Scribd
Upload
22 views6 pages

SIH2024 IDEA Presentation Format

The document outlines a proposal for the Smart India Hackathon 2024, focusing on enhancing the Rail Madad complaint management system using AI-powered solutions. The proposed solution includes automated complaint categorization, predictive maintenance, and a multilingual chatbot, all aimed at improving passenger experience and operational efficiency. The technical feasibility, economic viability, and expected social impact of the project are also discussed, emphasizing cost reduction and increased inclusivity.

Uploaded by

milarem130
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
22 views6 pages

SIH2024 IDEA Presentation Format

The document outlines a proposal for the Smart India Hackathon 2024, focusing on enhancing the Rail Madad complaint management system using AI-powered solutions. The proposed solution includes automated complaint categorization, predictive maintenance, and a multilingual chatbot, all aimed at improving passenger experience and operational efficiency. The technical feasibility, economic viability, and expected social impact of the project are also discussed, emphasizing cost reduction and increased inclusivity.

Uploaded by

milarem130
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

SMART INDIA HACKATHON 2024

TITLE PAGE

• Problem Statement ID – 1711

• Problem Statement Title- Enhancing Rail

Madad with Al-powered Complaint Management.

• Theme – Smart Automation

• PS Category- Software

• Team ID - 11760

• Team Name (Registered on portal) - Seeders


Seeders PROPOSED SOLUTION
IDEA / SOLUTION Predictive maintenance integration using
Automated categorization via multi-class image/video sequence pattern analysis using Markov
classification using computer vision. chain model to identify recurring issues and
Validating complaints using metadata analysis by help departments to be one step ahead
extracting data from images via OCR. through the insights received from the
visualized data.
Three types of priority level, P1 being the high-priority
Monitoring of model performance for
issues like Medical emergency,Security,etc. while P2 and
evaluation such as Speed of complaint
P3 are for recurring issues and others. This Priority level registration and resolution.
is determined by the weights of the complaints.
Automated response using pre-trained model for chatbot. UNIQUE VALUE PROPOSITION
Training the Llama language model on our dataset for Automated call to TTR and appropriate
fine-tuning it to our case. department for higher priority complaints.
Integration of LIVE train status API for ease
Routing of complaints by integrating LIVE train status routing of complaints for on-train passengers.
API for Level-1 priority complaints for on-train passengers Incentives for staffs/Officials/Admins to evaluate
to alert the next sudden station. For off-train department's involvement.
passengers, the complaints will be routed to the Chatbot with Multilingual support.
appropriate department. Tackling network issues while on the train through
bandwidth optimization.
Sentiment analysis is done on the data collected from Crowd-Source Based priority system.
user feedback to improve the model by BERT
LangModel.
@SIH Idea submission- Template 2
Seeders TECHNICAL APPROACH
Technology stack
● Frontend (UI/UX):
○ React, Astro, GraphQL(client-side API)

● Backend (API & Server-side Logic):


○ Node.js, RESTful API, Python

● Database:
○ PostgreSQL, MongoDB

● Model Development (AI/ML Integration):


○ TensorFlow, Hugging Face, Keras,
LangChain, OpenCV

● Monitoring and Observability:


○ Grafana, Prometheus

● Cloud and Infrastructure:


○ Docker, LLAMA (Meta AI)
Product status
Demo link:
@SIH Idea submission- Template 3
Seeders FEASIBILITY AND VIABILITY
Technical Feasibility Economic Viability
With a minimal GUI, leveraging pre-trained Automation reduces manual processing, cutting
models for image/video analysis, OCR, and operational costs and improving long-term
chatbots, and utilizing readily available cloud efficiency.
services and AI APIs.
The team has expertise in AI and automation, Operational Viability
ensuring smooth implementation, and Predictive maintenance minimizes downtime,
application can be easily integrated with existing while multi-language support broadens
systems. accessibility.

Financial Feasibility
The development cost is virtually zero,
considering the server infrastructure is already in
place.

@SIH Idea submission- Template 4


Seeders IMPACT AND BENEFITS

Passenger Benefits
Faster complaint resolution, personalized responses, and gamification improve satisfaction and
engagement.
Operational Benefits:
AI speeds up complaint handling, enhances accuracy, and reduces future issues via predictive
maintenance.

Social Impact
Multi-language support increases inclusivity, serving passengers from diverse backgrounds.
Redefining the customer service by addressing the passenger's unique needs and strengthening
the bond between the government and its citizens.

@SIH Idea submission- Template 5


Seeders REFERENCES

1. https://www.sciencedirect.com/science/article/abs/pii/S2210970621000317
2. http://dira.shodhsagar.com/index.php/j/article/view/71
3. https://ieeexplore.ieee.org/abstract/document/10403169
4. https://transparencyindia.org/wp-content/uploads/2019/05/Indian-Railways-Comp-min.pdf

@SIH Idea submission- Template 6

You might also like