A digital platform to crowdsource societal challenges and facilitate collaborative problem solving through universities and industry partnerships
Governmcnt of Jharkhand · Disaster Management · Software
Seven modules, four user types and a text classifier at the centre of it — this is a coordination portal whose value a judge has to imagine, so only take it if you intend to make deduplication and expertise matching genuinely good and let the rest be thin.
What it actually is
Ordinary people notice local problems long before anyone official does, but there is no way for them to hand those problems to someone who could actually solve them. Meanwhile universities have students looking for real projects and companies have money and equipment. The ask is a platform where citizens submit local problems and the right university and industry partner get matched to them.
What to build
A challenge intake and routing platform with a citizen submission interface accepting photographs, video, location and documents from individuals, panchayats, urban local bodies and departments, an automatic classification layer assigning each submission to one of the thematic domains the statement lists and deduplicating repeat reports of the same issue, routing logic matching validated challenges to universities by discipline, research centre and faculty specialisation, a university module for forming teams and submitting solution proposals, an industry module for mentorship, funding and prototyping partnership, project lifecycle tracking through milestones and validation, an analytics dashboard on submissions, participation and outcomes by district, and a notification layer connecting all four parties.
Smallest thing that wins the room
Submit a photo-and-location problem as a citizen, watch it classify and deduplicate against two similar existing reports, and see it routed automatically to the university department whose faculty expertise matches, with the notification landing on the university dashboard.
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.
Quieter than 3% of the 226 · #219 of 226 by expected field · reaches the 500 cap
Forecast to blow past the 500-idea cap. Submissions close when it fills, so late teams may not get in at all.
Why: state governments drew the biggest crowds in 2025.
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.
Acceptance potential
2/5This is a coordination portal whose only technical substance is a text classifier, structurally the same shape as the placement and marketplace portals that judges see repeatedly, and it is meta — a platform for organising problem-solving rather than solving a problem, which is a much harder thing to make anyone care about in a five-minute pitch.
Feasibility
4/5Nothing here is technically out of reach — submission, text classification, deduplication and workflow routing are all standard, and the classification can be trained on public civic complaint corpora, though matching problems to faculty expertise needs an institutional capability directory that does not exist and would have to be assembled.
Innovation scope
2/5Seven components are enumerated in full, each with its own capability list, so the platform architecture is entirely determined and your only real design decisions are inside the classification and routing logic.
Clarity
4/5The modules, the stakeholder types, the thematic domains and the analytics contents are all specified in detail, but the statement never defines what a good routing decision is or how solution quality is judged, which is the outcome the whole platform exists to produce.
Effort
MassiveA citizen app, a classification and deduplication engine, a routing service, separate university and industry portals, a project lifecycle tracker, an analytics dashboard and a notification system is seven products for four distinct user types, and even stubbing them all consumes the whole event.
Demo-ability
MediumThe submit-classify-route sequence is demonstrable and the deduplication moment is mildly satisfying, but nothing here produces an outcome a judge can feel — the platform's actual value only materialises months later when a project finishes.
In its favour
- Green flag: Deduplication of near-identical citizen reports is a genuinely useful and demonstrable capability, and it is the one part of this statement with real technical content — twenty people reporting the same broken handpump should become one challenge, not twenty
- Green flag: Public civic complaint corpora exist, so the classifier can be trained and evaluated on real citizen-written text rather than synthetic samples
- Green flag: The NEP 2020 framing gives the statement institutional backing that a state sponsor will recognise
- Green flag: Because the statement never defines a good routing decision, a team that builds a defensible expertise-matching model has room to make that the substance
Against it
- Red flag: The platform organises problem-solving rather than solving anything, so in a five-minute pitch you are asking a judge to imagine the value rather than see it
- Red flag: This is structurally identical to the placement and collaboration portals that appear at every hackathon, and judges recognise the shape immediately
- Red flag: Faculty expertise directories for Jharkhand's institutions do not exist as data, so the routing module — the whole point of the platform — runs on a directory you fabricated
- Red flag: Seven modules for four user types is far beyond what can be built well, and the usual outcome is seven login screens and one working flow
What you will be writing
- multilingual text classification for domain routing
- sentence embedding deduplication of similar reports
- faculty expertise directory with semantic matching
- Django multi-tenant portal with role separation
- PostGIS district-level submission analytics
- notification fan-out via email and SMS
- Civic engagement platforms
- Academia-industry collaboration
- Workflow and routing systems
Prior art to read before you start
citizen problem crowdsourcing and routing · automatic complaint classification and deduplication · multi-stakeholder collaboration portal
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.