AI-powered wearables for people with disabilities

Background

Most assistive technology is built for the "average" user with a given disability. But no two bodies or routines are the same. Two people with epilepsy, Parkinson's or chronic pain can have completely different triggers, warning signs and patterns.

Wearables already collect a steady stream of personal data: heart rate, movement, sleep, skin temperature. Today, most of it becomes generic step counts and alerts. For someone with a disability, it could be an early warning system, if it learned that one person's baseline and flagged when something was about to go wrong.

The cloud makes this possible. Models can keep learning from weeks of one person's data, and the results can be shared with caregivers and clinicians. The challenge is to build technology that adapts to the person, instead of making the person adapt to the technology.

Who you are designing for

One specific person living with a disability or chronic condition. Pick a real profile and research it properly. Around them are caregivers, family and clinicians who need the right information at the right moment, without being flooded.

What your concept should cover

1. What it senses. Which signals matter for this person, and what form does the device take?
2. How it learns "normal". How long does it take to learn one person's baseline, and how does it adjust as they change?
3. What counts as a warning. What patterns signal trouble ahead, and how early can it flag them?
4. What happens next. Who is told, how, and what can they actually do to prevent the problem?
5. Why AI and the cloud. What does each one do that the device on its own couldn't?

Things to think about

• The person stays in control. Who can see their data, and can they switch sharing off?
• Alert fatigue. A wearable that buzzes constantly gets taken off.
• Not a diagnosis. Where does your product stop and a clinician take over?
• Accessible by design. Can the device and its alerts be used by someone with limited mobility, vision or hearing?
• Battery, comfort and cost. The best model is useless if the device isn't worn.

What to deliver

Problem research

Who is affected, how often, what they do today and why it fails. Cite your sources.

A user and their journey

One specific person, before and after your solution, as a storyboard or journey map.

Concept architecture

A diagram of what data goes in, what the AI does, and how it all connects. No code required.

Mock-ups

Screens, a no-code prototype or a physical sketch, so the judges can picture it.

A 10-minute pitch

Including impact, feasibility and risks. Every member ready for Q&A.

Qwen is a strong research partner: use it to explore the problem, then check what it tells you against real sources.

How it's judged

Two judges score every team on this problem statement out of 100, using the non-technical track rubric.

1. Problem insight25 pts

   Real research: who exactly is affected, how often, why it matters, and what they do today.

2. Solution & user journey25 pts

   A clear concept someone can picture, shown through mock-ups, a storyboard, a prototype or a user flow.

3. Technology & AI reasoning20 pts

   Why AI and technology suit this problem, what they contribute, and roughly how information would flow through the solution.

4. Feasibility & impact15 pts

   Honest about risks, cost, implementation and adoption, and clear about what measurable success looks like.

5. Pitch15 pts

   Persuasive, structured, on time, and confident under questions.

Judges reward appropriate use of AI, not complexity for its own sake. Using Alibaba Cloud, Qwen or Qoder is supported but not required to score well.

Draft · final weights are confirmed before the workshops. Compare both track rubrics