. [4] A. Bouhouche et al., “Predicting the Duration of Judicial Cases Using Hybrid Systems Based on Language Models,” International Journal of Advanced Computer Science and Applications, Vol. 16, No. 1, 2025. [5] Peddarapu et al., “DocSum: A Universal PDF Summarizer Using ASP.NET Core for Professional Legal Insights,” Journal of AI and Law, February 2025. [6] S. Gao and W. Liao, “Transformer-Based Models for Automatic Legal Case Summarization: A Comparative Study of T5 and BART,” Artificial Intelligence and Law, Vol. 29, No. 4, pp. 567–588, 2024. |
