DecodeX
Home/Problem Statements/SIH26097
All 226 Statements
SIH26097SoftwareAgriculture, FoodTech & Rural Development
₹1,50,000 Prize (₹75k Joint)
•
Deadline: 20 September 2026
•
Submitted Ideas: 0/500

AI-Driven voice Assistant for livelihood Mapping and NSQF-Aligned Skilling Recommendations for SC Communities under GIA component of PM-AJAY

Ministry / Organization: Ministry of Social Justice and Empowerment (MoSJE)
Department: Department of Social Justice and Empowerment
SIH Official Portal
Technical Complexity
8/10
Dataset Accessibility
7/10
36h Hackathon Viability
9/10
Step 0 • Zero-Jargon Layman Summary

“Many members of Scheduled Caste communities struggle to find the right government-sponsored job training because existing applications are text-heavy, English-driven, and hard to use. We are building a friendly, voice-based AI assistant that speaks local languages and dialects to converse with people, understand their background, and match them with the best job training and livelihood schemes available nearby.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

An AI-powered multilingual voice assistant platform with an omnichannel deployment strategy (Web/Mobile app, IVR phone calls, WhatsApp voice notes, and offline kiosk mode) backed by an NSQF (National Skills Qualifications Framework) alignment engine and district-level labor market analytics dashboard.

Step 2

WHO IS IT FOR?

Primary beneficiaries are SC community members seeking livelihood and skilling. Secondary users include ground-level social workers, District Welfare Officers, and officials from the Ministry of Social Justice and Empowerment (MoSJE) managing the PM-AJAY GIA component.

Step 3

WHY DOES IT EXIST?

Beneficiaries face severe digital and language barriers when navigating complex text portals. Furthermore, there is a systemic disconnect between traditional family occupations, individual capabilities, local market demands, and government training programs, resulting in high dropout rates and poor employment outcomes.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

Voice inputs and audio notes in regional languages and rural dialects, user demographic details, educational background, geographic location, and structured datasets of NSQF-certified courses and local job market demand maps.

02 • Processing & AI Core

Speech-to-text transcription via Whisper/indic models, intent extraction and psychological profile matching using LLMs, multi-criteria decision analysis mapping user traits against local NSQF courses, and offline-first edge database caching.

03 • Actionable Deliverables

Empathetic voice guidance in local dialect, a personalized beneficiary skill passport, recommended NSQF-aligned training programs, self-employment/wage-employment pathways report, and administrative dashboards for MoSJE officials.

Step 5

CONSTRAINTS

  • Must operate seamlessly in low-connectivity and 2G rural network environments
  • Must support diverse regional accents, low-resource Indian languages, and local dialects
  • Must run lightweight inference on edge devices or cheap feature-phone IVR gateways
  • Must comply with national data privacy and secure storage norms for citizen data
Step 6

JURY METRICS

  • Speech recognition and intent classification accuracy across dialects
  • End-to-end voice interaction latency (<2 seconds for IVR/WhatsApp responses)
  • Relevance score of NSQF course recommendations against beneficiary profile
  • User interface simplicity, empathy score, and accessibility for low-literacy users
Step 7

CORE BOTTLENECK

Handling low-resource rural Indian dialects and processing voice inputs accurately under high background noise and intermittent 2G network constraints.

Why You Should Choose This PS (Pros)

  • Extremely high social impact addressing grassroots financial inclusion and upliftment
  • Direct alignment with an active government scheme (PM-AJAY), maximizing real-world implementation value
  • Clear, modular deliverables ranging from voice interfaces to admin dashboards and IVR integration
  • Strong emotional resonance and 'wow factor' during live demonstrations involving regional voice interactions

Challenges & Risks to Watch (Cons)

