SamDrishti

SamDrishti

Where citizen meets Transperency

SamDrishti

SamDrishti

Where citizen meets Transperency

The problem SamDrishti solves

This app bridges the gap between Government and Citizens, enhancing governance by bringing public issues and feedback closer to government authorities. It acts as a digital platform where citizens can raise complaints, understand policies, and provide feedback directly, creating a responsive loop between government bodies and the public.

Key features include:

  1. Citizen Chatbot: Allows users to report issues across various public sectors (electricity, water, roads) and direct them to relevant departments efficiently.

  2. Legal Document Summarizer: Condenses complex legal documents, enabling citizens and officials to quickly understand policy implications.

  3. Sentiment Analysis: Helps the government gauge public opinion on policies or events, supporting data-driven decision-making.

  4. Health Guidance: Provides preliminary health suggestions for common human and animal ailments, improving awareness, especially in underserved areas.

  5. Policy Feedback System: Enables citizens to share feedback on policies, allowing the government to make adjustments based on public needs.

By simplifying communication, increasing transparency, and enabling data-driven insights, this app empowers citizens and supports more effective governance, fostering a closer, more responsive relationship between citizens and government authorities.

Challenges we ran into

During development, we encountered several challenges. Integrating AI features into the app was complex, especially when connecting multiple components like the chatbot and sentiment analysis. One major hurdle was integrating the database with the chatbot, as we needed seamless interaction to handle citizen queries effectively. We resolved this by reworking our database schema and optimizing data flows to ensure smooth communication with the chatbot.

Another challenge was finding relevant datasets for training our machine learning models. This required extensive research and refinement to locate datasets that fit our use cases accurately.

Finally, the app’s complexity grew as we added features like document summarization, sentiment analysis, and health guidance, making development intricate. To manage this, we broke down tasks into smaller milestones, which allowed us to systematically test and integrate each feature, leading to a cohesive, functional app.

Tracks Applied (1)

Best Use of MongoDB Atlas

It uses MongoDB for storing data of user and also storing the complaints and services required.

Major League Hacking

Discussion