Inspiration

The inspiration behind Dukaan-AI stemmed from the need to streamline shop management tasks for small businesses, leveraging the power of AI and automation.

What it does

Dukaan-AI is an innovative solution that transforms spoken order details into SQL commands, facilitating the management of shop purchases, ledgers, and debts. It automates the process of updating the shop's database, saving time and ensuring accuracy.

How we built it

We built Dukaan-AI using Google's Vertex AI Agent Builder. The solution integrates Speech-to-Text (STT) technology to capture spoken orders, parses the text to extract relevant information, and generates SQL INSERT statements to update the database in real-time.

Challenges we ran into

One of the main challenges we encountered was ensuring the accuracy and reliability of the speech recognition component, especially in noisy environments or with varying accents. Additionally, optimizing the SQL generation process to handle different order formats efficiently posed a significant technical hurdle.

Accomplishments that we're proud of

We're proud to have developed a functional prototype of Dukaan-AI within the constraints of the hackathon. Despite the challenges, we were able to create an AI-powered solution that has the potential to revolutionize how small shopkeepers manage their operations.

What we learned

Through this project, we gained valuable insights into leveraging AI and cloud technologies for practical applications in real-world scenarios. We honed our skills in natural language processing, database management, and AI model integration.

What's next for Dukaan-AI

In the future, we envision expanding Dukaan-AI to include advanced features such as notification reminders, inventory management, and predictive analytics. We also aim to enhance the user experience with a more intuitive interface and seamless integration with existing shop management systems.

Built With

Share this project:

Updates