  • Speech-to-text models can hallucinate or fail on rare rural dialects without fine-tuning
  • Integration with live telecom IVR systems or WhatsApp Business APIs can be tricky within a 36-hour window
  • Crowded domain if teams build standard chatbots instead of a deeply localized voice assistant
Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile
React.js / Next.js for web dashboardFlutter for cross-platform mobile/kiosk appTailwind CSS
Backend & APIs
FastAPI / Python for high-performance async APIsNode.jsWebSockets for real-time audio streaming
AI / ML & Models
OpenAI Whisper / IndicWhisper for multilingual speech-to-textCoqui TTS / ElevenLabs / Bhashini API for voice generationLlama-3 / DeepSeek-R1 for conversational profile extraction and RAG
Database & Cloud
PostgreSQL with pgvector extension for semantic search of NSQF coursesRedis for session and cache managementMinIO for audio recording storage

Killer Features to Impress the SIH Jury

Dialect-Adaptive Conversational Engine: Seamlessly switches between Hindi, regional languages, and local rural dialects with empathetic, human-like pacing.
Omnichannel Fallback (IVR & WhatsApp): Works via smartphone apps, simple missed-call IVR call-backs, and WhatsApp voice notes for feature-phone users.
Automated NSQF Skill Passport: Instantly generates a visual, downloadable skill gap analysis and training roadmap for ground workers.
District Heatmap Analytics: An administrative command center for MoSJE officials showing skill demand versus training supply across blocks and districts.
View Official SIH 2026 Portal Raw Text
▼
•Background
•The Pradhan Mantri Anusuchit Jaati Abhyuday Yojana (PM-AJAY) aims to reduce poverty among Scheduled Caste (SC) communities through livelihood promotion, skill development, and enterprise support under its Grant-in-Aid (GIA) component. A major challenge in implementation is the identification of appropriate skill training pathways that align with both the aspirations of beneficiaries and the actual livelihood opportunities available in their local regions.
•Many target beneficiaries face barriers such as low digital literacy, limited awareness of modern trades, language constraints, and difficulty navigating text-heavy digital systems. As a result, there is often a mismatch between enrolled training programs and the beneficiary’s interests, capabilities, or local market demand, leading to high dropout rates and poor post-training employment outcomes.
•To improve inclusion and effectiveness, there is a need for an AI-enabled conversational system that can interact naturally in regional languages and dialects, understand beneficiary aspirations, assess skill gaps, and recommend suitable NSQF aligned livelihood opportunities in and around the beneficiary.
•Basic Issues under GIA Component:
•Lack of proper road map and Planning of the Perspective plans from execution to implementation
•Identification of the participants Trained and skilled Financial consultants
•Job placement issue after the skilling programme
•Coordination Issues among the corporation, Ministry/Departments
•Inadequate Technical and support team at ground level
•Detailed Description The proposed solution should be an AI-driven, multilingual, voice-based virtual livelihood assistant capable of conducting conversational interviews with beneficiaries from aspirational SC communities. Instead of relying on traditional form-filling methods, the system should use voice interactions to collect information such as:
•Educational background
•Existing or traditional family occupations
•Current livelihood activities
•Skills and interests
•Mobility and physical constraints
•Preference for self-employment or wage employment
•Local economic realities and opportunities The assistant should support regional languages and dialects to ensure accessibility for users with low literacy or limited digital exposure. The interaction should feel empathetic and conversational rather than administrative.The collected information should be analyzed using AI/MLbased profiling and recommendation mechanisms to identify:
•Suitable NSQF-aligned training programs
•Relevant trades and livelihood pathways
•Skill gaps requiring intervention
•Region-specific employment or enterprise opportunities The system should also function effectively in lowconnectivity and low-tech environments through deployment channels such as:
•IVR-based phone calls for feature phone users
•WhatsApp voice-note interfaces Lightweight mobile or kiosk-based solutions

•

EXPECTED SOLUTION

An AI-powered multilingual voice assistant application designed to help SC beneficiaries under PM-AJAY identify suitable skill training and livelihood opportunities.The app will support regional languages and local dialects, allowing users to interact through simple voice conversations instead of text-based forms.