about 3 years ago
Hello, rescue & recovery innovators!
We’re pumped about the awesome response the Bluemixathon has been getting from technologists and disaster relief experts alike. In particular, we’re grateful to have the support of CrisisMappers, Recovers, and Kopernik as partners for this challenge. CrisisMappers is a humanitarian technology network, and their site has tons of informational and GIS resources (it’s also another great place to look for hackathon teammates — just register as a member). Recovers is a free web app for organizing relief efforts; check out the TED talk about its founding by Morgan and Caitria O’Neill. Kopernik connects technology with in-need communities to reduce poverty. If you’re in need of inspiration, these three organizations provide a fertile source!
Speaking of inspiration: We’ve done a bit of brainstorming and have come up with some potential app ideas to help you get started. These are just suggestions; you can, of course, continue to work on something you’ve already started, or take a piece of one of these ideas and combine it with something else.
Pro tip: There’s a Bluemix tool suitable for each of these app suggestions. We’ve created a tools glossary with all the relevant information and links.
Need more help? No problem!
- Triage incoming voicemail messages to high/medium/low urgency levels and then funnel them to disaster support teams. Tool: Alchemy
- Combine the Alchemy API with the Speech To Text service to process voicemails before the data is processed through Alchemy. Tool: Alchemy, Speech To Text
- Build a FAQ or breaking news app in which rescue teams can enter the latest updates and minimize the amount of time they spend answering the same questions. Tool: Question and Answer
- Categorize and assess charges for basic necessities to identify incidents of price gouging. Tool: Alchemy
- Build a dictionary of common location terms and local vernacular to assist rescue teams in quick response to incoming reports. Tool: Concept Expansion
- Build an app for simple emergency evacuation and other details provided in spoken instruction rather than written text. Tool: Watson Dialog Service
- Provide audio emergency information; could help populations that cannot read for whatever reason. Tool: Text to Speech
Staff Training and Resource Coordination
- Build an index of field teams and their support levels to assess what / whom is available. Tool: Concept Expansion
- Assess group dynamics to identify where more support is needed to ensure different groups remain calm and focused on rescue attempts; identify areas of panic to ensure rescue focus on maintaining calm and order. Tool: Watson Personality Insights
- Determine where medical staff is most urgently needed, or where support teams and supplies are needed most. Tool: Tradeoff Analytics
- For recurring disasters (such as in areas prone to wildfires or hurricanes), pull from previous recovery data to refine current recovery activities. Tool: Cognitive Insights
Damage Assessment & Relocation Efforts
- Allow animal control groups to track where unattended pets are being sent, and allow owners to retrieve them more quickly. Tool: Tradeoff Analytics
- Help evacuate patients from nursing homes, and determine (and track) the best relocation options. Tool: Tradeoff Analytics
- Allow first responders to quickly assess damage using cell phone photographs; could be used by persons directly impacted by the disaster to record impact for insurance purposes or to ask for help in assessing whether buildings or other assets are safe for re-entry and use. Tool: Visual Recognition
- Create real-time maps that identify what is happening in the affected area: crime, injuries, supply needs. Could be used to identify where grassroots support is available, and which areas need formalized help. Tool: Cognitive Graphs
- Build a first responder (or insurance) triage app. Tool: Cognitive Insights
- Assess progress toward recovery phase (i.e. where are supplies, where are power sources, shelter locations, etc.).Tool: Cognitive Insights
Build smart apps that leverage natural language processing and computer vision to deeply understand the world's conversations, documents, and photos.
A service provided by Cognitive Scale, Cognitive Graphs are an encapsulation of knowledge, sourced from third party, internal, and private data sources, using domain-specific models, into a query-able graph representation.
The Concept Expansion service analyzes text and interprets its meaning based on usage in other similar contexts. For example, it could interpret "the Big Apple" as meaning "New York City." It can be used to create a dictionary of related words and concepts so that euphemisms, colloquialisms, or otherwise ambiguous phrases can be better understood and analyzed.
A service provided by Cognitive Scale, Cognitive Insights are contextually relevant and personalized observations or predictions, presented with a recommendation, with the purpose of invoking user action. An insight serves to augment the knowledge, perception, and awareness of the end user, with the goal of improving their efficiency, decisions, and ability to quickly react to emerging scenarios.
The IBM Watson Dialog Service allows developers to design the way an application interacts with an end user through a conversational interface.
Watson Personality Insights derives insights from transactional and social media data to identify psychological traits which determine purchase decisions, intent, and behavioral traits; utilized to improve conversion rates.
Interprets and answers user questions directly based on primary data sources (brochures, web pages, manuals, records, etc.) that have been selected and gathered into a body of data or “corpus.” The service returns candidate responses with associated confidence levels and links to supporting evidence. The current data on Bluemix focuses on the Travel and Healthcare industries.
The Text to Speech service processes text and natural language to generate synthesized audio output complete with appropriate cadence and intonation.
Tradeoff Analytics helps people make better choices while taking into account multiple and often conflicting goals that matter when making that choice. Tradeoff Analytics uses Pareto filtering techniques in order to identify the optimal alternatives across multiple criteria. It then uses various analytical and visual approaches to help the decision maker explore the tradeoffs within the optimal set of alternatives.
The Visual Recognition service enables analysis of the visual appearance of images or video frames to understand what is happening in a scene. Using machine learning technology, semantic classifiers recognize many visual entities, such as settings, objects, and events. The service applies these pre-learned models to imagery that you have uploaded to the service and returns a score for each image for each model, indicating the likelihood of that visual element being present in the image.