A web application that ingests mixed-format daily progress reports, links them to L5/L6 schedule activities using an LLM, and updates project timelines.
Oil India Limited · Software
Signing in saves it for your whole team — everyone on your invite link sees the same two entries. Anything you shortlisted while signed out comes with you.
Decomposed from what the description asks for. Nothing added.
Multi-Format Ingestion
Ingest heterogeneous inputs like free-text reports, spreadsheets, and schedule exports.
Conversational Interface
Provide a voice or chat interface for site supervisors to log activity start and end times.
Fuzzy Matching Engine
Link extracted discipline descriptions to the correct plan node and flag unmatched activities.
Schedule Auto-Update
Update actual start and end dates in the PMIS with a confidence score and audit trail.
Execution Repository
Produce a structured dataset for live analytics and historical project memory.
Both columns are read off the brief's own wording. Nothing here is inferred from the ministry's name.
The jury will check whether your prototype can successfully ingest at least two or three varied input formats, correctly perform fuzzy matching to link them to schedule nodes, and generate a clear audit trail for the updates.
A jury can still ask about these. Decide them deliberately rather than by accident.
Generated from the brief's own wording and the competition's published rules — never from a guess about what this ministry prefers.
Exact schema of the Primavera or MS Project exports?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Specific taxonomy of discipline-wise terms used by Oil India?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Target latency for the fuzzy matching and schedule update?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Has any part of this been shown at a previous event, hackathon or college project?
The guidelines are explicit: your solution must not have appeared in any previous event or programme, of any sort. A recycled project is what a team under time pressure reaches for.
Each one is quoted from a gap in the brief, not a guess about your team.
No dataset provided
The description depends on real data, and the organisers have not attached a dataset link.
Needs data you may not get
Sample daily progress reports and schedule extracts are mentioned as shareable only under NDA, requiring teams to work with synthetic data.
What the organisers attached, and what the brief assumes you can get.
Same organisation, same year. Reading two of theirs tells you more about what they care about than reading one.
Pick what you are about to do and copy the prompt. It carries the organisers' own wording, the constraints they never spell out, and an instruction not to invent requirements they never set.
Who has this problem, what already exists, and what you would have to find out.
The brief asks for multi-format ingestion. How would you build that?
Decoded from SIH26122 itself — Ingest heterogeneous inputs like free-text reports, spreadsheets, and schedule exports. The brief asks for it by name.
The brief asks for conversational interface. How would you build that?
Decoded from SIH26122 itself — Provide a voice or chat interface for site supervisors to log activity start and end times. The brief asks for it by name.
The brief asks for fuzzy matching engine. How would you build that?
Decoded from SIH26122 itself — Link extracted discipline descriptions to the correct plan node and flag unmatched activities. The brief asks for it by name.
The brief asks for schedule auto-update. How would you build that?
Decoded from SIH26122 itself — Update actual start and end dates in the PMIS with a confidence score and audit trail. The brief asks for it by name.
The brief asks for execution repository. How would you build that?
Decoded from SIH26122 itself — Produce a structured dataset for live analytics and historical project memory. The brief asks for it by name.
Where does your data come from — a published source, one you collect, or one you generate?
No dataset is attached to this problem statement, so sourcing it is part of the work and nobody told you that.
Why not use what already exists? Name the closest thing to this that is already running.
A team that has not named the alternative themselves is answering this for the first time in the room.
Which single thing will you demonstrate end to end, start to finish, with nothing skipped?
Ours, not a rule: a narrow thing that fully works survives questioning better than a broad thing that half works. If nobody on the team can name it, that is the finding.
Show me this working: the jury will check whether your prototype can successfully ingest at least two or three varied input formats, correctly perform fuzzy matching to link them to schedule nodes, and generate a clear audit trail for the updates.
This is the evaluator read for your problem statement, decoded from the brief's own wording.