Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26165Worth consideringacceptance 3/5

AI/NLP Engine to Detect Serious Injury & Fatality (SIF) Precursors in OIL's Unsafe-Act/Unsafe-Condition and Near-Miss Reports

Oil India Limited · Miscellaneous · Software

Well-specified and grounded in real safety science, but with no OIL data provided you train on constructed labels — build the Life-Saving Rule tagging against the published framework, handle the class imbalance deliberately, and be clear about what your classifier was validated on.

What it actually is

Companies collect thousands of safety observation and near-miss reports, but review them manually and late, and crucially most incidents are minor — only about a fifth carry genuine potential to kill someone. The ask is an engine that reads these free-text reports, flags the ones with real fatal potential, tags each to the relevant life-saving rule, and shows where fatal risk concentrates.

What to build

An NLP engine ingesting free-text safety reports that classifies each as SIF-potential — carrying serious-injury-or-fatality potential — versus non-SIF, tags each report to the relevant IOGP Life-Saving Rule such as Energy Isolation, Hot Work, Confined Space or Line of Fire, extracts recurring precursor patterns by activity, location and barrier failure, and presents an interactive dashboard ranking sites and activities by SIF-precursor density so the safety team can direct interventions where fatal potential is genuinely highest rather than where reports are merely numerous.

Smallest thing that wins the room

Feed in a batch of safety reports and show the engine separating the handful with genuine fatal potential from the routine majority, tagging one confined-space report to the correct Life-Saving Rule, and the dashboard ranking one site as high-priority because its SIF-precursor density is elevated.

How crowded this one gets

A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.

Moderate110–250 teams expectedroughly 1 in 92–213 wins it

Quieter than 63% of the 226 · #85 of 226 by expected field

A normal-sized field. Your idea has to be good, not miraculous.

Why: company-sponsored statements drew the smallest fields of all.

This is a guess, not a fact

Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.

The scores

The number is the shorthand. The line under it is the reason.

What you will be writing

  • Transformer text classification (SIF vs non-SIF)
  • Multi-label Life-Saving Rule tagging
  • IOGP Life-Saving Rules + EEI SIF framework
  • Precursor pattern mining (activity/location/barrier)
  • Class-imbalance handling for the SIF minority
  • Interactive risk-density dashboard
  • Process safety
  • Occupational health and safety NLP
  • Risk analytics

Prior art to read before you start

SIF precursor classification · safety report text mining · life-saving rule tagging

Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.