ReportEase

Landing Page
Crime-Analytics Dashboard
Extracted Text via OCR from provided sample
IPC & CrPC Suggestions along with CCTNS Database
FAQs
Video Demo on Website

Inspiration

Our mission is to harness the power of AI to decode legal complexities, automate processes, and improve judicial efficiency, ultimately paving the way for a more equitable and accessible justice system.

What it does

ReportEase is an Automated Legal Insight Project that uses Mistral AI, an open source Large Language Model (LLM) finetuned on IPC & CrPC Datasets, to analyze First Information Reports (FIRs) and generate insightful reports. The application also allows users to search the Crime and Criminal Tracking Network and Systems (CCTNS) database for relevant information.

Features: Upload PDF or image files of FIRs and extract the text using optical character recognition (OCR) with the help of Tesseract. Generate IPC and CrPC suggestions based on the situation extracted from the given prompt. Download the generated report as PDF files for further use or sharing. Search the CCTNS database using accused name and valid identity proof and get the results stating whether they are a repeating offender. Visualize the data of CCTNS in a dashboard format with the help of graphs and charts.

How we built it

We built ReportEase using a combination of different technologies and frameworks. We used React.js and Tailwind CSS for the frontend, Node.js and Express.js for the backend, and Flask API for the communication between the frontend and the backend. We also used Tesseract.js and Pdf-Poppler for the OCR and text extraction, and Mistral AI for the LLM suggestions. Finally, we used Git and GitHub for version control and collaboration.

Challenges we ran into

Visualization and Integration of CCTNS data was a major hassle as the data was not provided, so we had to make a dummy dataset which would mirror the real CCTNS data. Along with that, The tesseract OCR being used for OCR Scanning was also having troubles scanning pdfs which had filters on pages, but we overcame that by popping out the pages as separate images and scanning them efficiently with the help of parallel processing.

Accomplishments that we're proud of

We are proud of creating a web application that can automate the legal analysis of FIRs and generate insightful reports. We are also proud of integrating the CCTNS database and providing a search and visualization feature for the users. We think that our project can help the police and the public in accessing and understanding the legal aspects of FIRs and crime data.

What we learned

We learned a lot of new skills and concepts while working on this project. We learned how to use OCR and text extraction to process PDF and image files, and how to use LLM to generate IPC and CrPC suggestions. We also learned how to use Flask API to connect the frontend and the backend, and how to use Axios API to fetch data from the CCTNS database. We also learned how to use Chart.js to create interactive charts and graphs for data visualization. We also learned how to work as a team and use Git and GitHub for collaboration.

What's next for ReportEase

We have some ideas for improving and expanding our project in the future. Some of them are:

Adding more features and functionalities to the report generation, such as highlighting the important sections and providing a probability of how fake the report could be by using sentiment analysis.
Deploying the web application to a cloud platform, such as Azure or AWS, and making it available to a wider audience.